Abstract

A task unloading method based on unmanned aerial vehicle cooperation is provided. The method includes: establishing an unmanned aerial vehicle cooperation task unloading system; establishing, for each of ground users, a local task unloading model of the ground user; establishing, for each of the ground users, an unmanned aerial vehicle task unloading model of the ground user; establishing a hovering model of the unmanned aerial vehicles; and calculating an optimal task unloading assignment solution by using a second price auction algorithm to perform task unloading. With the method, task unloading is performed based on unmanned aerial vehicle mobile edge computing, improving the quality of service and the service experience of the users.

IPC Classes  ?

• G06F 9/50 - Allocation of resources, e.g. of the central processing unit [CPU]
• G06F 9/48 - Program initiatingProgram switching, e.g. by interrupt

Abstract

A secure industrial data transmission method based on an international data space, which method belongs to the technical field of industrial Internet-of-Things data security. The method comprises: constructing a production workshop industrial data management system, receiving from MetaData Broker an industrial data request that is sent by an IDS connector of an industrial data consumer, and forwarding the industrial data request to a target IDS connector corresponding to a target industrial data provider; the target IDS connector performing identity authentication, and if the identity authentication is successful, the target industrial data provider calling a corresponding data resource on the basis of the industrial data request, and performing AES encryption processing and BASE64 code conversion on the called data resource, so as to obtain request resource data; and the IDS connector following a formulated interaction contract to complete data transmission, and the industrial data consumer performing reverse processing on the received request resource data, so as to obtain an original data resource. The method can provide a secure and trusted transmission environment.

IPC Classes  ?

• H04L 67/12 - Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks

Abstract

The present disclosure provides a method and apparatus for generating an aerial view of a vehicle, a storage medium, an electronic device, and a vehicle. The method comprises: obtaining a road scenario image set of a plurality of directions acquired by a vehicle-mounted camera of a target vehicle; preprocessing the road scenario image set into a target image set of a target size, and obtaining camera parameters of the vehicle-mounted camera; using a convolutional network to extract multi-scale image features of the target image set, and using the central point of the target vehicle as an original point to create a three-dimensional coordinate grid; and using the multi-scale image features, the camera parameters, and the three-dimensional coordinate grid to generate an environment aerial view of the target vehicle.

IPC Classes  ?

• G06T 17/00 - 3D modelling for computer graphics
• G06T 7/80 - Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
• G06T 19/20 - Editing of 3D images, e.g. changing shapes or colours, aligning objects or positioning parts
• G06N 3/0464 - Convolutional networks [CNN, ConvNet]
• G06V 20/56 - Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
• G06V 10/44 - Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersectionsConnectivity analysis, e.g. of connected components
• G06V 10/52 - Scale-space analysis, e.g. wavelet analysis
• B60R 1/27 - Real-time viewing arrangements for drivers or passengers using optical image capturing systems, e.g. cameras or video systems specially adapted for use in or on vehicles for viewing an area outside the vehicle, e.g. the exterior of the vehicle with a predetermined field of view providing all-round vision, e.g. using omnidirectional cameras

Abstract

The present invention relates to an intelligent recognition method for job contents of barbershop employees, which belongs to the technical field of machine vision, comprising the following steps: S1: setting installation locations and installation conditions for collection devices; S2: establishing a label set of barbershop employee faces and customer faces, and training a face recognition model; S3: establishing an action label set related to items, tools and people, and training a barbershop action behavior recognition model; S4: conducting action behavior recognition for a practical barbershop service scenario by using the trained face recognition model and the barbershop action behavior recognition model; and constructing behavior sequences of “action pairs” involving elements from customers, employees and actions; S5: establishing a job content recognition label; and constructing a deep neural network model for job content recognition to determine service job contents of barbershop employees for customers. The present invention facilitates efficient intelligent management of barbershops through an intelligent recognition method for job contents of barbershop employees.

IPC Classes  ?

• G06V 40/20 - Movements or behaviour, e.g. gesture recognition
• G06V 10/774 - Generating sets of training patternsBootstrap methods, e.g. bagging or boosting
• G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
• G06V 40/16 - Human faces, e.g. facial parts, sketches or expressions

Abstract

The present invention relates to a blockchain-based multi-tenant distributed leasing method for satellite network resources, which belongs to the field of mobile communication. The method includes: S1: constructing a multi-tenant business ecosystem for satellite network resource leasing; S2: constructing a blockchain-based leasing mechanism for satellite network resources, specifically: S21: constructing a dual leasing mechanism for satellite network resources; S22: constructing a blockchain-based resource leasing mechanism; S23: obtaining reputation value of a participant: first calculating reputation score of the participant, then combining transaction fees to ensure honesty of the participant, and finally using a sliding window to ensure that the selected leader is an honest participant who contributes consistently. The present invention combines reputation with a blockchain-based leasing mechanism to prevent intermediate entities from manipulating transaction results, which improves the transaction throughput of the system and reduces transaction latency.

IPC Classes  ?

• H04L 41/0895 - Configuration of virtualised networks or elements, e.g. virtualised network function or OpenFlow elements
• H04L 12/14 - Charging arrangements
• H04L 41/0893 - Assignment of logical groups to network elements
• H04W 84/06 - Airborne or Satellite Networks

Abstract

The invention relates to a preparation method of Na+/Cu2+ ions co-doped cesium lead bromide perovskite quantum dots, products and applications thereof, which belongs to the technical field of modification research of perovskite quantum dots. The invention discloses a preparation method of Na+/Cu2+ ions co-doped cesium lead bromide (CsPbBr3) perovskite quantum dots, which adopts lead bromide (PbBr2), oleic acid (OA), oleylamine (OAm), sodium ion precursors and copper ion precursors for the reaction preparation in octadecene (ODE), in which copper ions (Cu2+) and sodium ions (Na+) substitute A and B crystal sites in cesium lead bromide (CsPbBr3) perovskite fluorescent quantum dots respectively. The quantum dots have been effectively improved in photoluminescence quantum yield, thermal stability, etc., and can be used as an active layer to fabricate light emitting diodes which achieve the tuning of emission color from green to blue.

IPC Classes  ?

• C09K 11/66 - Luminescent, e.g. electroluminescent, chemiluminescent, materials containing inorganic luminescent materials containing germanium, tin or lead
• H10H 29/01 - Manufacture or treatment
• H10H 29/851 - Wavelength conversion means
• H10H 29/854 - Encapsulations characterised by their material, e.g. epoxy or silicone resins

Abstract

The present invention relates to the technical field of data communication, and relates to a precise time synchronization clock parameter estimation method based on optimal invariant estimation. In the present invention, in a communication scene where unknown random time delay distribution information is present, on the basis of a precise time protocol, timestamp interaction is achieved by means of bidirectional data packet transfer between a master node and a slave node, and a clock relation model between the master node and the slave node is established; considering that a plurality of intermediate devices exist in the data packet interaction process, resulting that random time delay distribution information cannot be accurately obtained, a Gaussian mixture model is used to model a random time delay distribution, a competitive expectation maximization algorithm is used to learn mixture model parameters; and finally, on the basis of the parameters obtained by learning, an optimal invariant estimation method is used to estimate a clock frequency offset and a clock phase offset simultaneously, so as to realize time synchronization between the master node and the slave node. The present invention improves the accuracy of clock frequency offset estimation and clock phase offset estimation, is suitable for a communication scene where unknown random time delay distribution information is present, and enhances the robustness of the synchronization algorithm to a communication time delay.

IPC Classes  ?

• H04J 3/06 - Synchronising arrangements

Abstract

The present invention relates to the technical field of wireless sensor networks, and to an average consistency time synchronization method based on a multi-hop virtual link and event triggering. According to the method, in the case that a communication delay is present in a wireless network, a least squares estimator is used to restrain the effect of the delay in the relative frequency offset estimation process; clock information of nodes is fully called by means of the multi-hop virtual link for update, thereby effectively increasing the clock synchronization speed; an event triggering policy is used to reduce a transmission frequency between the nodes, thereby effectively reducing communication overhead; and a consistency algorithm is used to update logic clock parameters of the nodes, thereby realizing global consistency of clocks of the nodes in a wireless sensor network. According to the present invention, the effect of the communication delay in the wireless sensor network is taken into consideration, an iterative least squares estimator is used to obtain a high-precision relative frequency offset value to improve the synchronization precision, and by using an interaction mechanism of the multi-hop virtual link and event triggering, the communication overhead is effectively reduced while increasing the convergence speed of a clock synchronization error.

IPC Classes  ?

• H04W 56/00 - Synchronisation arrangements

Abstract

The present disclosure relates to a curvature-based signal segmentation method for solar-blind ultraviolet (UV) photodetectors, including the steps of: collecting solar-blind UV radiation using solar-blind UV photodetectors according to a preset sampling time and generating the same into sampled signals; performing noise reduction on the sampled signals to generate filtered signals using a fractional calculus digital filter; calculating estimated curvatures of the filtered signals using a method of circle fitting by discrete points, and numerically optimizing the estimated curvatures using an exponential function to obtain curvature vectors of the filtered signals; and calculating weight coefficients and weighting the filtered signals using a moving average filter function and a binarization method according to the curvature vectors.

IPC Classes  ?

• G06F 17/16 - Matrix or vector computation
• G01J 1/42 - Photometry, e.g. photographic exposure meter using electric radiation detectors
• G06F 17/11 - Complex mathematical operations for solving equations

Abstract

The present invention relates to the technical field of communications, and in particular to an edge cache replacement method based on deep reinforcement learning, comprising: constructing a system network model; acquiring a caching state of an MEC server in the system network model, and on the basis of the caching state of the MEC server, calculating the total time delay for acquiring cached content by a single user; on the basis of the total time delay for acquiring the cached content by the single user, calculating the total time delay for acquiring the content by all users; constructing an optimization objective function on the basis of the total time delay for acquiring the content by the users; constructing a Markov decision on the basis of the objective function; and on the basis of the Markov decision, using a dynamic content replacement algorithm based on deep reinforcement learning to replace the cache of the MEC server. According to the present invention, for a scenario of dynamic change of popularity, a dynamic content cache replacement scheme is formulated in light of a deep reinforcement learning technology, and on the basis of the condition of a cache space of the MEC server, a system can obtain the minimum average time delay for acquiring the content by the users and find the most suitable cache replacement policy.

IPC Classes  ?

• H04L 67/5682 - Policies or rules for updating, deleting or replacing the stored data

Abstract

The present invention belongs to the field of time-sensitive networks (TSNs), and relates to a TSN routing and scheduling calculation method based on an improved particle swarm algorithm. The method comprises: on the basis of a fully centralized configuration model, a CNC generating a network topology; selecting from among all TSN streams a stream having a priority greater than or equal to PRI, and performing calculation to obtain several alternative paths; the CNC initializing transmission paths and first-frame sending moments of all the streams, so as to form a particle position; initializing several particles, and using a particle swarm algorithm to iteratively update each particle; and the CNC calculating a gating list for a switch on the basis of a solution that meets requirements, the CNC sending configuration information of a terminal device to a CUC, the CUC configuring the terminal device, and the CNC also configuring a gating time list for a TSN switch. The present invention improves the schedulability of a TSN, and also improves a particle swarm algorithm, such that the particle swarm algorithm is applicable to this calculation scenario; and the present invention improves calculation efficiency, thereby ensuring collaborative calculation of TSN routing and scheduling.

IPC Classes  ?

• H04L 45/00 - Routing or path finding of packets in data switching networks

Abstract

The present invention relates to the technical field of wireless communications, and particularly relates to an intelligent reflecting surface (IRS)-assisted non-orthogonal multiple access (NOMA) network transmission method based on hardware damage. The method comprises: building an IRS-assisted NOMA network system; building a base station transmission power minimization model on the basis of a user quality of service constraint, a successive interference cancellation constraint and a reflection phase shift constraint; solving the base station transmission power minimization model to obtain an optimal transmission solution; and the system performing transmission on the basis of the optimal transmission solution. An optimal transmission power result for multiple users under the NOMA technology and with the assistance of the IRS can be reflected, enhancing the robustness of the system.

IPC Classes  ?

