Abstract: A method for a target image reconstruction is provided. The method includes emitting stepped frequency waveforms having different constant frequencies at different periods of time, modulating the stepped frequency waveforms into frequency ranges each having a first frequency and a second frequency, wherein each of the stepped frequency waveforms are increased from the first frequency to the second frequency based on a range function, wherein the modulated stepped frequency waveforms are arranged with some sparsity factor.

Abstract: A system for sensing a state of a device is provided. The system includes an autoencoder comprising an encoder, a latent subnetwork, and an extended decoder. The encoder encodes each input data point of input data from an input state space into a latent space to produce latent data points and propagates the latent data points with a neural Ordinary Differential Equation (ODE) to estimate an initial point of latent dynamics of the device in the latent space. The latent subnetwork propagates the initial point till a time index of interest using the neural ODE to produce a state of latent dynamics of the device at the time index of interest. The extended decoder decodes the state of latent dynamics of the device into an output state space different from the input state space to produce output data including the state of the device at the time index of interest.

Abstract: A distance estimation method comprises transmitting a wave of radiation modulated in frequency domain by an emitter to a scene, receiving a reflection of the transmitted wave from the scene, and interfering a copy of the transmitted wave with the received reflection to generate a sequence of samples of the beat signal with wrapped phases in a time domain. The method also comprises estimating a frequency of the beat signal in the time domain in an iterative manner until a termination condition is met. The iterative estimation of the frequency of the beat signal is based on phase unwrapping of the samples of the beat signal subject to correlated phase error derived from phase noise statistics of the emitter and a linear regression fitting the frequency of the beat signal into the unwrapped phases of the beat signal.

Abstract: A network manager is provided for delivering a firmware/software program to multi-mode nodes and single-mode nodes arranged in a multi-hop wireless IoT network. The network manager includes a transceiver configured to perform wireless communication by transmitting the encoded packets of the firmware/software program to the first-hop nodes. The network manager divides firmware/software program into source blocks, encodes the source blocks into encoded blocks based on coding scheme, packs the encoded blocks into encoded packets, transmits the encoded packets to the first-hop nodes. In this case, the first-hop nodes are configured to receive, decode, re-encode and re-transmit the encoded packets to propagate firmware/software distribution to the other-hop nodes. The network manager keeps broadcasting the encoded packets to the first-hop nodes until a predetermined percent of the first-hop nodes receive the firmware/software program.

Abstract: A system for automated construction of an artificial neural network architecture is provided. The system includes a set of interfaces and data links configured to receive and send signals, wherein the signals include datasets of training data, validation data and testing data, wherein the signals include a set of random number factors in multi-dimensional signals X, wherein part of the random number factors are associated with task labels Y to identify, and nuisance variations S. The system further includes a set of memory banks to store a set of reconfigurable deep neural network (DNN) blocks, hyperparameters, trainable variables, intermediate neuron signals, and temporary computation values including forward-pass signals and backward-pass gradients.

Abstract: A Bluetooth-enabled device is provided, the Bluetooth-enabled device being configured to control a radio frequency (RF) chain during a first period to receive at a single antenna selected from a plurality of antennas, a constant tone extension (CTE) signal of multiple frames transmitted by the Bluetooth-enabled transmitter over multiple frequencies. Further the RF chain is controlled during a second period to switch among the plurality of antennas to receive the CTE signal at each of the plurality of antennas. An initial time-of-flight (ToF) data of the CTE signal is determined from first samples of the CTE signal received during the first period. Further, the Bluetooth-enabled transmitter is localized with respect to a location of the Bluetooth-enabled device using a signal model connecting samples of the CTE signal with an unknown angle-of-arrival of the CTE signal received at specific times, an unknown ToF conditioned on the initial ToF data.

