Abstract: A deep learning medical device implantable in a body is provided. The device includes a processing and communication unit and a sensing and actuation unit. The processing and communication unit includes a deep learning module including a neural network trained to process the input samples, received from the sensing and actuation unit, through a plurality of layers to classify physiological parameters and provide classification results. A communication interface in communication with the deep learning module receives the classification results for ultrasonic transmission through biological tissue. Methods of sensing and classifying physiological parameters of a body and methods of embedding deep learning into an implantable medical device are also provided.

Abstract: Methods and systems for allocating radio access network (RAN) spectrum resources among a plurality of mobile virtual network operators (MVNOs) of a network of base stations. The methods and systems include determining a slicing enforcement policy that assigns resource blocks (RBs) of frequency units and time slots of spectrum resources to each MVNO according to a slicing policy in which each MVNO is allocated an amount of the spectrum resources on at least one base station in a determined time span. The slicing enforcement policy minimizes overlap between each MVNO's set of RBs with another MVNO's set of RBs on a same base station, and interference between each MVNO's set of RBs with another MVNO's set of RBs on an interfering base station.

Abstract: A polymorphic platform for wireless communication systems is provided that employs trained classification techniques to determine physical layer parameters from a transmitter at a receiver. The system includes a learning module to determine transmitted physical layer parameters of the signal using a trained classification module, such as a deep learning neural network. The trained classification module receives I/Q input samples from receiver circuitry and processes the I/Q input samples to determine transmitted physical layer parameters from the transmitter. The system includes a polymorphic processing unit that demodulates data from the signal based on the determined transmitted parameters.

Abstract: A method of generating a deep neural network (DNN) may comprise receiving one or more application-level requirements associated with network communications, translating the one or more application-level requirements into one or more technical constraints, and providing the one or more technical constraints to a control loop that generates a certified DNN architecture based on the technical constraints. The control loop may further comprise a DNN search engine and a hardware synthesis engine. The method may comprise selecting, using the DNN search engine, a candidate DNN architecture based on the technical constraints, and generating, using the hardware synthesis engine, a hardware architecture corresponding to the selected candidate DNN architecture.

Abstract: A method of determining a response of a radio frequency wireless communication system to an adversarial attack is provided. Adversarial signals from an adversarial node are transmitted to confuse a target neural network of the communication system. An accuracy of classification of the incoming signals by the target neural network is determined.

Abstract: A method of determining a response of a radio frequency wireless communication system to an adversarial attack is provided. Adversarial signals from an adversarial node are transmitted to confuse a target neural network of the communication system. An accuracy of classification of the incoming signals by the target neural network is determined.

Abstract: A system and corresponding method identify a remote device. The system comprises a transceiver and a classifier. The transceiver captures a channel state information (CSI) packet that is sent from a receiver device in response to receiving a calibration packet. The calibration packet is sent by the remote device via transmitter hardware. The classifier extracts a feature set from the CSI packet captured. The feature set is affected by characteristics of the transmitter hardware. The classifier produces a classified feature set by classifying the feature set extracted. The classifier further determines an identifier based on the classified feature set. The identifier corresponds to the remote device. The system enables the remote device to be fingerprinted via the identifier and without the need for software-defined radio (SDR) capabilities. As such, the system can be any low-cost Wi-Fi device, such as a laptop.

Abstract: Apparatuses and methods for real-time spectrum-driven embedded wireless networking through deep learning are provided. Radio frequency, optical, or acoustic communication apparatus include a programmable logic system having a front-end configuration core, a learning core, and a learning actuation core. The learning core includes a deep learning neural network that receives and processes input in-phase/quadrature (I/Q) input samples through the neural network layers to extract RF, optical, or acoustic spectrum information. A processing system having a learning controller module controls operations of the learning core and the learning actuation core. The processing system and the programmable logic system are operable to configure one or more communication and networking parameters for transmission via the transceiver in response to extracted spectrum information.

Abstract: A machine learning (ML) agent operates at a transmitter to optimize signals transmitted across a communications channel. A physical signal modifier modifies a physical layer signal prior to transmission as a function of a set of signal modification parameters to produce a modified physical layer signal. The ML agent parses a feedback signal from a receiver across the communications channel, and determines a present tuning status as a function of the signal modification parameters and the feedback signal. The ML agent generates subsequent signal modification parameters based on the present tuning status and a set of stored tuning statuses, thereby updating the physical signal modifier to generate a subsequent modified physical layer signal to be transmitted across the communications channel.

Abstract: Methods and systems are provided for frequency sharing in RANs using artificial intelligence including scanning, by a spectrum classification unit (SCU) of a channel-aware reactive mechanism (ChARM) app, a plurality of frequencies associated with ongoing communication, classifying, by a DNN of the SCU, I/Q samples of each of the scanned frequencies, the DNN executable via the one or more of the near-RT RIC, the DU, the RU, or combinations thereof, receiving, at a policy decision unit (PDU) from the SCU, the classified frequencies, applying, by the PDU, an embedded policy to the classified frequencies, transmitting commands from the PDU to a DU for making changes to the ongoing communication according to the applied policy, receiving, at a control interface implemented in the DU, the commands transmitted by the PDU, and changing, by the DU according to the commands, an operating parameter of a RU.