• H04W 72/044 - Wireless resource allocation based on the type of the allocated resource
• H04W 72/541 - Allocation or scheduling criteria for wireless resources based on quality criteria using the level of interference
• H04W 72/543 - Allocation or scheduling criteria for wireless resources based on quality criteria based on requested quality, e.g. QoS
• H04B 17/391 - Modelling the propagation channel

Abstract

A multi-sensor fusion method and system for intelligent driving vehicles are provided, which relate to the technical field of intelligent driving vehicles. The method includes: establishing an extended target tracker based on a GM-PHD algorithm and a rectangular target model of a detected object; processing detection information of a millimeter-wave radar by using the extended target tracker to obtain millimeter-wave radar track information of the detected object; processing detection information of a laser radar by using the established bounding-box detector and a JPDA tracker provided with an IMM-UKF to obtain laser-radar track information of the detected object; processing the millimeter-wave radar track information and the laser-radar track information by performing time-space conversion to obtain a central fusion node; and processing the central fusion node by using an IMF algorithm to obtain global track information.

IPC Classes  ?

• G01S 13/86 - Combinations of radar systems with non-radar systems, e.g. sonar, direction finder
• G01S 13/72 - Radar-tracking systemsAnalogous systems for two-dimensional tracking, e.g. combination of angle and range tracking, track-while-scan radar
• G01S 13/931 - Radar or analogous systems, specially adapted for specific applications for anti-collision purposes of land vehicles
• G01S 17/931 - Lidar systems, specially adapted for specific applications for anti-collision purposes of land vehicles

Abstract

A collaborative task offloading and service caching method based on graph attention multi-agent reinforcement learning, which method belongs to the technical field of mobile communications. The method comprises: constructing an MEC system in an MEC network scenario where there are multiple base stations and diversified service requests; modeling a collaborative task offloading and service caching problem by taking as an objective the maximization of a system utility based on QoE; converting the collaborative task offloading and service caching problem into a decentralized partially observable Markov decision process; and using an algorithm based on graph attention multi-agent reinforcement learning to solve the decentralized partially observable Markov decision process obtained by means of conversion. By means of a simulation experiment, compared with a benchmark algorithm, significant improvements are made in terms of a cache hit rate, system utility and computation success rate to the algorithm proposed herein.

IPC Classes  ?

• H04W 28/08 - Load balancing or load distribution
• H04W 28/24 - Negotiating SLA [Service Level Agreement]Negotiating QoS [Quality of Service]
• H04W 28/14 - Flow control using intermediate storage

Abstract

The present invention includes techniques for data processing and particularly relates to a method and system for predicting human fall risk based on electronic nursing text (ENT) data. The method comprises the following steps: obtaining an ENT data set, pre-processing data in the ENT data set, and constructing a Morse Fall Scale (MFS) dictionary with the pre-processed data; extracting features from the ENT data of patients to be predicted with a natural language processing technology; analyzing the extracted text features by the MFS dictionary to obtain a data set of risk factors; training a decision tree algorithm by using the data set of risk factors to obtain a prediction result of the patient's fall risk; clustering and precisely nursing the patients according to the prediction result. The invention constructs the MFS dictionary through the electronic health records to obtain fall risk factors of the patients, and iteratively predicts their fall risks according to the risk factors, thereby improving the prediction efficiency.

IPC Classes  ?

• G06F 40/279 - Recognition of textual entities
• G16H 50/20 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
• G16H 50/70 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients

Abstract

The present invention relates to a target detection system based on a LiDAR and visual heuristic learning, which uses the difference between detection capabilities of two types of sensors in different scenarios to perform interactive heuristic learning on respective detection results, so as to improve the performance of two sensor detection models. The system comprises a visual target detection module, which is used for collecting visual data, performing target detection by means of a visual model-1, and sending to a heuristic learning module a detection result as visual pseudo label data; a LiDAR target detection module, which is used for collecting LiDAR data, performing target detection by means of a LiDAR model-1, and sending to the heuristic learning module a detection result as LiDAR pseudo label data; and the heuristic learning module, which is used for using an evaluator to evaluate visual target output pseudo label information and LiDAR target output pseudo label information, using a visual pseudo label to train a LiDAR model-2, using a LiDAR pseudo label to train a visual model-2, and respectively using the visual model-2 and the LiDAR model-2 to update the visual model-1 and the LiDAR model-1.

IPC Classes  ?

• G06V 10/774 - Generating sets of training patternsBootstrap methods, e.g. bagging or boosting

Abstract

A resource allocation method for an unmanned aerial vehicle-assisted edge computing network based on intelligent reflecting surface assistance, comprising: constructing an unmanned aerial vehicle-assisted edge computing network system model based on intelligent reflecting surface assistance; constructing a communication model, a time delay model and an energy consumption model; according to the communication model, the time delay model and the energy consumption model, constructing a maximum average throughput function; optimizing the maximum average throughput function by using successive convex approximation and block coordinate descent algorithms, and according to the optimized maximum average throughput function, calculating an optimal resource allocation result. The present application uses an intelligent reflecting surface to assist in an unmanned aerial vehicle-assisted network system, thereby increasing the channel gain of links between automobiles and unmanned aerial vehicles.

IPC Classes  ?

• H04W 16/22 - Traffic simulation tools or models

Abstract

A group switching method in an energy-saving mode. The access and switching of a user are dynamically managed by means of a grouping method, so that a sufficient number of services having sufficient quality are provided for existing users, the efficiency of switching is improved, cells are not overloaded, and resources are not wasted. The proposed group switching method mainly comprises: on the basis of a user service type, performing group partitioning on a switching user and an energy-saving compensation cell, dynamically partitioning a user group according to a magnitude relationship between resources required by a user and resources provided by the compensation cell, and accessing the user group.

IPC Classes  ?

• H04W 52/02 - Power saving arrangements

Abstract

The present invention belongs to the technical field of wireless communications and relates to a minimization of drive test (MDT) configuration coverage protection and user grouping method. The method comprises: performing information collection; receiving memory information of a UE; according to the memory information of the UE, determining whether it is possible to store both LTE extended configuration information and NR extended configuration information; if both the LTE extended configuration information and the NR extended configuration information can be stored, sending configuration content of the two pieces of configuration information to the UE; and if it is not possible to store both the LTE extended configuration information and the NR extended configuration information, determining whether one piece of the LTE extended configuration information and the NR extended configuration information can be stored. The present invention is applicable to a large-scale wireless sensor network, and solves the problem of logged MDT configuration coverage to a certain extent.

IPC Classes  ?

• H04W 24/02 - Arrangements for optimising operational condition

Abstract

An intelligent reflecting surface assistance-based task unloading and resource allocation method for an unmanned aerial vehicle mobile edge computing network system, comprising: constructing an intelligent reflecting surface-assisted unmanned aerial vehicle mobile edge computing network system model; constructing an intelligent reflecting surface-assisted unmanned aerial vehicle mobile edge computing network communication model ; according to the communication model, obtaining a time delay model and an energy consumption model; establishing a multivariable joint optimization model so as to minimize the energy consumption of an unmanned aerial vehicle; and using a deep reinforcement learning method to solve the objective optimization model. By means of intelligent reflecting surface assistance, joint optimized unloading decision and resource allocation, the present application effectively reduces the energy consumption of the unmanned aerial vehicle and improves the performance of the unmanned aerial vehicle network system.

IPC Classes  ?

• H04W 4/40 - Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P]

Abstract

A joint optimization method for path selection and gate scheduling in time-sensitive networking comprises S1, a CNC finding a TSN topology, and abstracting same into a network directed graph; S2, a terminal device sending to a CUC a TSN connection request, and the CUC sending same to the CNC; S3, the CNC selecting K shortest paths as alternative paths; S4, the CNC selecting m preferred paths; S5, the CNC finding an optimal transmission path for a TT stream, and finding a proper transmission path for a non-TT stream; S6, CNC completing traversal; S7, configuring a gate control list for the optimal transmission path of each pair of terminal devices; and S8, the CNC encapsulating a computation result into a gate scheduling table, configuring the gate scheduling table to a TSN switch, and then sending a traffic transmission computation result to the TSN terminal device.

IPC Classes  ?

• H04L 47/125 - Avoiding congestionRecovering from congestion by balancing the load, e.g. traffic engineering
• H04L 45/24 - Multipath
• H04L 45/302 - Route determination based on requested QoS

Abstract

A path planning method oriented to various parking scenarios, said method relating to the technical field of unmanned vehicles. The method comprises: building a vehicle kinematic model, and designing a multi-stage non-linear prediction control model; designing a multi-stage non-linear prediction controller, and designing a constraint function which takes as basic constraints the pose of a vehicle at a starting point, the pose of the vehicle at a target point, a parking speed, a parking steering angle, a non-holonomic kinematic constraint, and the minimum safe obstacle avoidance distance; integrating constraints of a parking system into an optimization control problem that satisfies the multi-stage non-linear prediction control model and the constraints of the parking system; and using an interior point method to solve the optimization control problem, so as to obtain an optimal control sequence, and applying elements in a first column in the sequence to vehicle low-level control. The present invention can ensure the controllability and accuracy of parking and can also improve the flexibility and efficiency of a parking process, thereby greatly optimizing the architecture of an automatic parking control system.

IPC Classes  ?

• B60W 30/06 - Automatic manoeuvring for parking

Abstract

The present invention relates to a vehicle-end dynamic blockchain-based information transmission method for the Internet of Vehicles, comprising: vehicles constructing in the Internet of Vehicles a dynamic blockchain network, so as to achieve a decentralized architecture. Each vehicle becomes a network node to jointly participate in transaction verification and blockchain management, improving system security and attack resistance. A vehicle stores data in a blockchain, and other vehicles obtain the data on the basis of consensus and verification, helping to drive vehicle systems and share traffic information. The vehicles may create the blockchain by means of lightweight software and infrastructure without a large amount of hardware investment and maintenance cost any more. The present invention uses the vehicles to construct the dynamic blockchain and implement identity authentication, so that the vehicles may have more autonomous control rights.

IPC Classes  ?

• H04L 9/00 - Arrangements for secret or secure communicationsNetwork security protocols

Abstract

A task unloading method based on unmanned aerial vehicle cooperation, relating to the field of unmanned aerial vehicles. The method comprises: constructing an unmanned aerial vehicle cooperation task unloading system; according to the number of CPU cycles which can be executed by a ground user in unit time and the number of CPU cycles of a task, creating a local task unloading model of the ground user; according to the transmitting power of the ground user, the number of CPU cycles which can be executed by MEC servers on an original unmanned aerial vehicle and a cooperative unmanned aerial vehicle in unit time and the number of CPU cycles of the task, creating an unmanned aerial vehicle task unloading model of the ground user; according to the hovering power and the hovering delays of the unmanned aerial vehicles, creating a hovering model of the unmanned aerial vehicles; and, according to the local task unloading model of the ground user, the unmanned aerial vehicle task unloading model of the ground user and the hovering model of the unmanned aerial vehicles, computing by using a second-price sealed-bid auction algorithm to obtain an optimal task unloading allocation solution so as to unload the task. The present invention uses unmanned aerial vehicle assisted mobile edge computing for performing task unloading, thereby improving quality of service and experience of service for users.

IPC Classes  ?

• G06F 9/445 - Program loading or initiating
• G06F 9/50 - Allocation of resources, e.g. of the central processing unit [CPU]

Abstract

An agent policy learning method with privacy protection in mobile edge computing, which belongs to the technical field of mobile communications. The method comprises: establishing an edge collaborative computing unloading model which comprises a service caching model, a task unloading model and a system cost model; on the basis of the edge collaborative computing unloading model, using the minimization of the processing cost of a task as a target to establish an optimization problem of joint task unloading, service caching, computing power resource allocation and transmission power control; abstracting an optimal problem into a partially observable Markov decision process; and on the basis of the Markov decision process, using a multi-agent deep reinforcement learning algorithm based on a federated learning method to autonomously learn a task unloading, service caching, computing power resource allocation and transmission power control policy. In the present invention, an edge collaborative computing unloading model is established, such that an agent network protects privacy security of data and sensitive information of users by means of training based on federated learning.

IPC Classes  ?

• H04L 67/10 - Protocols in which an application is distributed across nodes in the network

Abstract

A data sharing incentivizing method based on a blockchain and an evolutionary game theory, relating to the technical field of data sharing incentivizing mechanisms. The method comprises: constructing a data sharing incentivizing model; on the basis of the data sharing incentivizing model, computing expected gains of users adopting different strategies; computing a replicator dynamics equation on the basis of the expected gains of the users adopting different strategies; and solving evolutionarily stable state points on the basis of the replicator dynamics equation, and analyzing a stable state condition on the basis of the evolutionarily stable state points to obtain a sharing incentivizing scheme. The present invention can improve the user participation rate.