Abstract: Data communications and storage systems require error control techniques and digital modulation schemes to be transferred efficiently and successfully. Constellation shaping based on probabilistic amplitude shaping (PAS) offers an energy-efficient transmission in particular for long shaping blocks. However, longer shaping blocks can cause burst errors and enhancement of bit error rates besides longer latency to complete distribution matcher and dematcher operations. Methods and systems are disclosed that provide a way to resolve the issues by introducing a dual concatenation of pre-shaping and post-shaping error correction codes to mitigate burst errors of shaping. This enables low-complexity, high-performance and parallel architecture with a balanced overhead of dual-concatenation codes for shaping systems.

Abstract: A computer-implemented pre-processed time-delay autoencoder based anomaly detection method are provided for detecting anomalous states of machines arranged in a factory automation (FA) system or a manufacturing production line.

Abstract: An optical coherence tomography (OCT) system comprises an interferometer configured to split incident light into a reference beam and a test beam, and to interfere the test beam reflected from the specimen with the reference beam reflected from a reference mirror to produce an interference pattern. The OCT system also comprises a spectrometer configured to analyze spectral components of the interference pattern at non-uniformly sampled wavenumbers. A computer-readable memory of the OCT system is configured to store a measurement model with elements connecting different depth values with different non-uniformly sampled wavenumbers and weighted with weights derived from a power spectral density (PSD) of the incident light for corresponding wavenumbers. The OCT system further comprises a processor configured to determine the profilometry measurements of the specimen as a maximum likelihood estimate of the specimen surface depth by back-projection of the measured intensities with the measurement model.

Abstract: A system for fusion of Wi-Fi measurements from multiple frequency bands to monitor indoor and outdoor space is provided. The system includes a multi-band wireless network comprising a set of radio devices to provide coverage in an environment, wherein the set of radio devices are configured to establish wireless communication or sensing links over multi-band wireless channels, wherein the multi-band wireless channels use a first radio band at a millimeter wavelength and a second radio band at a centimeter wavelength. The system further includes a computing processor communicatively coupled to the set of radio devices and a data storage, wherein the data storage has data comprising a parameterized model, modules and executable programs.

Abstract: The present disclosure provides a method and a system for training a neural network suitable for localization of a device within an environment based on signals received by the device. The method comprises training a bi-regressor neural network to identify locations from labeled data, wherein the bi-regressor neural network includes a feature extractor and a bi-regressor including two regressors; training parameters of the bi-regressor using the labeled data and unlabeled data, such that each of the two regressors identifies the same labeled locations while processing the labeled data and identifies different locations while processing the unlabeled data; and training parameters of the feature extractor using an adversarial discriminator to extract domain invariant features from the unlabeled data with statistical properties of the labeled data according to the adversarial discriminator such that each of the two regressors identifies the same locations while processing the domain invariant features.

Abstract: A system and method for automated construction of a stochastic deep neural network (DNN) architecture is provided. The framework of invention automatically searches for most relevant stochastic modes underlaying datasets for variational Bayesian inference. The invention provides a way to use heterogenous, irregular, and mismatched beliefs in stochastic sampling for intermediate representation in DNNs with a capability of an automatically tuning mechanism of posterior, prior, and likelihood models to enable accurate generative models and uncertainty models for machine learning tasks. The system further allows adjustable discrepancy measure to regularize intermediate representation by variants of divergence metrics including Renyi's alpha, beta, and gamma divergences. The invention enables diverse mixture combinations of stochastic models for misspecified and unspecified probabilistic relations in an automatic fashion.

Abstract: A system and a computer-implemented method using physics-informed neural network (PINN) are provided for data communications. At a transmitter, the method is configured to acquire source data to be transmitted, encode the source data to codewords based on forward error correction (FEC) codes, map the codewords to amplitude symbols, modify the mapped amplitude symbols to pre-equalized symbols including pre-distort channel impairments symbols based on a predetermined physical model, and transmit digital data of the pre-equalized symbols over a channel as channel data.

