Embodiments of the disclosure provide a method and system to reduce scattering effects such as multiplicative speckle noise in synthetic aperture radar (SAR) with machine learning. Methods of the disclosure include converting an input image into an enhanced image via an encoder-decoder network having an adversarial learning system. Methods of the disclosure also include identifying a target within the enhanced image by separating the enhanced image into a plurality of segments via a tracker module having at least a spatial attention layer, a channel attention layer, and a depth-wise convolution.
G01S 7/41 - Détails des systèmes correspondant aux groupes , , de systèmes selon le groupe utilisant l'analyse du signal d'écho pour la caractérisation de la cibleSignature de cibleSurface équivalente de cible
G01S 13/66 - Systèmes radar de poursuiteSystèmes analogues
G01S 13/90 - Radar ou systèmes analogues, spécialement adaptés pour des applications spécifiques pour la cartographie ou la représentation utilisant des techniques d'antenne synthétique
2.
RADIO FREQUENCY FINGERPRINTING USING ATTENTIONAL MACHINE LEARNING
Embodiments of the disclosure provide a sensitivity enhancing radio frequency identification technique using machine learning. A method according to the disclosure includes obtaining an input signal associated with a radio frequency (RF) transmission; separately extracting at least two features from a group comprising: spatial domain features, time-frequency domain features, and temporal domain features from the input signal; processing the at least two features to generate an attentional vector; and predicting at least one descriptor for an emitter of the RF transmission based on the attentional vector.
Embodiments of the disclosure provide a machine learning framework to control an autonomous agent in a dynamic environment. A system according to the disclosure includes a sensor coupled to the autonomous agent to receive a set of inputs. At least one actuator causes the autonomous agent to perform an action. A controller causes the actuator to perform an action based on the inputs and an operative policy. The controller determines whether the operative policy is terminated, based on the set of inputs. Upon terminating the operative policy, the controller evaluates several candidate policies and selects one of the candidate policies as a new operative policy.
G05D 1/656 - Interaction avec des charges utiles ou des entités externes
G05B 13/02 - Systèmes de commande adaptatifs, c.-à-d. systèmes se réglant eux-mêmes automatiquement pour obtenir un rendement optimal suivant un critère prédéterminé électriques
G05D 101/15 - Détails des architectures logicielles ou matérielles utilisées pour la commande de la position utilisant des techniques d’intelligence artificielle [IA] utilisant l’apprentissage automatique, p. ex. les réseaux neuronaux
4.
MACHINE LEARNING SYSTEM FOR IDENTIFYING AND COUNTERING NON-FRIENDLY RADAR NETWORKS
Embodiments of the disclosure provide a machine learning system for identifying and countering non-friendly radar networks. Methods of the disclosure include generating, in a machine learning module, an operational model of a radar network within an environment. An autonomous agent within the environment detects the radar network. The method also includes classifying the radar network as friendly or non-friendly based on the operational model. The method also includes generating, in a reinforcement learning module, a counter-radar maneuver based on the operational model in response to classifying the radar network as non-friendly. Embodiments of the disclosure implement the counter-radar maneuver via the autonomous agent in communication with the reinforcement learning module.
The disclosure provides processes to generate an identification tag for a transponder in a wireless network via a machine learning module. Methods of the disclosure include capturing, via a wireless receiver within a wireless network, a plurality of time-domain communication samples of a transponder operating within the wireless network. A multi-dimensional tensor is generated, indicating a plurality of features of the time-domain communication samples of the transponder. A machine learning module converts the multi-dimensional tensor into a one-dimensional feature vector indicating the plurality of features of the time-domain communication samples. The machine learning module extracts a hardware identification feature for the transponder from the one-dimensional feature vector. The machine learning module includes: an embedding component for extracting the one-dimensional feature vector from a multi-dimensional tensor indicating a set of hardware intrinsic features; or an attentional component for deducing a hardware signature from the one-dimensional feature vector.
G06F 7/00 - Procédés ou dispositions pour le traitement de données en agissant sur l'ordre ou le contenu des données maniées
G06K 7/10 - Méthodes ou dispositions pour la lecture de supports d'enregistrement par radiation électromagnétique, p. ex. lecture optiqueMéthodes ou dispositions pour la lecture de supports d'enregistrement par radiation corpusculaire
Embodiments of the disclosure provide distributed authentication with network segmentation and dynamic authorization for networks. The system may include a device within a network of devices. An identifier is within the device and includes a cryptographic certificate. The device is configured to transmit the identifier to an authenticator as a security proof. The authenticator is configured to disable the device from performing at least one operation within the network before verifying an identity of the device via the identifier.