IPC Classes  ?

• H04L 67/104 - Peer-to-peer [P2P] networks

Abstract

A beam-forming optimization method and apparatus for an IRS-assisted MISO communication system, and an electronic device, which relate to the technical field of wireless communications. The beam-forming optimization method for an IRS-assisted MISO communication system comprises: establishing an IRS-assisted MISO communication system, wherein the communication system comprises an AP, an IRS and a user; with the target of recovering data s, which is sent to the user by means of the AP, constructing a problem P of jointly optimizing AP active beam-forming and IRS passive beam-forming; decomposing the problem P into a beam-forming vector optimization problem P1 and an IRS phase shift optimization problem P2; giving an IRS phase shift, and solving the beam-forming vector optimization problem P1; and according to an acquired optimal beam-forming vector, solving the IRS phase shift optimization problem P2, so as to finally obtain the original data s, which is sent to the user by means of the AP.

IPC Classes  ?

• H04B 7/06 - Diversity systemsMulti-antenna systems, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station

Abstract

The present invention relates to the field of big data recommendation, and in particular to a multi-party semi-supervised learning-based method for recommending financial products for potential users, for use in solving the problem that a financial product provider only has own data of positive samples and cannot perform recommendation. When the security and privacy of multi-party data are protected, multi-party unlabeled data is randomly sampled for multiple times to construct a binary classification dataset having balanced positive and negative samples, a vertical federated learning model based on a base learner is trained, reliable positive samples are selected from unlabeled sample data according to a prediction result, the process of dataset reconstruction sampling and model training prediction is iterated for multiple times, and a batch of reliable positive samples is selected. The method effectively solves batch recommendation of only a small number of positive samples and a large number of unlabeled samples, improves the reliability of recommendation, and achieves accurate batch recommendation of financial products for potential users.

IPC Classes  ?

• G06Q 30/0601 - Electronic shopping [e-shopping]

Abstract

The present invention belongs to the field of fluid-pipeline leakage detection, and relates to a fluid-pipeline leakage detection method based on an improved fuzzy twin support vector machine (FTSVM). The method comprises: acquiring acoustic vibration signals of a fluid pipeline under different degrees of leakage; performing feature extraction on the acoustic vibration signals indicating different degrees of leakage, and performing normalization processing on extracted feature data; and inputting normalized data into an improved FTSVM model, so as to obtain a pipeline leakage detection result. In the present invention, regional division is performed on a sample space by using the ratio of relative spatial distances of different samples, a theory of fuzzy data set is introduced into a noise and support vector aliasing region to perform distinguishing, and degree-of-membership assignment is also performed on a normal data region and a noise data region again, such that the present invention reduces the impact of noise data on an identification model, and also solves the defect of the robustness of the model being poor due to an FTSVM being unable to distinguish a support vector from noise data.

IPC Classes  ?

• G06F 30/20 - Design optimisation, verification or simulation

Abstract

A curvature-based solar-blind ultraviolet photodetector signal segmentation method, comprising: collecting solar-blind ultraviolet radiation according to a preset sampling time by using a solar-blind ultraviolet photodetector to generate a sampled signal; performing noise reduction on the sampled signal by means of a fractional calculus digital filter to generate a filtered signal; calculating a curvature estimated value of the filtered signal by using a method of fitting a circle with discrete points, and performing numerical optimization on the curvature estimated value by using an exponential function to obtain a curvature vector of the filtered signal; according to the curvature vector, solving a weighting coefficient by using a moving average filtering function and a binarization method, and weighting the filtered signal to obtain a plurality of non-zero discrete time domain segments; for the non-zero discrete time domain segments, eliminating an interference segment according to mean values and widths to obtain a candidate segmentation point signal; and setting a determination index according to the candidate segmentation point signal to determine upper and lower segmentation boundary points to segment and rectify the filtered signal to obtain a solar-blind ultraviolet photodetector signal.

IPC Classes  ?

• G01J 1/42 - Photometry, e.g. photographic exposure meter using electric radiation detectors
• G06F 18/10 - Pre-processingData cleansing
• G06F 18/213 - Feature extraction, e.g. by transforming the feature spaceSummarisationMappings, e.g. subspace methods

Abstract

The present invention belongs to the technical field of communications, and relates to a clustering routing method based on an optimal number of cluster heads and applied to satellite networking. The method comprises the following steps: S1, establishing a system module; S2, establishing a satellite-networking double-layer coverage model; and S3, establishing a clustering routing algorithm based on an optimal number of cluster heads and applied to satellite networking. The present invention provides a new clustering hierarchical structure system, in which an area formed by small satellite networking is a cluster; instead of full-area flooding, intra-cluster information is transmitted to a cluster head satellite after being processed; and the cluster head satellite, i.e., a low-orbit satellite node, delivers the intra-cluster information to a medium-orbit satellite, and the medium-orbit satellite delivers the intra-cluster information to a ground station or other cluster groups. A double-layer satellite network coverage model is formed. The aim of reducing the network throughput and network overheads is achieved.

IPC Classes  ?

• H04W 40/32 - Connectivity information management, e.g. connectivity discovery or connectivity update for defining a routing cluster membership

Abstract

The present invention relates to the technical field of trajectory prediction, and particularly relates to an automatic trajectory prediction method based on a graph spatial-temporal pyramid. The method comprises: pre-processing radar point cloud data collected in real time, so as to obtain an aerial view; processing the aerial view by means of a spatial-temporal pyramid network, so as to output a scenario feature; performing screening and processing on conventional historical trajectory data collected by a sensor, so as to obtain original data; further processing the original data to acquire an input representation and a fixed graph, and inputting the input representation and the fixed graph into a graph convolutional network for processing, so as to obtain a graph feature; inputting the graph feature and the scenario feature into a graph attention network for integration, so as to obtain a spatial-temporal graph; and inputting the spatial-temporal graph into a transformer network, and outputting predicted trajectories and categories of traffic participants around an autonomous vehicle. In the present invention, normal historical trajectory data is additionally added, and the interpretability and robustness of an input are improved by means of combining a graph convolutional network with a spatial-temporal pyramid network, thereby improving the precision of prediction.

IPC Classes  ?

• G06T 7/246 - Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
• G06V 10/80 - Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
• G06V 10/774 - Generating sets of training patternsBootstrap methods, e.g. bagging or boosting
• G06N 3/0464 - Convolutional networks [CNN, ConvNet]

Abstract

A task offloading and resource allocation method based on mobile edge computing, relating to the technical field of wireless communications. The method comprises: constructing a mobile edge computing system model; constructing a service cache model and a service assignment model on the basis of the mobile edge computing system model; establishing a task offloading and resource allocation constraint condition on the basis of the service cache model and the service assignment model; according to the task offloading and resource allocation constraint condition, constructing a task offloading and resource allocation joint optimization problem for the objective of minimizing a task processing delay; and solving the task offloading and resource allocation joint optimization problem by using a DSRA algorithm to obtain a task offloading and resource allocation strategy. The present invention can realize a low delay and a high cache hit rate and realize on-demand allocation of resources.

IPC Classes  ?

• H04W 28/08 - Load balancing or load distribution

Abstract

The present invention relates to a cross-network time synchronization method for industrial wireless network and TSN fusion, which belongs to the field of Industrial Internet, comprising the following steps: S1: conducting clock synchronization by a TSN module of a border gateway with a TSN switch of a TSN 2 in a slave clock state; S2: inside the border gateway, using the TSN module as a master clock of an industrial wireless module, and conducting clock synchronization by the industrial wireless module with the TSN module through a serial port; S3: conducting clock synchronization by a routing device in the industrial wireless network with the industrial wireless module of the border gateway through a beacon frame synchronization mode in the slave clock state, and conducting clock synchronization by the routing device as the master clock of a node device for the node device; S4: conducting clock synchronization by a terminal side conversion node in the slave clock state with the node device in the industrial wireless network through a timestamp-free synchronization mode, and finally, synchronizing a TSN switch of a TSN 1 with the terminal side conversion node in the slave clock state.

IPC Classes  ?

• H04J 3/06 - Synchronising arrangements

Abstract

The present invention relates to a uniform configuration method for the integration of an industrial wireless network and a time-sensitive network (TSN), and belongs to the field of network configuration management. The method comprises the following steps: S1: establishing a user plane application to acquire service traffic information and a network topology structure; S2: the user plane application transferring the service traffic information to a control plane by means of a northbound interface, and acquiring a data plane network state by means of the northbound interface; S3: a uniform configuration system performing modeling for the service traffic information and the network topology structure, a scheduling calculation module parsing a service traffic information model, performing scheduling calculation, and obtaining a scheduling calculation result; S4: designing a network device configuration method for an industrial wireless network and a TSN, so as to configure network devices in a heterogeneous network; S5: designing heterogeneous network configuration information based on an XML format; and S6: the uniform configuration system issuing the configuration information, and configuring a network device in the heterogeneous network and a field device.

IPC Classes  ?

• H04L 41/0803 - Configuration setting
• H04L 41/0266 - Exchanging or transporting network management information using the InternetEmbedding network management web servers in network elementsWeb-services-based protocols using meta-data, objects or commands for formatting management information, e.g. using eXtensible markup language [XML]

Abstract

A small sample speech separation method based on data generation, comprising: S1, collecting and constructing a data set of speech to be separated and a data set of target speaker clean speech; S2, preprocessing the data sets; S3: by using an LSTM-based speech matching model, performing frame-level target speaker matching on each segment of speech in the preprocessed data set of speech to be separated, and according to a matching result, determining a speech segment to: not contain a target speaker, only contain one target speaker, and contain a plurality of target speakers; S4, by using a GAN-based speech generation model containing a plurality of target speakers, expanding a speech segment to be separated; and S5: constructing and training a TCN-based speech separation model, separating speech to be separated containing a plurality of target speakers to obtain speech data of a single target speaker, and finally concatenating to obtain complete speech of the single target speaker.

IPC Classes  ?

• G10L 21/0272 - Voice signal separating

Abstract

The present invention belongs to the technical field of digital health management, and particularly relates to a depression diet management method based on food image segmentation, comprising: constructing a depression diet index-based digital health management database; acquiring physical health condition data of a current user; according to the physical health condition data of the current user, and in combination with the depression diet index-based health management database, performing intelligent data analysis, and reasoning a diet recommendation result for the current user; by means of the database, acquiring and storing the physical health condition data of the user and food images; carrying out intelligent segmentation on the images, and, by using a Fisher discriminant analysis method, performing anti-depression index analysis on foods after the segmentation; and performing clustering on selected foods, and, according to the physical health condition information of the user and food categories obtained after the clustering, setting a diet recommendation result. The present invention uses the Fisher discriminant analysis method to perform analysis and screening with respect to depression diet indexes of foods, enabling the food diet recommendation result to be more accurate.

IPC Classes  ?

• G16H 20/60 - ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to nutrition control, e.g. diets
• G16H 20/70 - ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mental therapies, e.g. psychological therapy or autogenous training
• G06V 10/762 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
• G06F 16/535 - Filtering based on additional data, e.g. user or group profiles
• G06F 16/55 - ClusteringClassification

Abstract

The present invention relates to a clock skew tracking method based on weighted observation fusion and timestamp-free interaction, and belongs to the technical field of wireless sensor networks. The method comprises performing listening synchronization by an implicit node S within an overlapping communication range between a reference node and multiple active nodes, and after multiple pairs of timestamp-free communication messages are successfully overheard, using multiple extended Kalman filtering algorithms to perform weighted fusion of multiple observed values on multiple obtained tracking results based on a scalar weighted linear minimum variance information fusion criterion, thus realizing timestamp-free relative skew fusion tracking of the implicit node. The present invention can not only dynamically track a relative clock skew on the basis of sending no message, but also reduce influence of a node with a relatively large tracking error on a listening node, thus robustness of skew tracking of the listening node is increased.

IPC Classes  ?

• H04J 3/06 - Synchronising arrangements
• H04L 67/12 - Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks

Abstract

The present invention relates to a software defined optical network controller deployment method based on multi-path survivability protection, and belongs to the technical field of networks, which is applied to the deployment of layer 2 SDN controllers. On the premise of ensuring the requirements of users for the survivability of the control plane, a multi-controller multi-path cooperative control of switching nodes is proposed to further reduce the number of controllers and control the cost. The present invention first works out a controller deployment scheme with a unique link between switches and controllers. The scheme contains redundant controllers, and the number of controllers needs to be further reduced. The present invention verifies whether the fault probability of each switch is lower than that required by the user by adopting the posteriori thought, that is, according to the deployment result. The number of controllers is gradually reduced, and the survival probability of the switches is always ensured until the deployment number of controllers is minimized. Finally, a controller with minimum communication time delay is selected as a control center to complete the deployment of the entire control plane.