Abstract: Communication-capable devices such as commercial Wi-Fi devices can be used for integrated sensing and communications (ISAC) systems to jointly exchange data and monitor environment. Such devices typically require diverse signal processing such as machine learning inference that demands high-power operations for real-time sensing and computing. The present invention provides a way to realize energy-efficient computing by exploiting the capability of data communications to access distributed computing resources including classical computers and quantum computers over networks. The system and method are based on the realization that computationally intensive processing is offloaded to networked hybrid classical-quantum computing to build dynamic computing graphs. Some embodiments use automated classical-quantum machine learning whose circuits and hyperparameters are automatically adjusted via gradient or heuristic optimization for Wi-Fi indoor monitoring and human tracking.

Abstract: A reconfigurable device is provided for splitting optical beams. The device includes an input port configured to receive an input beam including at least two primary wavelengths, a tunable splitter configured to separate the input beam into at least two beams via at least two routes corresponding to the at least two primary wavelengths, wherein each of the at least two routes is configured to propagate one of the at least two primary wavelengths of the input beam, wherein the tunable splitter includes a bottom electrode, a substrate on the bottom electrode, core segments arranged on the substrate, a top layer, support segments to connect the substrate and the top layer, a top electrode on the top layer, a controllable refractive index layer arranged to fill gaps between the substrate, the support segments, and the top layer; and at least two output ports configured to transmit the at least two beams propagated via the at least two routes.

Abstract: Provided herein is a method for controlling a manipulator, comprising accepting an initial pose of a load and a task for moving the load and retrieving using a mapping function, an identification trajectory corresponding to the initial pose of the load and controlling a plurality of actuators of the manipulator to move the load according to the retrieved identification trajectory and obtaining measured motion data and estimated motion data of the load each corresponding to motion of the load. The method further comprises estimating parameters of the load based on the measured motion data and the estimated motion data, obtaining a model of the manipulator having the load with the estimated parameters, and determining a performance trajectory to move the load according to the task based on the obtained model of the manipulator. The method further comprises controlling the actuators to move the load according to the performance trajectory.

Abstract: Embodiments of the present disclosure disclose a method and a system for training a neural network for improving adversarial robustness. The method includes collecting a plurality of data samples comprising clean data samples and adversarial data samples. The training of the neural network includes training of a probabilistic encoder to encode the plurality of data samples into a probabilistic distribution over a latent space representation. In addition, the training of the neural network comprising training of a classifier to classify an instance of the latent space representation to produce a classification result. In addition, the method includes training shared parameters of a first instance of the neural network using the clean data samples and a second instance of the neural network using the adversarial data samples. Further, the method includes outputting the shared parameters of the first instance of the neural network and the second instance of the neural network.

Abstract: A Bluetooth-enabled device is provided, the Bluetooth-enabled device being configured to control a radio frequency (RF) chain during a first period to receive at a single antenna selected from a plurality of antennas, a constant tone extension (CTE) signal of multiple frames transmitted by the Bluetooth-enabled transmitter over multiple frequencies. Further the RF chain is controlled during a second period to switch among the plurality of antennas to receive the CTE signal at each of the plurality of antennas. An initial time-of-flight (ToF) data of the CTE signal is determined from first samples of the CTE signal received during the first period. Further, the Bluetooth-enabled transmitter is localized with respect to a location of the Bluetooth-enabled device using a signal model connecting samples of the CTE signal with an unknown angle-of-arrival of the CTE signal received at specific times, an unknown ToF conditioned on the initial ToF data.

Abstract: A system for flexible regularization and adaptable scaling of an artificial neural network is provided.

Abstract: Embodiments of the present disclosure disclose a method and a system for training a neural network for generating universal adversarial perturbations. The method includes collecting a plurality of data samples. Each of the plurality of data samples is identified by a label from a finite set of labels. The method includes training a probabilistic neural network for transforming the plurality of data samples into a corresponding plurality of perturbed data samples having a bounded probability of deviation from the plurality of data samples by maximizing a conditional entropy of the finite set of labels of the plurality of data samples conditioned on the plurality of perturbed data samples. The conditional entropy is unknown. The probabilistic neural network is trained based on an iterative estimation of a gradient of the unknown conditional entropy of labels. The method further includes generating the universal adversarial perturbations based on the trained probabilistic neural network.