A learning device (10) includes an acquirer (11), a learner (12), and a generator (14). The acquirer (11) acquires a learning signal. The learner (12) performs, in accordance with similarities indicating degrees of similarity between waveforms, clustering of partial signals cut out from the learning signal acquired by the acquirer (11), and learns reference waveforms that each indicate a waveform of a corresponding partial signal of the clustered partial signals. The generator (14) generates, based on at least one of a distribution of the similarities or characteristics of clusters that each include a corresponding partial signal of the clustered partial signals, progress information indicating a progress status of the learning by the learner (12), and outputs the progress information.

According to one embodiment, a condition monitoring device includes a processor. The processor is configured to acquire a time-series signal about a condition of a monitor target from a first sensor, acquire operation timing information indicating start of operation of the monitor target, detect a first operation segment signal from the time-series signal based on the operation timing information, detect a second operation segment signal from the first operation segment signal based on a waveform feature of the first operation segment signal, and determine the condition of the monitor target based on the second operation segment signal.

Methods, systems and computer program products for speech and gesture interaction of multiple users with devices using voice activated interfaces are provided herein. A computer-implemented method includes transmitting a pilot signal from a device comprising a voice activated interface, the pilot signal having a frequency, detecting motion of at least one user around the device, associating the detected motion with a gesture, and performing a function in response to the gesture. Detecting the motion includes receiving a reflected signal of the pilot signal caused by the motion of the at least one user, and detecting a shift in the reflected signal from the pilot signal, wherein detecting the shift comprises determining one or more differences between a waveform corresponding to the pilot signal and a waveform corresponding to the reflected signal.

Embodiments of the disclosure are directed towards electricity fraud detection systems that involve a behavioral detection ecosystem to improve the detection rate of electricity fraud while reducing the rate of false-positives. More specifically, machine learning algorithms are eschewed in favor of two separate models that are applied sequentially. The first model is directed to improving the detection rate of electricity fraud through the use of detectors to identify customers engaging in suspicious behavior based on the demand profiles of those customers. The second model is directed to reducing the rate of false-positives by identifying potential legitimate explanations for any suspicious behavior. Subtracting away the suspicious behavior with legitimate explanations leaves only the identified, unexplained suspicious behavior that is highly likely to be associated with fraudulent activity.

An image-processing device, for gas detection that performs image processing on infrared images of a subject being taken at plurality of times a day, includes a hardware processor that generates physical-quantity-change data indicating chronological change in physical quantity determined based on pixel data of pixels constituting the infrared image. The hardware processor selects, from the pixels constituting the infrared image, a reference pixel used as a reference and a comparison pixel to be compared with the reference pixel, and calculates a degree of phase similarity indicating a degree of similarity in phase between a waveform of the physical-quantity-change data of the reference pixel and a waveform of the physical-quantity-change data of the comparison pixel. The hardware processor determines, based on the degree of phase similarity, that an image including the reference pixel and the comparison pixel is not a gas image.

The motion performance of an animal that makes a motion in response to the movement of at least one moving body other than the animal, which is a subject for evaluation, is properly evaluated. The motion data of the animal is acquired by manipulating the difficulty factor of the motion which is made by the animal in response to the movement of the moving body, and the motion performance of the animal is evaluated based on the motion data of the animal. It is to be noted that the motion data contains information indicating the timing of the motion of the animal.

The present application discloses a lip-language recognition AAC system based on surface electromyography, which includes: a training subsystem configured to collect the facial and neck EMG signals during lip-language movements through the high-density electrode array, improve the signal quality through the signal preprocessing algorithm, classify the lip-language movements through the classification algorithm, select the optimal number of electrodes and optimal positions through the channel selection algorithm, and establish the optimal matching template between the EMG signals and the lip-language information, and upload it to the network terminal for storage; and a detection subsystem configured to collect the EMG signals at the optimal positions during the lip-language movements based on the optimal number and positions of electrodes selected by the training subsystem, call the optimal matching template, classify and decode the EMG signals, recognize the lip-language information, and convert it into corresponding voice and picture information for display in real time.

Methods and systems for disentangling discriminative features of a user of a device from motion signals and authenticating a user on a mobile device are provided. In at least one aspect of the methods and systems, each captured motion signal is divided into segments. The segments are then converted into translated segments using one or more trained translation algorithms. The segments and translated segments are then provided to a machine learning system. Discriminative features of the user are then extracted from the segments and translated segments with the processor using the machine learning system that applies one or more feature extraction algorithms.

Disclosed is a method and a device of trajectory outlier detection. The method may include: points on a trajectory to be detected are obtained by sampling the trajectory; characteristic points are extracted from the points according to spatial state and temporal state of each of the points; trajectory segments are obtained by segmenting the trajectory according to the characteristic points; each of the trajectory segments is compared to normal trajectory segments and abnormal trajectory segments; and one or more trajectory outliers are identified from the trajectory segments based on comparison results. Wherein, the normal trajectory segments and the abnormal trajectory segments are obtained by clustering trajectory segments in a training set; and the trajectory segments in the training set are obtained by segmenting historical trajectories based on characteristic points extracted from points on the historical trajectories according to spatial state and temporal state of the points.

A method and system for remotely monitoring intoxication of a user, comprising: prompting the user to provide a breath sample at a time point; at a breath sample acquisition device, generating a breath sample signal upon reception of the breath sample from the user, and broadcasting a unique signature proximal in time to the time point; using a sensor of a mobile computing device, generating an authentication signal derived from detection of the unique signature; at a processing system in communication with the mobile computing device and the sample acquisition device, receiving the breath sample signal and the authentication signal; generating a verification assessment that validates provision of the breath sample by the user; determining a value of an intoxication metric for the user based upon the breath sample signal; and transforming the verification assessment and the value of the intoxication metric into an analysis of intoxication of the user.