IPC Classes  ?

• H04Q 11/00 - Selecting arrangements for multiplex systems

Abstract

The present invention relates to a timestamp-free synchronization clock parameter tracking method based on extended Kalman filter, and belongs to the technical field of wireless sensor networks. With a first order Gauss Markov model and a clock model as a state equation, evolution processes of clock skew and instantaneous clock offset is described. Then an observation equation constituted by observation models of timestamp-free synchronization and instantaneous clock offset is established, and clock skew and instantaneous clock offset are jointly tracked by a tracking method based on extended Kalman filter to realize synchronization between a node to be synchronized and a reference clock node. The method can track two time-varying parameters simultaneously by following a network data flow without needing a dedicated synchronization frame to exchange synchronization information, which reduces energy consumption and improves synchronization precision.

IPC Classes  ?

• G06F 1/12 - Synchronisation of different clock signals
• G06F 17/11 - Complex mathematical operations for solving equations
• G06F 18/20 - Analysing

Abstract

The present invention relates to the technical field of oil wear debris monitoring, and specifically relates to a partition entropy-based oil wear debris feature signal extraction method. The method comprises: using a lubricating oil wear debris monitoring system for real-time data collection to obtain an original signal to be processed; performing low-pass filtering and harmonic interference suppression on said original signal to obtain a preprocessed signal; using a sliding window to divide the preprocessed signal to obtain a time domain sequence segment set; calculating a partition entropy set corresponding to the time domain sequence segment set, and performing processing to obtain a normalized partition entropy; performing curve fitting by using an empirical cumulative distribution of the normalized partition entropy to obtain an adaptive threshold, and partitioning a sample signal by using the adaptive threshold to obtain non-zero discrete time domain segments; and eliminating residual noise interference by using target signal feature recognition indexes to obtain a final oil wear debris feature signal extraction result. The present invention can protect the morphological features of a tiny wear debris sensing signal from being damaged while suppressing background noise.

IPC Classes  ?

• G06F 18/213 - Feature extraction, e.g. by transforming the feature spaceSummarisationMappings, e.g. subspace methods
• G06F 18/24 - Classification techniques
• G06F 18/10 - Pre-processingData cleansing
• G06F 123/00 - Data types

Abstract

The present invention relates to a consensus-based clock synchronization skew estimation method based on sequential least squares, and belongs to the technical field of wireless sensor networks. The method is to establish a relationship model of clock information and time delay between nodes with respect to a bounded random communication time delay scenario subject to arbitrary distribution, fully consider all clock information received by a node from a neighbor, build a clock parameter estimation model and a cost function based on a least squares principle, iteratively estimate relative clock skew by a sequential least squares method, and update logical clock parameters of nodes by a consensus-based clock synchronization method, so as to achieve global clock consistency of all nodes in a network in a completely distributed way. The present invention improves accuracy of relative skew estimation, effectively reduces storage overhead of the nodes, and improves robustness of a consensus-based synchronization algorithm against communication time delay.

IPC Classes  ?

• H04L 7/00 - Arrangements for synchronising receiver with transmitter
• H04W 56/00 - Synchronisation arrangements

Abstract

A driving system in an area outside an enhanced autonomous valet parking (E-AVP) lot, and an application method thereof, relating to the technical fields of autonomous driving, vehicle-infrastructure cooperation, and intelligent transportation systems. The system comprises a client, an E-AVP cloud, a road side unit, and a 5G-V2X vehicle end; the client communicates with the E-AVP cloud by means of 5G; the E-AVP cloud communicates with the client, the road side unit, and the 5G-V2X vehicle end by means of 5G; the road side unit communicates with the 5G-V2X vehicle end by means of V2X communication; the 5G-V2X vehicle end achieves inter-vehicle interaction by means of a CAN bus. The present application achieves interaction among an E-AVP management system, a user terminal, and a vehicle-mounted terminal, and solves the existing problems that parking and vehicle searching are difficult for users, thereby achieving the objectives of unmanned supervision of remote valet parking and improvement of the parking experience of the users.

IPC Classes  ?

• G08G 1/0968 - Systems involving transmission of navigation instructions to the vehicle
• G08G 1/14 - Traffic control systems for road vehicles indicating individual free spaces in parking areas
• H04W 4/44 - Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P] for communication between vehicles and infrastructures, e.g. vehicle-to-cloud [V2C] or vehicle-to-home [V2H]

Abstract

Provided is an automatic parking decision making method based on the fusion of model predictive control and reinforcement learning, relating to the technical field of autonomous driving. In the process of automatic parking, the process of selecting an optimal action is trained by using a proximal policy optimization algorithm, wherein the proximal policy optimization algorithm comprises an Actor network and a Critic network, a policy function corresponds to the Actor network, a value function corresponds to the Critic network, the output of the Actor network is the probability of taking each possible steering action when a vehicle is in a specific state, and the output of the Critic network is a state value function of the state after the steering action of the Actor network is taken. In the context of narrow and vertical parking spaces, model predictive control is combined with a proximal policy optimization reinforcement learning algorithm, so that the problems that the parking planning time is long and the success rate is low under the condition that the parking spaces are narrow are solved, and the parking space selection range of the system is expanded.

IPC Classes  ?

• G05B 19/042 - Programme control other than numerical control, i.e. in sequence controllers or logic controllers using digital processors
• B60W 30/06 - Automatic manoeuvring for parking

Abstract

The present invention relates to an age-of-information optimized scheduling method for a multi-sensor multi-server industrial Internet of Things, and belongs to the technical field of industrial wireless networks. Oriented to a multi-sensor multi-server industrial Internet of Things system, the method minimizes the average age-of-information of the system by means of selecting a link scheduling combination in each time slot, forms the strong coupling optimization problem of link scheduling, server selection and service preemption into a Markov decision process, reduces a state space and an action space for problem solving by means of a deep Q-network having a plurality of improved network branches and shared decision-making modules, and increases the training speed by means of a fixed dominant policy so as to obtain a link scheduling method. By means of the branch deep Q-network and the fixed dominant policy, the present invention increases the learning speed of the scheduling method and ensures the newness of delivered industrial Internet of Things data.

IPC Classes  ?

• H04W 24/02 - Arrangements for optimising operational condition
• H04W 4/30 - Services specially adapted for particular environments, situations or purposes
• G06N 3/047 - Probabilistic or stochastic networks
• G06N 3/08 - Learning methods

Abstract

A distributed task offloading and computing resources management method based on energy harvesting is provided, including: establishing a task local computing model and an edge cloud computing model; establishing a device maximum benefit objective function based on the perturbation Lyapunov optimization algorithm and a mobile edge computing server maximum benefit objective function; pre-selecting, by the device based on a pre-screening criteria, a mobile edge computing server for task offloading; calculating an optimal task size strategy for performing task offloading by the device to the selected mobile edge computing server by using a Lagrange multiplier algorithm and a KKT condition; obtaining an optimal quotation strategy of the mobile edge computing server for the device in each of time slots; and obtaining a solution of the optimal task size strategy meeting a Stackelberg equilibrium and a solution of the optimal dynamic quotation strategy meeting the Stackelberg equilibrium as a resource allocation strategy.

IPC Classes  ?

• H04L 67/1023 - Server selection for load balancing based on a hash applied to IP addresses or costs

Abstract

The present invention belongs to the field of industrial communications, and relates to a Modbus TCP cross-TSN joint scheduling method. The method comprises: S1, constructing a heterogeneous network scheduling model, which comprises establishing a heterogeneous network and a traffic demand model; S2, using a scheduling pre-processing algorithm to complete priority pre-processing in network transmission; and S3, constructing a two-dimensional offline bin-packing problem model, i.e. using a two-dimensional offline bin-packing algorithm to abstract a transmission demand into a two-dimensional item, so as to perform problem conversion, and in view of the priority of network transmission, changing the placement principle and a sequence order during a bin-packing process, so as to optimize and resolve a scheduling problem. By means of the present invention, the operation efficiency of a scheduling algorithm can be improved, the difficulty of scheduling computation can be reduced, and the optimization and resolving of a scheduling problem can be realized.

IPC Classes  ?

• H04L 41/14 - Network analysis or design
• H04L 41/142 - Network analysis or design using statistical or mathematical methods
• H04L 12/46 - Interconnection of networks

Abstract

A task offloading and resource allocation method in an uncertain network environment is provided. A task offloading process is modeled as a two-stage offloading model. The model is optimized to a task offloading and resource allocation problem based on two-stage stochastic programming. Based on a stochastic simulation algorithm, the task offloading and resource allocation problem is transformed to a sample mean approximation problem. The sample mean approximation problem is decoupled to a local computing resource allocation sub-problem, a transmission power and edge computing resource joint allocation sub-problem, and an offloading decision sub-problem. The three sub-problems are solved respectively by using a standard Lagrange multiplier algorithm, by using a genetic algorithm, and by analyzing delay estimation and energy consumption budget of local computing and delay estimation and energy consumption budget of edge computing. The user performs task offloading based on an optimal allocation strategy obtained by solving the three sub-problems.

IPC Classes  ?

• G06F 9/48 - Program initiatingProgram switching, e.g. by interrupt

Abstract

The present invention relates to the technical field of machine vision, and relates to an intelligent recognition method for work content of a barbershop staff. The method comprises the following steps: S1, configuring an installation position and an installation condition of an acquisition device; S2, establishing a label library of barbershop staff faces and customer faces, and training a face recognition model; S3, establishing an action label library related to objects, tools and people, and training a barbershop action behavior recognition model; S4, using the trained face recognition model and the trained barbershop action behavior recognition model to perform action behavior recognition on an actual haircut service scene, and constructing an "action pair" behavior time sequence of elements, i.e., customer, staff and action; S5, establishing a work content recognition label, and constructing a deep neural network model for work content recognition, so as to determine service work content of a barbershop staff to a customer. According to the present invention, the intelligent recognition method for work content of the barbershop staff assists in realizing effective intelligent management of a barbershop.

IPC Classes  ?

• G06V 40/20 - Movements or behaviour, e.g. gesture recognition

Abstract

The present invention relates to the field of image processing, and relates to a transfer learning strategy-based real-time few-shot object detection method, comprising the following steps: S1: constructing a detection network model; S2: preprocessing input data; S3: training an object detection model from scratch by using large-sample class data; S4: fine-tuning a few-shot class detection branch by using few-shot class data; and during the fine-tuning, using a new regularization method to guide the model to pay attention to a global feature of an object; and S5: training the detection model by means of a training set, and carrying out a test by using a test set. The present invention avoids overfitting of a model in a fine-tuning stage, avoids dominance by local salient features, and enhances the generalization capability of the model. The present invention not only can achieve accurate detection on few-shot class objects using fewer model parameters, but also can achieve real-time detection of related objects.

IPC Classes  ?

• G06N 3/096 - Transfer learning
• G06V 10/764 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects

Abstract

The present invention belongs to the field of network device testing, and relates to a micro service-based test system and method for an industrial wireless network device accessing IPv6. The method comprises: a user logging in to a test management system, creating a test item, filling in a PICS form, and providing a device under test to a tester; the tester making the device under test access a network environment under test; the test management system generating a set of test cases, and performing priority ranking on the test cases in the set of test cases; the test management system executing the test cases one by one, and sending a test instruction to a test agent; the test agent sending, according to an operation instruction, a test flow to an environment for testing an industrial wireless network device accessing IPv6; a network device in the environment for testing the industrial wireless network device accessing IPv6 forwarding the test flow, and responding to the test agent; the test agent uploading a result to the test management system based on a micro-service architecture; and after all test cases are executed, the test management system analyzing the test result to generate a test report.

IPC Classes  ?