Embodiments of the disclosure provide a sensitivity enhancing radio frequency identification technique using machine learning. A method according to the disclosure includes obtaining an input signal associated with a radio frequency (RF) transmission; separately extracting spatial domain features, time-frequency domain features, and temporal domain features from the input signal; processing the spatial domain features, time-frequency domain features, and temporal domain features to generate an attentional vector; and predicting at least one descriptor for an emitter of the RF transmission based on the attentional vector.
Embodiments of the disclosure provide a system and methodology for secure coexistence between wireless fidelity and cellular networks. Methods include: determining whether a wireless fidelity (WiFi) device is sharing a spectrum of a network; and adjusting a parameter of a cellular device sharing the spectrum in response to determining that the WiFi device is sharing the spectrum, wherein the parameter includes a modulation and coding scheme or a transmission power of the cellular device. Methods further include controlling admission of users to a communications network, including: determining whether an incoming transmission is an authentication request from a new user; issuing a temporary authentication to the user to transmit a set of access requirements to the user; determining whether a reply from the user complies with the set of access requirements; and issuing a long-term authentication to the user in response to the reply complying with the set of access requirements.
A system for governing access to a network environment, including: at least one communication node communicatively coupled to a network infrastructure; a network assurance agent configured to monitor the at least one communication node, wherein the network assurance agent performs actions including: generating, in response to an access request for a network resource from the at least one communication node, an environmental model of the at least one communication node relative to the network environment, wherein the environmental model includes operational data of the at least one communication node or at least one other communication node in the network environment, calculating a risk score for the at least one communication node via a machine learning algorithm, based on the environmental model, and granting or denying the access request based on the risk score.
Embodiments of the disclosure provide a system for operating a radio frequency (RF) network having a plurality of communication nodes. A network transceiver communicates with communication nodes in the RF network. A computing device coupled to the network transceiver performs actions including: evaluating a state of the RF network using a machine learning model, based on a spectrum environment and a communication objective, generating a set of communication parameters based on the state of the RF network, causing the network transceiver to communicate with the a communication node using the generated set of communication parameters, and modifying the machine learning model based on a result of causing the network transceiver to communicate with the communication node.
Embodiments of the disclosure provide a transmission system, including: an encoder for encoding a set of information symbols into a set of encoded signals for transmission, wherein the encoder applies a full-diversity space-time block code (STBC) to the set of information symbols; and at least three antennas for transmitting the set of encoded signals over four epochs at a code rate of two.
Methods and systems for controlling dynamic spectrum access (DSA) for the purposes of wirelessly communicating or exchanging data within a network environment are disclosed. Methods may include detecting, via at least one asset included in a wireless device network, at least one candidate asset attempting to enter the wireless device network from an external network, and constructing a spectrum profile for the wireless device network based on metadata for transactions between assets in the wireless device network. The method may also include applying an access policy including the spectrum profile to the at least one candidate asset within the wireless device network, and admitting the at least one candidate asset to the wireless device network in response to applying the access policy to the at least one candidate asset.
A vertebral assist device for monitoring, supporting, stabilizing, and adjusting vertebrae. An embodiment of the vertebral assist device includes: a plurality of vertebral support sections, each of the plurality of vertebral support sections configured to support a respective vertebra of a patient; an actuating system for interconnecting each adjacent pair of the plurality of vertebral support sections, the actuating system dynamically controlling an alignment of the plurality of vertebral support sections; and a control system for actively monitoring the alignment of the plurality of vertebral support sections and for directing the actuating system to dynamically adjust the alignment of the plurality of vertebral support sections until an alignment goal is achieved.
A61B 17/70 - Dispositifs de mise en position ou de stabilisation de la colonne vertébrale, p. ex. stabilisateurs comprenant un liquide de remplissage dans un implant
A61F 2/48 - Moyens d'actionnement ou de commande, p. ex. de l'extérieur du corps, commande de sphincters
A61B 17/00 - Instruments, dispositifs ou procédés chirurgicaux
42 - Services scientifiques, technologiques et industriels, recherche et conception
Produits et services
Computer programming and software design; Design and development of computer software; Design, development and implementation of software; Developing computer software
