Techniques for audio tagging of an object of interest are provided. An object of interest within a field of view of a first video camera may be identified at a first time. At least one audio tag representing a first sound created by the object of interest may be generated and associated with the object of interest. At a second time later than the first and at a second video camera, a second sound generated by an unidentified object that is not in the field of view of the second video camera may be detected. An audio tag representing the second tag may be generated. It may be determined that the object of interest and the unidentified object of interest are the same when the audio tag representing the first sound and the second sound are the same.

A method is described for extracting aperiodic components from a time-series wave data set for diagnosis purposes. The method may include collecting time-series wave data within a controlled environment were a plurality of contrasting conditions can be used in collecting the time-series wave data set. Aperiodic components can be extracted from the time-series wave data set and the aperiodic components can then be fitted to the plurality of contrasting conditions of the controlled environment to product regressed aperiodic components from which diagnostic determination can be made.

Provided is an image processing apparatus, including: an acquisition unit configured to acquire information on a layer boundary in tomographic structure of a current subject to be inspected; a determination unit configured to determine a depth range relating to a current en-face image of the subject to be inspected based on information indicating a depth range relating to a past en-face image of the subject to be inspected and the information on the layer boundary; and a generation unit configured to generate the current en-face image through use of data within the depth range relating to the current en-face image among pieces of three-dimensional data acquired for the current subject to be inspected.

Techniques for edge-enabled trajectory map generation are disclosed herein. For example, a method can include segmenting one or more node trajectories based on data collected at a node, determining one or more initial trajectories based on the segmented node trajectories, and generating a map including trajectories generated by associating attribute data and event data with the initial trajectories.

A system comprising a plurality of neuromuscular sensors, each of which is configured to record a time-series of neuromuscular signals from a surface of a user's body; and at least one computer hardware processor programmed to perform: applying a source separation technique to the time series of neuromuscular signals recorded by the plurality of neuromuscular sensors to obtain a plurality of neuromuscular source signals and corresponding mixing information; providing features, obtained from the plurality of neuromuscular source signals and/or the corresponding mixing information, as input to a trained statistical classifier and obtaining corresponding output; and identifying, based on the output of the trained statistical classifier, and for each of one or more of the plurality of neuromuscular source signals, an associated set of one or more biological structures.

A target speech signal extraction method for robust speech recognition includes: initializing a steering vector for a target speech source and an adaptive vector, setting a real output channel of the target speech source as an output by the adaptive vector, initializing adaptive vectors for a noise and setting a dummy channel as an output by the adaptive vectors for the noise; setting a cost function for minimizing dependency between a real output for the target speech source and a dummy output for the noise; setting an auxiliary function to the cost function, and updating the adaptive vector for the target speech source and the adaptive vectors for the noise by using the auxiliary function and the steering vector; estimating the target speech signal by using the adaptive vector thereby extracting the target speech signal from the input signals; and updating the steering vector for the target speech source.

The present invention provides a SoC including a person recognition circuit, a sound detection circuit and a processing circuit. The person recognition circuit is configured to obtain image data from an image capturing device, and perform a person recognition operation on the image data to generate a recognition result. The sound detection circuit is configured to receive a plurality of sound signals from a plurality of microphones, and determine a sound characteristic value of a main sound. The processing circuit is configured to determine a specific region in the image data according to the recognition result and the sound characteristic value of the main sound, and process the image data to highlight the specific region.

A system for marking cardiac time intervals from heart valve signals includes a non-invasive sensor unit for capturing electrical signals and composite vibration objects, a memory containing computer instructions, and one or more processors coupled to the memory. The one or more processors causes the one or more processors to perform operations including separating a plurality of individual heart vibration events into heart valve signals from the composite vibration objects, and marking cardiac time interval from the heart valve signals by detecting individual heartbeats using at least one or more of a PCA algorithm or deep learning.

A smart mat includes a stepping potential generation unit, a computing processor and a transmission processor for sensing the stepping direction of a stepper to control the operation of a device. The stepping potential generation unit includes an upper mat, an isolating airgap layer, a lower mat and at least one high-resistance strips. When the stepper stands on the smart mat to press the stepping potential generation unit, a part of the stepping potential generation unit is pressed by an open-circuit state to form a closed circuit and generate a potential. The computing processor uses the distributed position of each potential and the time sequence of distributing each potential to compute and analyse a potential stepping process distribution area to obtain a stepping direction, so as to control the operation of the device through the transmission processor.

An automated system and method is provided for biotype extraction and biomarker discovery from task-based fMRI imaging data. The system and method may include automatically mapping a localizome, such as a task-condition/contrast/population-specific brain functional localizome, based on fMRI data and automatically selecting and sorting brain regions or brain nodes to produce a subset of functional brain regions or brain nodes. A report may then be generated indicating that the subject has a particular brain circuit pattern of activity and connectivity associated with one or more symptoms of the given mental disorder, treatments, or associated with normal brain functions, based upon the extracted biosignatures by searching for the optimal multivariate classifier with least dimensionality in the brain functional localizome. These biosignatures and biomarkers that reveal hidden, implicit, and latent brain circuit patterns provoked by fMRI tasks, can also provide for the development of non-invasive diagnostics and targeted therapeutics in neuropsychiatric diseases.