• H04L 43/06 - Generation of reports
• H04L 43/08 - Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
• H04L 41/0246 - Exchanging or transporting network management information using the InternetEmbedding network management web servers in network elementsWeb-services-based protocols
• H04L 41/044 - Network management architectures or arrangements comprising hierarchical management structures
• H04L 41/0823 - Configuration setting characterised by the purposes of a change of settings, e.g. optimising configuration for enhancing reliability

Abstract

The present invention relates to a successive approximation-based joint scheduling method for a time sensitive network and an industrial wireless network, and belongs to the field of industrial wireless network scheduling. The method comprises the following steps: in an offline stage: S1, performing customization processing on a superframe structure in an industrial wireless network, determining a superframe duration and a slot length, and calculating the number of slots; S2, acquiring data packet information sent by a node, wherein the data packet information remains consecutive temporally; S3, constructing a training set and a test set for a slot requirement forecasting model; and S4, training the slot requirement prediction model; and in an online stage: S5, configuring a heterogeneous network, which involves configuring configuration information, which is determined in the off-line stage, for a cooperative scheduling subsystem, an industrial wireless gateway, a wireless routing device and an industrial wireless node; S6, performing slot prediction and allocation, and broadcasting beacons; and S7, performing data transmission according to an allocated path. The present invention ensures the flexibility and determinacy of a heterogeneous network.

IPC Classes  ?

• H04L 12/46 - Interconnection of networks

Abstract

A multi-sensor fusion method and system for an intelligent driving vehicle, relating to the technical field of intelligent driving vehicles. The method comprises: constructing an extended target tracker according to a GM-PHD algorithm and a rectangular target model of a detection object; processing detection information of a millimeter wave radar by means of the extended target tracker to obtain millimeter wave radar track information of the detection object; processing detection information of a lidar by means of a constructed bounding box detector and a JPDA tracker provided with an IMM-UKF to obtain lidar track information of the detection object; processing the millimeter wave radar track information and the lidar track information by means of time-space conversion to obtain a central fusion node; and processing the central fusion node by means of an IMF algorithm to obtain global track information.

IPC Classes  ?

• G01S 13/931 - Radar or analogous systems, specially adapted for specific applications for anti-collision purposes of land vehicles
• G01S 13/86 - Combinations of radar systems with non-radar systems, e.g. sonar, direction finder
• G01S 17/931 - Lidar systems, specially adapted for specific applications for anti-collision purposes of land vehicles
• G06V 20/54 - Surveillance or monitoring of activities, e.g. for recognising suspicious objects of traffic, e.g. cars on the road, trains or boats
• G06T 7/20 - Analysis of motion

Abstract

The present invention relates to the technical field of wireless sensor networks and relates to a wireless sensor network time synchronization method based on partial timestamp information. According to the method, partial timestamp information and response time interval information are transmitted at a local time when a preset clock source node returns an acknowledgement frame, thereby avoiding timestamp interaction; and for a Gaussian random delay and an exponential random delay, a maximum likelihood estimation method and a best linear unbiased estimation method are respectively used to simultaneously estimate a frequency offset and a phase offset of a clock, thereby implementing the synchronization between nodes. According to the present invention, the transmission of synchronization information does not depend on a specific synchronization frame, and a synchronization function can be embedded into existing network data streams, thereby effectively reducing energy consumption for synchronization.

IPC Classes  ?

• H04W 56/00 - Synchronisation arrangements

Abstract

A human body fall risk prediction method and system based on electronic nursing text data, relating to the technical field of data processing. The method comprises: obtaining an electronic nursing data set, preprocessing data in the electronic nursing data set, and constructing a Morse fall dictionary according to the preprocessed data in the electronic nursing data set; using a natural language processing technology to perform text feature extraction on the electronic nursing text data of a user to be predicted; parsing extracted text features by using the Morse fall dictionary, so as to obtain a variable data set; training a decision tree algorithm by using the variable data set, so as to obtain a human body fall risk prediction result; and performing clustering and accurate nursing on the user according to the prediction result. The Morse fall dictionary is constructed by means of an electronic health record, a risk factor of the user is obtained according to the Morse fall dictionary, and fall risk prediction is performed on the user according to the risk factor, and thus, the prediction efficiency is improved.

IPC Classes  ?

• G16H 50/70 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
• G16H 10/60 - ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
• G06F 40/242 - Dictionaries

Abstract

322), oleic acid (OA), oleylamine (OAm), a sodium ion precursor and a copper ion precursor in octadecene (ODE). Copper ions (Cu2+) and sodium ions (Na+33) perovskite fluorescent quantum dots. The finally prepared product is effectively improved in terms of photoluminescence quantum yield, thermal stability and the like, can be used as an active layer to package an electroluminescent diode, and realizes transition from green light to blue light by means of electroluminescence based on recombination of doping ions and excitons.

IPC Classes  ?

• C09K 11/66 - Luminescent, e.g. electroluminescent, chemiluminescent, materials containing inorganic luminescent materials containing germanium, tin or lead
• B82Y 20/00 - Nanooptics, e.g. quantum optics or photonic crystals
• B82Y 30/00 - Nanotechnology for materials or surface science, e.g. nanocomposites
• B82Y 40/00 - Manufacture or treatment of nanostructures
• H01L 33/50 - Wavelength conversion elements

Abstract

The present application relates to the technical field of mobile communications, and specifically relates to an evolutionary game-based multi-user switching method in a software-defined satellite network system. The multi-user switching method comprises: respectively calculating the elevation angle and the remaining coverage time of a satellite according to obtained information, and calculating the payoff according to three basic factors, i.e., the capacity, the elevation angle, and the remaining coverage time of the satellite; a controller calculating the average payoff of users in the area, and broadcasting same to the users; when it is determined that the payoff of all the users is greater than the average payoff, ending multi-user switching; and when it is determined that the payoff of all the users is not greater than the average payoff, the users selecting other switching satellites having higher payoffs.

IPC Classes  ?

• H04W 36/08 - Reselecting an access point
• H04W 84/06 - Airborne or Satellite Networks

Abstract

The present invention relates to the field of dining food image data processing, and in particular to a nutritional management method and system using a deep learning-based food image recognition model. The method comprises: a user-side obtaining an image of food to be ingested by a user, and inputting the obtained food image into a trained deep learning-based food image recognition model to obtain different types of food sub-images; calculating the amounts of nutrients contained in the different types of food sub-images, and accumulating the nutrients in all food to obtain total intakes of various nutrients of the user; setting intake thresholds for various nutrients, and comparing the calculated total intakes of various nutrients with the corresponding nutrient intake thresholds to obtain comparison results; and adjusting, according to the comparison results, the type and amount of the food to be ingested, so as to complete nutritional management. According to the present invention, food intake information uploaded by the user is associated with other data sets by means of a server, so that whether energy, the ratio of energy-yielding nutrients, etc. are at appropriate recommended amounts is known, and finally, the data obtained by analysis is fed back to the user, thereby prompting the user to improve a dietary pattern.

IPC Classes  ?

• G06V 20/20 - ScenesScene-specific elements in augmented reality scenes
• G06V 10/26 - Segmentation of patterns in the image fieldCutting or merging of image elements to establish the pattern region, e.g. clustering-based techniquesDetection of occlusion
• G06V 10/20 - Image preprocessing
• G06V 10/80 - Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
• G06K 9/62 - Methods or arrangements for recognition using electronic means
• G16H 20/60 - ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to nutrition control, e.g. diets

Abstract

A blockchain-based method for multi-tenant distributed leasing of satellite network resources, which belongs to the field of mobile communications. The method comprises: S1, constructing a multi-tenant commercial ecosystem for satellite network resource leasing; and S2, constructing a blockchain-based satellite network resource leasing mechanism, which specifically comprises: S21, constructing a double-leasing mechanism for satellite network resources; S22, constructing a blockchain-based resource leasing mechanism; and S23, acquiring a reputation value of a participant, involving: firstly calculating a reputation score of the participant, then combining same with a transaction cost to ensure the honesty of the participant, and finally using a sliding window to ensure that a selected leader is an honest participant that makes a continuous contribution. In the method, reputation is combined with a blockchain-based leasing mechanism, thereby preventing an intermediate entity from manipulating a transaction result, improving the transaction throughput of a system and reducing the transaction delay.

IPC Classes  ?

• G06Q 30/06 - Buying, selling or leasing transactions
• G06Q 30/08 - Auctions
• G06Q 20/42 - Confirmation, e.g. check or permission by the legal debtor of payment
• G06Q 20/38 - Payment protocolsDetails thereof

Abstract

The present invention relates to a joint optimization method for path selection and gate scheduling in time-sensitive networking, and belongs to the technical field of time-sensitive networking. The method comprises the following steps: S1, a CNC finding a TSN topology, and abstracting same into a network directed graph; S2, a terminal device sending to a CUC a TSN connection request, and the CUC sending same to the CNC; S3, the CNC selecting K shortest paths as alternative paths; S4, the CNC selecting m preferred paths; S5, the CNC finding an optimal transmission path for a TT stream, and finding a proper transmission path for a non-TT stream; S6, CNC completing traversal; S7, configuring a gate control list for the optimal transmission path of the TT stream of each pair of terminal devices; and S8, the CNC encapsulating a computation result into a gate scheduling table, configuring the gate scheduling table to a TSN switch, and then sending a traffic transmission computation result to the TSN terminal device by means of the CUC.

IPC Classes  ?

• H04L 45/30 - Routing of multiclass traffic

Abstract

A low-complexity selective mapping method using cyclic redundancy check is provided. In performing coding, a transmitter adds a check bit to information bits to be transmitted to obtain modulated data. Demodulation is performed on an M-order modulation symbol received by a receiver to obtain a decoding result of a coding polynomial of the modulation symbol and bit information received by the receiver. A modulo-2 division result of the decoding result of the coding polynomial and a generation polynomial is calculated. In a case that a remainder of the modulo-2 division result is equal to zero, if the modulated data corresponding to the same index value of the receiver and the transmitter are identical, a current iteration is stopped, and a current value is outputted as a phase rotation sequence index recovery value. Finally, the receiver obtains a decoded signal.

IPC Classes  ?

• H03M 13/09 - Error detection only, e.g. using cyclic redundancy check [CRC] codes or single parity bit
• H03M 13/15 - Cyclic codes, i.e. cyclic shifts of codewords produce other codewords, e.g. codes defined by a generator polynomial, Bose-Chaudhuri-Hocquenghem [BCH] codes

Abstract

A distributed computation offloading method based on computation-network collaboration in a stochastic network is provided. The distributed computation offloading method includes: building a device revenue maximization problem model and a MEC server revenue maximization problem model based on a local computing model and an edge cloud computing model; building composite sets of scenarios for dwell time and waiting latency based on a random movement of a user and burst computation demands; compensating for a game strategy by using a posteriori recourse action and building a game-based stochastic programming model between the device and the MEC server; transforming a multi-stage stochastic regularization problem for both the device and the MEC server into a DEP problem by constructing a scenario tree, and solving the DEP problem to obtain an optimal task strategy for the offloading from the MEC server and an optimal offering strategy of the MEC server to the device.

IPC Classes  ?

• H04L 67/1023 - Server selection for load balancing based on a hash applied to IP addresses or costs
• G06F 9/48 - Program initiatingProgram switching, e.g. by interrupt

Abstract

The present invention relates to the technical field of charging load prediction, and in particular to a charging load probability prediction system and method based on non-intrusive detection, which are used for solving the problems of charging load prediction and planning. The charging load probability prediction system based on non-intrusive detection comprises an image acquisition unit, a temperature detection unit, a positioning unit, an Internet of Vehicles service system, and a cloud storage computing platform. Vehicle pictures and real-time temperature data acquired by traffic cameras can be received in real time on the cloud storage computing platform, and the data obtained from vehicle picture recognition are classified according to the temperature data range and input into a corresponding charging load prediction model to obtain the probability of when and where the target is to be charged and the charging load. Over time, the probability of when and where to charge and the charging load can be used in the planning and construction of charging facilities of certain regions. The electric vehicle charging demand in a prediction area can be predicted, and the layout planning of a charging facility is reasonably selected.

IPC Classes  ?

• G06Q 10/06 - Resources, workflows, human or project managementEnterprise or organisation planningEnterprise or organisation modelling

Abstract

A time series data adversarial sample generating method and system, an electronic device, and a storage medium, relating to the field of time series data processing. The method comprises: training a time series prediction model using original time series data (101); calculating a maximum value of a loss function in the time series prediction model by means of a stochastic gradient descent optimization strategy (102); determining corresponding noise according to the maximum value of the loss function (103); and superimposing the noise on the original time series data to generate a globally disturbed time series data adversarial sample (104). The method can significantly reduce the model accuracy under the condition of a small amount of data disturbance, has important significance for safe application of an industrial system, and has wide applicability and transferability.

IPC Classes  ?