Abstract: A system and corresponding method sense an environment. The system comprises a wireless transmitter device that transmits a wireless signal through the environment. The system further comprises a plurality of wireless receivers that each 1) receive the wireless signal at a distinct location within the environment via at least one respective antenna and 2) generate a channel state information (CSI) packet indicating a state of a wireless communications channel associated with the wireless signal. The system still further comprises a computing device and classifier. The computing device processes the CSI packets from the plurality of wireless receivers and generates a CSI dataset as a function of the CSI packets processed. The classifier determines at least one class for the CSI dataset. The system and corresponding method improve robustness of sensing operations, such as robustness of Wi-Fi sensing operations to noise and interference.

Abstract: A system and method for beam management in a wireless network are provided. A learning module having a trained classification module processes received I/Q input samples to determine transmitted beam information of incoming RF transmissions. The learning module includes a beam inference engine to determine waveform characteristics of incoming RF transmissions, and an angle of arrival engine operative to determine an angle of arrival of the incoming RF transmissions on an antenna array. An incoming RF transmission and angle of arrival are selected based on the determined waveforms for beam management operations.

Abstract: An underwater acoustic communication system for a mobile electronic device, such as a smartphone, has a communication unit with one or more ultrasonic transducers to transmit and receive underwater ultrasonic signals. The communication unit is connected to an audio auxiliary interface of the mobile electronic device. A processing unit in communication with the auxiliary interface receives RF signals from and transmits RF signals to the communication unit via the audio auxiliary interface.

Abstract: A networking device, such as an Internet of Things (IoT) device, implements an operative neural network (ONN) to optimize an internal wireless transceiver based on detected radio frequency (RF) spectrum conditions. The wireless transceiver detects the RF spectrum conditions local to the networking device and generates a representation of the RF spectrum conditions. The ONN determines transceiver parameters based on the RF spectrum conditions. A controller causes the representation of the RF spectrum conditions to be transmitted to a network node. Independent of the networking device, a training neural network (TNN) is trained based on the representation of the RF spectrum conditions, and neural network (NN) parameters are generated via the training a function of the representation of the RF spectrum conditions. The controller then reconfigures the ONN based on the NN parameters.

Abstract: A machine learning (ML) agent operates at a transmitter to optimize signals transmitted across a communications channel. A physical signal modifier modifies a physical layer signal prior to transmission as a function of a set of signal modification parameters to produce a modified physical layer signal. The ML agent parses a feedback signal from a receiver across the communications channel, and determines a present tuning status as a function of the signal modification parameters and the feedback signal. The ML agent generates subsequent signal modification parameters based on the present tuning status and a set of stored tuning statuses, thereby updating the physical signal modifier to generate a subsequent modified physical layer signal to be transmitted across the communications channel.

Abstract: A polymorphic platform for wireless communication systems is provided that employs trained classification techniques to determine physical layer parameters from a transmitter at a receiver. The system includes a learning module to determine transmitted physical layer parameters of the signal using a trained classification module, such as a deep learning neural network. The trained classification module receives I/Q input samples from receiver circuitry and processes the I/Q input samples to determine transmitted physical layer parameters from the transmitter. The system includes a polymorphic processing unit that demodulates data from the signal based on the determined transmitted parameters.

Abstract: Methods and systems for allocating radio access network (RAN) spectrum resources among a plurality of mobile virtual network operators (MVNOs) of a network of base stations. The methods and systems include determining a slicing enforcement policy that assigns resource blocks (RBs) of frequency units and time slots of spectrum resources to each MVNO according to a slicing policy in which each MVNO is allocated an amount of the spectrum resources on at least one base station in a determined time span. The slicing enforcement policy minimizes overlap between each MVNO's set of RBs with another MVNO's set of RBs on a same base station, and interference between each MVNO's set of RBs with another MVNO's set of RBs on an interfering base station.

Abstract: A system and method for beam management in a wireless network are provided. A learning module having a trained classification module processes received I/Q input samples to determine transmitted beam information of incoming RF transmissions. The learning module includes a beam inference engine to determine waveform characteristics of incoming RF transmissions, and an angle of arrival engine operative to determine an angle of arrival of the incoming RF transmissions on an antenna array. An incoming RF transmission and angle of arrival are selected based on the determined waveforms for beam management operations.

Abstract: Methods and systems are provided for allocating resources to users in a wireless network including a plurality of edge nodes that provide wireless network access and multi-access edge computing functions. Slice requests are received from the users for a type of resource, including one or more of networking resources, storage resources, and computation resources. A set of slice requests to be admitted is determined based on resource availability constraints among one or more of the networking resources, the storage resources, and the computation resources at each edge node.

Abstract: A communications system provides for accurate fingerprinting of devices across a communications channel. A transmitter device modifies a physical layer signal prior to transmission as a function of signal modification parameters. A receiver device classifies a received physical layer signal and to outputs a classification indicator and a score. The receiver further analyzes the classification indicator and the score to produce an updated set of signal modification parameters provides the parameters to the transmitter device. The transmitter device, in turn, updates its signal modification parameters accordingly, thereby generating subsequent communications that more clearly indicate a fingerprint of the transmitter device.