System and methods for relational time-series learning are provided. Unlike traditional time series forecasting techniques, which assume either complete time series independence or complete dependence, the disclosed system and method allow time series forecasting that can be performed on multivariate time series represented as vertices in graphs with arbitrary structures and predicting a future classification for data items represented by one of nodes in the graph. The system and methods also utilize non-relational, relational, temporal data for classification, and allow using fast and parallel classification techniques with linear speedups. The system and methods are well-suited for processing data in a streaming or online setting and naturally handle training data with skewed or unbalanced class labels.

A gesture recognition device and method using radar are proposed. The gesture recognition device includes: a signal receiving unit for receiving a radar signal reflected by a gesture of a user; a clutter removing unit for removing clutter from the signal received by the signal receiving unit; and a signal magnitude variance acquiring unit for acquiring the variance of a signal magnitude from a reflection signal from which the clutter has been removed. The proposed device and method have an advantage of enabling a gesture to be recognized with performance that is robust to changes in distance and direction between a user and a radar sensor.

A processor-implemented method of generating feature data includes: receiving an input image; generating, based on a pixel value of the input image, at least one low-bit image having a number of bits per pixel lower than a number of bits per pixel of the input image; and generating, using at least one neural network, feature data corresponding to the input image from the at least one low-bit image.

Techniques are disclosed for automatically calibrating a reference orientation of an implantable medical device (IMD) within a patient. In one example, sensors of an IMD sense a plurality of orientation vectors of the IMD with respect to a gravitational field. Processing circuitry of the IMD processes the plurality of orientation vectors to identify an upright vector that corresponds to an upright posture of the patient. The processing circuitry classifies the plurality of orientation vectors with respect to the upright vector to define a sagittal plane of the patient and a transverse plane of the patient. The processing circuitry determines, based on the upright vector, the sagittal plane, and the transverse plane, a reference orientation of the IMD within the patient. As the orientation of the IMD within the patient changes over time, the processing circuitry may recalibrate its reference orientation and accurately detect a posture of the patient.

A system comprises an authentication sub-system configured to authenticate a user and a biochemical analysis sub-system configured to perform a biochemical analysis on a biological sample provided to the biochemical analysis sub-system. The system is configured to authenticate a user using the authentication sub-system, instruct an authenticated user to provide a biological sample to the biochemical analysis sub-system, execute a biochemical analysis on a provided biological sample.

Industries deploy a plethora of sensors that are attached to a system or human being, respectively. Under multi-sensor environment scenarios, there is a need to detect which sensors are behaving similarly within a time span. Sensor values often vary in range of values yet depict similar time series characteristic and sometimes have a phase difference in operation, thus making it impossible to detect such sensor similarity in a large system where the number of input parameters/sensor observations. Systems and methods of the present disclosure determine similar behavioral pattern between time series data obtained from multiple sensors and cluster the sensors. The system implements a pattern recognition-based approach to find the similarity and then applies a Dynamic Programming-based approach to detect similarity in at least two time series data and cluster the sensors and corresponding time series data into specific cluster(s).

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training and deploying machine-learned compact representations of radio frequency (RF) signals. One of the methods includes: determining a first RF signal to be compressed; using an encoder machine-learning network to process the first RF signal and generate a compressed signal; calculating a measure of compression in the compressed signal; using a decoder machine-learning network to process the compressed signal and generate a second RF signal that represents a reconstruction of the first RF signal; calculating a measure of distance between the second RF signal and the first RF signal; and updating at least one of the encoder machine-learning network or the decoder machine-learning network based on (i) the measure of distance between the second RF signal and the first RF signal, and (ii) the measure of compression in the compressed signal.

A touch device with the FPR function includes a plurality of sensing regions, a plurality of first switch sets, a plurality of first shift register circuits, a plurality of second switch sets, and a plurality of second shift register circuits. The first switch sets are coupled to transmitting electrodes and to transmit a first signal. The first shift register circuits are to control the first switch sets according to a plurality of first reset signals and a plurality of first control signals respectively. The second switch sets are coupled to receiving electrodes and to receive a second signal. The second shift register circuits are to control the second switch sets according to a second reset signal and a plurality of second control signals. The first signal and the second signal are for a touch operation and a FPR operation.

An embodiment of a data pattern analysis optimizer includes a time sequence data memory, an estimator, a grouping unit, and a time sequence pattern extractor. The time sequence data memory stores a plurality of time sequence data made from items in time order. The estimator estimates the upper limit of the total number of types of time sequence patterns present in the time sequence data at a rate higher than a minimum support level, based on a respective rate of presence of each item, wherein each of the time sequence patterns present in the time sequence data is a predefined number of items. In case that the estimated upper limit exceeds an upper limit of the number of types of time sequence patterns as a maximum processing load to a computer, the grouping unit groups a plurality of time sequence data into sub-groups, based on a group of items having the increased number of items and gives the estimator instructions to perform estimation. The time sequence pattern extractor gives the computer instructs to extract the time sequence patterns for each of the sub-groups, in case that the estimated upper limit does not exceed the upper limit of the number of time sequence patterns.

An apparatus, methods and systems for data collection in an industrial environment are disclosed. A monitoring system can include a data collector coupled to a plurality of sensors to collect data, a data storage structured to store a plurality of data collection management plans, a data acquisition circuit structured to interpret a plurality of detection values from the collected data, and a data analysis circuit structured to analyze the collected data and select one of the plurality of data collection management plans, wherein the selected one of the plurality of data collection management plans is selected is at least in part based on a data analysis of received data from the plurality of sensors.