• G06N 3/094 - Adversarial learning

Abstract

The present invention relates to the field of digital signal processing, and in particular to a Costas sequence time-frequency joint synchronization method based on all-phase spectrum correction. The method improves the defects existing in a discrete frequency spectrum correction algorithm using short-time Fourier transform and sliding correlation. The improvement mainly comprises: the present disclosure provides a solution based on iterative optimization: when an actual frequency offset is an integral multiple of the spectral resolution, a large error can occur, frequency offset correction and time delay correction are carried out on a signal by using an estimated value having a large estimated error, then estimation is carried out again, and the frequency offset of the signal is not a special value by means of an iteration mode.

IPC Classes  ?

• H04L 27/00 - Modulated-carrier systems
• H04L 7/00 - Arrangements for synchronising receiver with transmitter
• H04L 27/10 - Frequency-modulated carrier systems, i.e. using frequency-shift keying

Abstract

The present invention relates to a small sample remote sensing image scene classification method based on an embedding smoothing graph neural network, which method belongs to the field of remote sensing image recognition. The method comprises: first inputting scene images into an embedding learning module, and extracting scene embedding features by means of a convolutional neural network; then introducing embedding smoothing into scene classification, and capturing the similarity and difference between the embedding features under an unsupervised condition, thereby improving the distinguishability between the embedding features, expanding a decision-making boundary, and reducing the effect of irrelevant features; in addition, constructing a graph matrix by means of an attention mechanism and by using a task-level relationship, associating a target sample with all samples in a task, and generating relationship representations having a high distinguishability between different scene categories; then, constructing graphs according to intrinsic relationships between the samples; and a label matching module iteratively generating prediction labels of samples in a test set according to the constructed graphs by means of transductive learning, until an optimal solution is obtained. By means of the present invention, accurate image classification can be realized.

IPC Classes  ?

• G06V 10/764 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
• G06V 10/774 - Generating sets of training patternsBootstrap methods, e.g. bagging or boosting
• G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
• G06V 20/13 - Satellite images
• G06K 9/62 - Methods or arrangements for recognition using electronic means
• G06N 3/04 - Architecture, e.g. interconnection topology
• G06N 3/08 - Learning methods

Abstract

An embedded GPU-based wideband parallel channelized receiving method includes: constructing an OpenCL platform; decimating a wideband signal read in the OpenCL platform at an interval indicated by the number of channels; assigning data in each row to one of multiple work groups for processing; filtering data on each of channels based on a coefficient of a polyphase filter on a branch; multiplying the filtered data by a factor; and performing an FFT on the formed two-dimensional matrix by columns to obtain data outputted from each of the channels.

IPC Classes  ?

• H04B 1/06 - Receivers
• G06F 8/76 - Adapting program code to run in a different environmentPorting
• G06F 17/16 - Matrix or vector computation
• H03H 17/02 - Frequency-selective networks

Abstract

The present invention relates to machine learning, and in particular to a data feature combination pricing method and system based on a Shapley value and an electronic device. The method comprises: collecting feature variables of a feature data set provided by a seller, and preprocessing the feature variables; constructing a learning model based on machine learning, and selecting an optimal feature classification variable from feature classification variables; estimating feature Shapley values constructed on the basis of ghost data instances so as to calculate marginal contribution and an average Shapley value of selected feature variables; and according to the marginal contribution and the average Shapley value of the feature variables, determining whether the feature variables can be subjected to transaction, and if yes, performing the transaction. In the embodiments of the present invention, long-term benefit maximization of a data provider can be realized, risk assessment of the data seller on the data buyer company is met, and the risk loss is reduced.

IPC Classes  ?

• G06Q 30/02 - MarketingPrice estimation or determinationFundraising
• G06N 20/00 - Machine learning
• G06Q 30/08 - Auctions
• G06Q 40/02 - Banking, e.g. interest calculation or account maintenance
• G06Q 40/04 - Trading Exchange, e.g. stocks, commodities, derivatives or currency exchange

Abstract

The present invention belongs to the field of industrial Internet, and relates to an industrial wireless network-and-TSN fusion-oriented cross-network time synchronization method. The method comprises the following steps: S1, a TSN module of a border gateway performing, in a slave clock state, clock synchronization with a TSN switch of a TSN network 2; S2, taking, inside the border gateway, the TSN module as a master clock of an industrial wireless module, wherein the industrial wireless module performs clock synchronization with the TSN module by means of a serial port; S3, a routing device in an industrial wireless network performing, in a slave state, clock synchronization with the industrial wireless module of the border gateway by means of beacon frame synchronization, and further taking the routing device as a master clock of a node device, so as to perform clock synchronization on the node device; and S4, a terminal-side conversion node performing, in a slave clock state, clock synchronization with a node device of the industrial wireless network by means of timestamp-free synchronization, and finally, a TSN switch of a TSN network 1 performing, in a slave clock state, synchronization with the terminal-side conversion node.

IPC Classes  ?

• H04J 3/06 - Synchronising arrangements
• H04W 56/00 - Synchronisation arrangements

Abstract

The present application relates to a computing and network collaboration-based distributed computation offloading method in a random network. The distributed computation offloading method comprises: on the basis of a local computing model and an edge cloud computing model, constructing a device revenue maximization problem model and an MEC server maximized revenue problem model; according to random movement and burst computing requirements of a user, respectively establishing composite scene sets of dwell time and waiting delay; using a posterior resource action to compensate game strategies, and establishing a game-based stochastic programming model for both the device and the MEC server; and constructing a scene tree, converting a multi-stage stochastic programming problem of both the device and the MEC server into a DEP problem, and solving the problem to obtain an optimal task policy of MEC server offloading and an optimal quotation policy of the MEC server to the device. The present application realizes dynamic offloading and adaptive computing capability management of tasks in a time-varying environment on the basis of an extensive game theory method of a Lyapunov optimization theory.

IPC Classes  ?

• H04W 28/16 - Central resource managementNegotiation of resources or communication parameters, e.g. negotiating bandwidth or QoS [Quality of Service]

Abstract

The present invention relates to a layered semi-parallel LDPC decoder system having a single permutation network, and belongs to the field of decoder hardware design. The system comprises a layered decoding architecture of the single permutation network, a layered semi-parallel decoding architecture of the single permutation network, a pipeline design for layered semi-parallel decoding and a hardware framework of a layered semi-parallel LDPC decoder. The present invention removes a permutation network module between a check node and a variable node by modifying the cyclic shift value of each information block transferred from the variable node to the check node, i.e., the cyclic shift operation of the decoder can be completed through the single permutation network so as to reduce hardware resources of the decoder. A semi-parallel decoding structure is adopted, and meanwhile, a pipeline is added between half layers. Compared with a decoder with a layered full-parallel structure, a decoder with a semi-parallel structure has the degree of parallelism of a variable node equal to only half of the code length but can achieve ¾ of the throughput as well as reduce hardware resources by half.

IPC Classes  ?

• H03M 13/11 - Error detection or forward error correction by redundancy in data representation, i.e. code words containing more digits than the source words using block codes, i.e. a predetermined number of check bits joined to a predetermined number of information bits using multiple parity bits

Abstract

The present invention relates to a low-energy routing method based on inter-satellite communication, which method belongs to the technical field of communications. The method comprises: improved calculation of three-dimensional Fermat points; calculation of Fermat points in three target areas; selection of satellite nodes of the Fermat points; and a low-energy Fermat point three-dimensional routing algorithm LEFTR. According to the present invention, a method for calculating three-dimensional Fermat points is improved, so as to be more suitable for inter-satellite communication; and a method for directly calculating Fermat points in three target areas in a three-dimensional environment is provided. A Fermat point node search algorithm is provided for finding a node, which plays the role of transit transmission. The present algorithm is used for making the energy consumption of network transmission more balanced when the node, which plays the role of transit transmission, needs to be found after the Fermat points have been calculated. An efficient geocasting algorithm LEFTR suitable for satellite communication is provided. By extending the algorithm to multiple target areas, a Fermat point tree is constructed by using the characteristics of the Fermat points, such that low-energy data transmission in the multiple target areas is realized.

IPC Classes  ?

• H04B 7/185 - Space-based or airborne stations
• H04W 40/02 - Communication route or path selection, e.g. power-based or shortest path routing

Abstract

The present invention relates to a clock frequency offset tracking method based on weighted observation fusion and timestamp-free interaction, which method belongs to the technical field of wireless sensor networks. The method comprises: a hidden node S which is located in an overlapping communication range of a reference node and a plurality of active nodes executing monitoring synchronization; and after a plurality of pairs of timestamp-free communication messages are successfully monitored, performing, by using a plurality of groups of extended Kalman filtering algorithms, multi-observation weighted fusion on a plurality of obtained tracking results according to a scalar weighted linear minimum variance information fusion criterion, so as to realize timestamp-free relative frequency offset fusion tracking of the hidden node. By means of the present invention, a relative clock frequency offset can be dynamically tracked on the basis that there is no message to be sent, and the influence of a synchronization node with a relatively large tracking error on a monitoring node can also be reduced, thereby increasing the robustness of frequency offset tracking of a monitoring node.

IPC Classes  ?

• H04J 3/06 - Synchronising arrangements
• H04L 27/00 - Modulated-carrier systems
• H04W 84/18 - Self-organising networks, e.g. ad hoc networks or sensor networks
• H03H 17/02 - Frequency-selective networks

Abstract

A software defined optical network controller deployment method based on multi-path survivability protection, which method belongs to the technical field of networks, and is applied to the deployment of a two-layer SDN controller. On the premise of ensuring a survivability requirement of a user for a control plane, the number of controllers is further reduced according to the situation of the multi-controller multi-path cooperative management and control of switch nodes, so as to control the cost. A controller deployment solution in which a switch and a controller have a unique link is obtained at first, the solution contains redundant controllers, and thus the number of controllers needs to be further reduced. Whether a fault probability of each switch is lower than a fault probability required by the user is verified by using a posteriori thought, that is, according to a deployment result. The number of controllers is gradually reduced, and the survival probability of the switch is ensured all the time, until the number of deployed controllers is minimized. Finally, the controller having the smallest communication delay is selected as a management and control center, so as to complete the deployment work of the entire control plane.

IPC Classes  ?

• H04Q 11/00 - Selecting arrangements for multiplex systems

Abstract

The present invention relates to a timestamp-free synchronizing clock parameter tracking method based on the extended Kalman filter (EKF), and belongs to the technical field of wireless sensor networks. Th method comprises: by using a first-order Gauss-Markov model and a clock model as state equations, describing the evolution process of clock skew and clock instantaneous offset; and then establishing an observation equation formed by a timestamp-free synchronizing and clock instantaneous offset observation model, and jointly tracking the clock skew and clock instantaneous offset by using a tracking method based on the EKF, so as to achieve the synchronization between a node to be synchronized and a reference clock node. In the method, simultaneous tracking of two time-varying parameters may be completed by following a network data flow, a dedicated synchronization frame is not needed to exchange synchronization information, thus reducing energy consumption, and improving synchronization precision.

IPC Classes  ?

• H04J 3/06 - Synchronising arrangements
• H04W 56/00 - Synchronisation arrangements
• G06K 9/62 - Methods or arrangements for recognition using electronic means
• G06F 17/11 - Complex mathematical operations for solving equations
• G06F 17/16 - Matrix or vector computation

Abstract

The present application relates to the technical field of wireless communications, and in particular to a task offloading and resource allocation method in an uncertain network environment. The method comprises: modeling a task offloading process into a two-stage offloading model, optimizing the model into a task offloading and resource allocation issue based on two-stage stochastic programming, converting the task offloading and resource allocation issue into a sample average approximation issue by using a stochastic simulation method, and decoupling the sample average approximation issue into a local computing resource allocation sub-issue, a transmission power and edge computing resource joint allocation sub-issue, and an offloading decision sub-issue; solving for the three sub-issues by using a standard Lagrange multiplier method, a genetic algorithm, and analysis of delay estimation and energy consumption budgeting for local computing and edge computing; and a user performing task offloading according to optimal allocation strategies obtained by solving for the three sub-issues. The present application can meet the task computing delay requirement in a network having an uncertain delay, and simultaneously can ensure minimum system energy consumption.

IPC Classes  ?

• H04W 24/02 - Arrangements for optimising operational condition

Abstract

An anole-imitating wind-vibration-resistant climbing robot, which is composed of a body functional module, foot functional modules (5), leg functional modules (4), a control and drive functional module (1-1) and a power supply device (1-2), wherein the body functional module comprises a head (1), a spine (2-3), which completes a cross-legged gait advancing function by means of bending, a flexible abdominal thin film (2-9) prepared from magnetically sensitive rubber, a tail (3), which converts wind energy into advancing power by means of bending deformation, and a rib frame (2-2); each foot functional module (5) is composed of toes (5-4), which each comprise a claw (5-4-2) and a plurality of phalanges (5-4-1), and a toe connector (5-3); and each leg functional module (4) comprises a pneumatic functional portion and a motion functional portion. According to the robot, with reference to structural change characteristics of an anole in strong wind, a flexible abdomen and a tail, which can adjust a pneumatic performance, are designed, and adhesive feet capable of improving the adhesion capability are also designed, such that the robot can solve the problem of stable climbing in a strong wind environment, and the robot can adapt to a wall face having a certain curvature, and can adapt to wider and more complex settings.

IPC Classes  ?

• B62D 57/032 - Vehicles characterised by having other propulsion or other ground-engaging means than wheels or endless track, alone or in addition to wheels or endless track with ground-engaging propulsion means, e.g. walking members with alternately or sequentially lifted supporting base and legVehicles characterised by having other propulsion or other ground-engaging means than wheels or endless track, alone or in addition to wheels or endless track with ground-engaging propulsion means, e.g. walking members with alternately or sequentially lifted feet or skid
• B62D 57/024 - Vehicles characterised by having other propulsion or other ground-engaging means than wheels or endless track, alone or in addition to wheels or endless track with ground-engaging propulsion means, e.g. walking members specially adapted for moving on inclined or vertical surfaces

Abstract

A sequential least squares-based consistent clock synchronization frequency deviation estimation method, relating to the technical field of wireless sensor networks. According to the method, for a random bounded communication delay scene in compliance with an arbitrary distribution, a relational model for clock information and delays between nodes is established; by fully considering all clock information received by the nodes from respective neighbors, a clock parameter estimation model and a principle of least squares-based cost function are constructed; a relative clock frequency deviation between the nodes is iteratively estimated by using a sequential least squares method; and logic clock parameters of the nodes are updated by using a consistent clock synchronization method, such that all the nodes in a network achieve global clock consistency in a fully distributed manner. The method improves the accuracy of relative frequency deviation estimation, effectively reduces storage overhead of nodes, and improves the robustness of a consistent synchronization algorithm for communication delays.

IPC Classes  ?

• H04W 56/00 - Synchronisation arrangements

Abstract

The present invention relates to the technical field of industrial Internet, and relates to an industrial heterogeneous network high-speed protocol conversion apparatus and a parallel processing unit. The apparatus comprises a queue transceiving unit, a protocol conversion unit, a parallel processing unit, and an SDN management interface unit; industrial wireless network data is transceived by means of a wireless module, and industrial wired network data and IPv6 backbone network data are transceived by means of a network card; the queue transceiving unit is configured for classification management of a data packet; the protocol conversion unit is configured to complete protocol conversion between an industrial wireless network and an industrial wired network and an IPv6 backbone network; the parallel processing unit is configured for parallel processing of multi-protocol conversion; the SDN management interface unit implements management and control of the protocol conversion apparatus by an upper-layer SDN controller. The present invention supports protocol conversion between an industrial wireless network and an industrial wired network and an IPv6 backbone network, uses technologies such as parallel processing and cache optimization, guarantees parallel and high-speed processing of multi-protocol conversion, and achieves efficient interconnection of industrial heterogeneous networks.

IPC Classes  ?

• H04L 12/28 - Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]

Abstract

The present invention relates to a frequency offset estimation method for average consensus-based clock synchronization, and belongs to the technical field of wireless sensor networks. According to the method, in combination with distributed one-way broadcast characteristics, solving of maximum likelihood estimation is converted into a linear optimization problem, and a relative frequency offset estimation value is obtained by adopting an iterative method. By applying the estimation value to the compensation of logic clock parameter between nodes, an effect of keeping logic clocks of network nodes consistent can be achieved. According to the present invention, distribution characteristics of communication time delay are fully considered, accurate relative frequency offset estimation can be implemented, so the synchronization precision of average consensus-based clock synchronization is effectively improved, the maximum likelihood estimation solving is performed by adopting the iterative method, an estimation algorithm is simplified, and storage overhead is reduced.

IPC Classes  ?

• H04W 56/00 - Synchronisation arrangements
• H04J 3/06 - Synchronising arrangements
• H04L 25/02 - Baseband systems Details
• H04L 27/00 - Modulated-carrier systems

Abstract

A scheduling method applied in an industrial heterogeneous network in which a TSN and a non-TSN are interconnected is provided. The TSSDN controller classifies data flows according to the delay requirements, and calculates the scheduling priorities of the data flows in the industrial heterogeneous network. The TSSDN controller adopts an improved CSPF algorithm to determine a shortest path in the heterogeneous network, and marks the scheduling priorities of the data flows which are transmitted from the subnet of the heterogeneous network and arrive at the switch for the first time. Flow table matching is performed at the SDN switch. In a case of performing flow table matching successfully, the counter is updated and the instruction included in the flow table is executed. In a case of performing flow table matching unsuccessfully, a PacketIn message is transmitted to the TSSDN controller, and the TSSDN controller performs analysis and makes a decision.

IPC Classes  ?

• H04L 47/52 - Queue scheduling by attributing bandwidth to queues
• H04L 41/0896 - Bandwidth or capacity management, i.e. automatically increasing or decreasing capacities
• H04L 45/00 - Routing or path finding of packets in data switching networks
• H04L 47/24 - Traffic characterised by specific attributes, e.g. priority or QoS
• H04L 47/56 - Queue scheduling implementing delay-aware scheduling

Abstract

The present invention relates to a judgment method for edge node computing result trustworthiness based on trust evaluation, and belongs to the technical field of data processing. By means of the present invention, a security mechanism for trustworthiness of a computing result output by an industrial edge node is guaranteed, the industrial edge node is prevented from outputting error data, and attacks of false data of malicious edge nodes are resisted, it is guaranteed that trustworthy computing results not be tampered are input in the industrial cloud, and a site device is made to receive correct computing results rather than malicious or meaningless messages, thereby improving efficiency and security of industrial production.

IPC Classes  ?

• H04L 9/32 - Arrangements for secret or secure communicationsNetwork security protocols including means for verifying the identity or authority of a user of the system
• H04L 9/40 - Network security protocols

Abstract

A time series data adversarial sample generating method and system, an electronic device, and a storage medium, relating to the field of time series data processing. The method comprises: training a time series prediction model using original time series data (101); calculating a maximum value of a loss function in the time series prediction model by means of a stochastic gradient descent optimization strategy (102); determining corresponding noise according to the maximum value of the loss function (103); and superimposing the noise on the original time series data to generate a globally disturbed time series data adversarial sample (104). The method can significantly reduce the model accuracy under the condition of a small amount of data disturbance, has important significance for safe application of an industrial system, and has wide applicability and transferability.

IPC Classes  ?

• G06Q 10/04 - Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"

Abstract

The present invention relates to the field of machine learning and deep learning, and relates to a user portrait construction method based on microblog heterogeneous information. The method comprises: 1) collecting suitable text data and image data, and respectively training an image classification network and a text classification network; 2) crawling text information and image information of microblogs by using a crawler technology, and obtaining tags, i.e., a user-top matrix, by using the constructed classification networks, and taking the user-topic matrix as a user portrait; 3) performing fuzzy clustering on user-topic to discover a community of a user; 4) performing, using TF-IDF, keyword discovery on the microblogs classified by the user to obtain a topic-item matrix, and calculating an associated word using a knowledge graph concept; and 5) performing user similarity calculation on the community to which the user belongs, selecting a user having a high similarity and repeating the method of step 4), and selecting a keyword as a content supplementation recommendation according to a word frequency threshold. The present invention can recommend a user having high similarity to a user.

IPC Classes  ?

• G06F 16/9535 - Search customisation based on user profiles and personalisation
• G06F 40/247 - ThesaurusesSynonyms

Abstract

The present application relates to the technical field of mobile communications, and in particular, to a distributed task offloading and computing resource management method based on energy harvesting, comprising: establishing a task local computing model and an edge cloud computing model; establishing an objective function of a device for maximizing the revenue of the device on the basis of perturbed Lyapunov optimization and an objective function for maximizing the revenue of a mobile edge computing server; the device pre-selecting, according to a pre-screening criterion, a mobile edge computing service server to offload tasks; using a Lagrange multiplier method and a KKT condition to calculate an optimal task quantity strategy for offloading from the device to the selected mobile edge computing server; obtaining an optimal quotation strategy of the mobile edge computing server to the device in each time slot; and obtaining a solution of the optimal task quantity strategy and the optimal dynamic quotation strategy meeting the Stackelberg equilibrium as a resource allocation strategy. The present application realizes stable management of the battery energy level and on-demand allocation of the computing resources for heterogeneous users.

IPC Classes  ?

• H04W 72/04 - Wireless resource allocation

Abstract

The present disclosure relates to systems and methods for a handover. The methods may include establishing a connection between a vehicle terminal and a first macro evolved Node B (MeNB) and a connection between the vehicle terminal and a secondary evolved Node B (SeNB), the vehicle terminal in a dual connectivity mode with the first MeNB and the SeNB; receiving, by the vehicle terminal, a handover command from the first MeNB; and disconnecting, based on the handover command, the vehicle terminal from the first MeNB and establishing synchronization between the vehicle terminal and a second MeNB, wherein the connection between the vehicle terminal and the SeNB is maintained. The SeNB is a secondary vehicle terminal meeting a preset condition or an SeNB installed at a fixed location.

IPC Classes  ?

• H04W 4/00 - Services specially adapted for wireless communication networksFacilities therefor
• H04W 36/00 - Handoff or reselecting arrangements
• H04W 76/34 - Selective release of ongoing connections
• H04W 4/44 - Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P] for communication between vehicles and infrastructures, e.g. vehicle-to-cloud [V2C] or vehicle-to-home [V2H]
• H04W 76/15 - Setup of multiple wireless link connections
• H04W 36/08 - Reselecting an access point
• H04W 36/24 - Reselection being triggered by specific parameters
• H04W 36/30 - Reselection being triggered by specific parameters by measured or perceived connection quality data
• H04W 36/32 - Reselection being triggered by specific parameters by location or mobility data, e.g. speed data
• H04W 36/38 - Reselection control by fixed network equipment
• H04W 56/00 - Synchronisation arrangements

Abstract

The present application belongs to the technical field of satellite communications, and in particular relates to a routing method based on fuzzy logic in a low earth orbit satellite network. The method comprises: on the basis of a control policy of a virtual topology, shielding the dynamics of a satellite network topology, initializing a satellite set, and marking the superiority of an inter-satellite link of two satellites, which are not directly connected to each other, to be infinitely small; according to degrees of membership of transmission time delay, propagation time delay and queuing time delay, calculating the superiority of a link formed from a source node to a target node; searching for the superiority of paths between all the nodes in a satellite set Y and the source node, selecting a node k with the highest link superiority at present, putting the node into a set X, and deleting the node from Y; and monitoring, in real time, states of neighbor nodes around the node k in the satellite set, updating the superiority of links from the source node to all the nodes in the satellite set Y, and performing rerouting according to the superiority of a path between a source node s and the node k. By means of the present application, self-adaptive adjustment can be performed on blockage and failures.

IPC Classes  ?

• H04B 7/185 - Space-based or airborne stations

Abstract

The present invention relates to the field of signal processing, and to a sparse LMS method combining zero attraction penalty and attraction compensation. In the method, zero attraction penalty and attraction compensation are combined, coefficients of an estimation filter are divided into a near-zero coefficient, a small coefficient and a large coefficient, and then different attraction methods are used. In each iteration update, for the near-zero coefficient of the estimation filter, only a product term in an iterative update formula is used to calculate; for the large coefficient of the estimation filter, a trace amount of attraction compensation is performed thereon to accelerate the convergence speed of the estimation filter coefficient approaching a large coefficient of a channel; and for the small coefficient of the estimation filter, if the coefficient approaches a zero coefficient value or a large coefficient value of the channel during iteration, processing is performed according to the methods for the near zero coefficient and the large coefficient of the estimation filter, respectively, or otherwise, simple zero attraction penalty is performed on the small coefficient. The method is high in convergence speed, low in complexity and wide in the scope of application of a tuning parameter.

IPC Classes  ?

• H04L 25/02 - Baseband systems Details
• H04M 9/08 - Two-way loud-speaking telephone systems with means for conditioning the signal, e.g. for suppressing echoes for one or both directions of traffic

Abstract

Provided is a path parameter extraction method for a millimeter wave 3D MIMO channel, which belongs to the field of communication channel parameter extraction. The method comprises the following steps: S1. obtaining wireless channel measurement data, and integrating the measurement data into a channel matrix; S2. increasing the vertical dimension of a guide vector in the channel matrix in S1, and dividing path parameters to be estimated into three parameter subsets: propagation delay, horizontal and vertical angles at a transmitting end, and horizontal and vertical angles at a receiving end; S3. performing iterative operation on each path channel parameter by using a joint search policy of time delay and three-dimensional space angle, and updating channel parameters in a current parameter subset to be estimated; and S4. on the basis of the extraction result in S3, performing multi-path cluster characteristic analysis, and obtaining intra-cluster delay extension and angle extension features. The described method is suitable for extracting parameters of a millimeter wave 3D MIMO wireless channel, and can ensure the accuracy and resolution in the extraction of the parameters of a sparse multi-path channel.

IPC Classes  ?

• H04B 17/309 - Measuring or estimating channel quality parameters

Abstract

A method for image processing, which comprises the following steps: Generating a first histogram from a first image; Calculating a first parameter profile from the first image indicative of the quality of the first image; Adjusting the first parameter profile to generate a second parameter profile; Using the second parameter profile to generate a statistical distribution via a statistical distribution generator, wherein the statistical distribution is characterized by at least three parameters; Using the statistical distribution to perform a histogram specification to the first histogram of the first image to generate a second histogram; Generating a second image based on the first image and the second histogram.

IPC Classes  ?

• G06T 5/40 - Image enhancement or restoration using histogram techniques
• G06T 5/00 - Image enhancement or restoration
• G06T 5/10 - Image enhancement or restoration using non-spatial domain filtering
• G06T 5/50 - Image enhancement or restoration using two or more images, e.g. averaging or subtraction
• H04N 1/60 - Colour correction or control

Abstract

The present invention relates to the field of digital signal processing, and in particular to a Costas sequence time-frequency joint synchronization method based on all-phase spectrum correction. The method improves the defects existing in a discrete frequency spectrum correction algorithm using short-time Fourier transform and sliding correlation. The improvement mainly comprises: the present invention provides a solution based on iterative optimization: when an actual frequency offset is an integral multiple of the spectral resolution, a large error can occur, frequency offset correction and time delay correction are carried out on a signal by using an estimated value having a large estimated error, then estimation is carried out again, and the frequency offset of the signal is not a special value by means of an iteration mode. In order to solve the second problem, due to errors caused by spectrum leakage, all-phase Fourier transform is used for replacing FFT in short-time Fourier transform to reduce the spectrum leakage phenomenon as much as possible. Estimation precision of an original algorithm is improved by improving the two points.

IPC Classes  ?

• H04L 27/00 - Modulated-carrier systems

Abstract

The present invention relates to the technical field of short-wave data communication, and relates in particular to a Watterson model-based short-wave aviation mobile channel modeling method, comprising acquiring the operating state of an aircraft, the operating state of the aircraft comprising the maximum moving speed, acceleration, maneuvering frequency, and motion trajectory of the aircraft; constructing a short-wave aviation mobile channel model according to the operating state of the aircraft and an improved Watterson model; and in the improved Watterson model, by re-modeling the Doppler shift of a channel, constructing the Doppler shift into a time-varying Doppler shift related to the motion state. By studying the effect of the maximum moving speed and acceleration, maneuvering frequency, motion trajectory and other factors of an aircraft on a short-wave aviation mobile channel, the present invention combines the complexity of a moving scene with channel fading, reflects all features of short-wave mobile communication, and has important reference value for further research into short-wave aviation mobile communication systems.

IPC Classes  ?

• H04B 17/391 - Modelling the propagation channel

Abstract

The present invention provides a factory power management and control method based on edge-cloud coordination, including: 1) forming an industrial field network by a field node, a routing node and a device executing production tasks; 2) parsing production task information data and sending; 3) issuing an STN model in production field to an edge node; 4) sending to the edge node; 5) computing, required to complete the production tasks; 6) computing values of comprehensive ranks; 7) executing, by the edge node, the higher rank, and executing, by the cloud power management center, the lower rank; 8) executing, by the edge node, a demand response algorithm; 9) executing, by the production device, the production tasks based on computing results; and executing, by a power generation station in factory, a power storage station in factory and a power supply station outside factory, corresponding schemes based on the results.

IPC Classes  ?

• G06F 1/00 - Details not covered by groups and
• G06F 1/329 - Power saving characterised by the action undertaken by task scheduling
• G05B 19/418 - Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
• G06F 9/50 - Allocation of resources, e.g. of the central processing unit [CPU]
• G06F 1/3203 - Power management, i.e. event-based initiation of a power-saving mode

Abstract

The present invention relates to the field of decoder hardware design, and provides a hierarchical semi-parallel LDPC decoder system having a single permutation network. The system comprises a hierarchical decoding architecture of a single permutation network, a hierarchical semi-parallel decoding architecture of the single permutation network, pipeline design of hierarchical semi-parallel decoding, and a hardware architecture of a hierarchical semi-parallel LDPC decoder. According to the present invention, by changing a cyclic shift value of each information block transferred from a variable node to a check node, a permutation network module between the check node and the variable node is removed, that is, a cyclic shift operation of the decoder can be completed by the single permutation network, so that hardware resources of the decoder are reduced. A semi-parallel decoding structure is adopted, and a pipeline is added between the half layers. The variable node parallelism of the decoder having the semi-parallel structure is only half of a code length compared to a decoder having a hierarchical full-parallel structure, but 3/4 throughput can be achieved and the hardware resources are reduced by half.

IPC Classes  ?

• H03M 13/11 - Error detection or forward error correction by redundancy in data representation, i.e. code words containing more digits than the source words using block codes, i.e. a predetermined number of check bits joined to a predetermined number of information bits using multiple parity bits

Abstract

A fine-grained data stream reliable offloading method based on a callback mechanism. The offloading method comprises: a client device establishing a connection with an edge cloud server according to MQTT; extracting a coarse-grained data stream according to a first specific frame fragment corresponding to a data stream type; using a convolutional neural network to extract a fine-grained data stream from a second specific frame fragment in the coarse-grained data stream; the client device determining whether the fine-grained data stream needs to be offloaded to a server; and if the fine-grained data stream needs to be offloaded to a server, a client uploading the fine-grained data stream to the edge cloud server, the edge cloud server returning an uplink callback message to the client device, the edge cloud server generating a result after processing data, and returning the result to the client device, and the client device returning downlink callback information to the edge cloud server; otherwise, directly locally processing, on the client device, the fine-grained data stream and generating a result. By means of the offloading method, the uploading of data to a server and the issuing of a result to a client are guaranteed on the basis of the callback mechanism, thereby significantly improving the QoE and improving the utilization rate of computing resources.

IPC Classes  ?

• G06F 9/48 - Program initiatingProgram switching, e.g. by interrupt
• G06F 9/445 - Program loading or initiating
• G06F 9/54 - Interprogram communication
• G06N 3/02 - Neural networks

Abstract

The present application relates to the technical field of mobile communications, and specifically relates to an evolutionary game-based multi-user switching method in a software-defined satellite network system. The multi-user switching method comprises: respectively calculating the elevation angle and the remaining coverage time of a satellite according to obtained information, and calculating the payoff according to three basic factors, i.e., the capacity, the elevation angle, and the remaining coverage time of the satellite; a controller calculating the average payoff of users in the area, and broadcasting same to the users; when it is determined that the payoff of all the users is greater than the average payoff, ending multi-user switching; and when it is determined that the payoff of all the users is not greater than the average payoff, the users selecting other switching satellites having higher payoffs. According to the present application, a multi-user switching problem is modeled into an evolutionary game problem; evolutionary equilibrium serves as an equilibrium solution of the game; the dynamic policy adjustment process is repeated until an equilibrium state is reached; the optimal policy proportion is solved; it is guaranteed that all the users can obtain the best service after switching, and thus the fairness of the users is guaranteed.

IPC Classes  ?

• H04B 7/185 - Space-based or airborne stations

Abstract

A method for predicting a remaining life of a tool of a computer numerical control machine is provided. In the method, indirect measurement indicators of the tool are selected based on monitoring and analyzing a current state of the tool, a prediction model for the remaining life of the tool is established based on data de-noising, feature extraction and a multi-kernel W-LSSVM algorithm. Thereby, a method for predicting a remaining life of a tool of a computer numerical control machine is provided.

IPC Classes  ?

• G01N 29/14 - Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic wavesVisualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object using acoustic emission techniques
• G05B 19/4065 - Monitoring tool breakage, life or condition
• G01N 29/44 - Processing the detected response signal
• G01M 13/00 - Testing of machine parts

Abstract

The present invention relates to the technical field of communications, and particularly relates to a low-complexity selected mapping method using cyclical redundancy check. The method comprises: when a sending end performs encoding, add a check bit to a sent information bit so as to obtain modulated data; demodulate an M-order modulation symbol received by a receiving end to obtain a decoding result of an encoded polynomial of the modulation symbol and bit information received by the receiving end; calculate the decoding result of the encoded polynomial and a modulo-2 division result of a generator polynomial; when the remainder of the modulo-2 division result is zero, and if the modulated data corresponding to the same index value of the receiving end and the sending end is identical, end iteration in advance, and output the number of iterations at this time to be used as a phase rotation sequence index recovery value; the receiving end obtains a decoded signal according to the phase rotation sequence index recovery value and a modulation symbol that is obtained by performing IFFT on a received signal. The present invention obtains a huge calculation gain, and also obtains the same PAPR suppression effect as the prior art by using a simple phase sequence.

IPC Classes  ?

• H03M 13/09 - Error detection only, e.g. using cyclic redundancy check [CRC] codes or single parity bit

Abstract

The present invention relates to a method of estimating lithium battery capacity based on a convolution long-short-term memory neural network (CNN-LSTM). The present invention obtains a model that lithium battery capacity estimation through the four steps: processing a lithium battery's data, selecting parameters of an improved convolution long-short-term memory neural network using a genetic algorithm, training the improved CNN-LSTM, and testing model. Hyper-parameters of the improved CNN-LSTM are optimized using the genetic algorithm. Using the convolution neural network to extract the spatial features of lithium battery charge and discharge data, and then input these features into the improved long-short-term memory neural network to extract temporal features, estimated capacity is output through a fully connected layer finally. The present invention overcomes the limitation of the traditional model-based algorithm overly relying on the battery model and has the engineering application prospect.

IPC Classes  ?

• G06N 3/04 - Architecture, e.g. interconnection topology
• G06N 3/08 - Learning methods
• G01R 31/00 - Arrangements for testing electric propertiesArrangements for locating electric faultsArrangements for electrical testing characterised by what is being tested not provided for elsewhere
• G01R 31/367 - Software therefor, e.g. for battery testing using modelling or look-up tables
• G01R 31/396 - Acquisition or processing of data for testing or for monitoring individual cells or groups of cells within a battery

Abstract

A cavity optomechanical vibratory gyroscope pertains to technical fields of resonant optical gyroscopes and micro-optical-electro-mechanical systems. A novel cavity optomechnical Coriolis vibratory micro gyroscope is realized based on ring micro rings and the Coriolis vibration principle, and driving and detection thereof is completely different from conventional electric or magnetic means. Based on the principle of angular velocity sensitive structures in the conventional Coriolis vibratory gyroscopes, full-optical driving, detecting and sensing of a vibratory gyroscope are achieved using cavity optomechnical technologies, which fundamentally suppresses various noises (including thermal noise, cross interference, connection point noise and quadrature error) introduced by electric or magnetic driving. Besides, displacement (vibration) sensing information is obtained according to a linear relationship between frequency shift and light amplitude in the micro cavity optomechnical effect.

IPC Classes  ?

• G01C 19/5684 - Turn-sensitive devices using vibrating masses, e.g. vibratory angular rate sensors based on Coriolis forces using the phase shift of a vibration node or antinode of essentially two-dimensional vibrators, e.g. ring-shaped vibrators the devices involving a micromechanical structure
• G01C 19/5733 - Structural details or topology