Abstract: A feature enhancement and data augmentation method for detecting at least one action of at least one tested subject is provided. The feature enhancement and data augmentation method includes obtaining at least one spectrogram; and performing a feature enhancement processing on the at least one spectrogram, to enhance at least one feature corresponding to at least one action in the at least one spectrogram and generate at least one feature enhanced spectrogram. The feature enhancement processing comprises a directional filtering.

Abstract: A wearable device with heart rate detection includes a heart rate detection assembly and a processor. The heart rate detection assembly is configured to obtain a plurality of dynamic heart rate signals according to a default frequency. The processor includes a finite state machine and a storage. The storage is configured to store the plurality of dynamic heart rate signals, and the finite state machine determines a heart rate state according to a sampling parameter and the plurality of dynamic heart rate signals. The processor obtains a weight according to the heart rate state, and obtains a dynamic heart rate value according to the weight.

Abstract: A physiological signal feature extraction method includes receiving a physiological signal, determining in a situation that a second pulse in a plurality of pulses of the physiological signal being correlated to a first pulse in the plurality of pulses, selecting the second pulse as one of a plurality of reference pulses in a reference waveform sequence after the second pulse is determined as correlated to the first pulse, averaging the plurality of reference pulses into a template pulse, performing match comparison on the plurality of pulses by the template pulse one by one, and extracting a plurality of features from each of the plurality of pulses that matches the template pulse.

Abstract: A sound recognition model training method comprises determining a relationship between a sound event and first parameter and deciding a second parameter in response to the relationship, performing sampling on the sound event using the first parameter and the second parameter to generate training audio files, and inputting at least part of the training audio files to a sound recognition model for training the sound recognition model, wherein a length of each of the training audio files is associated with the first parameter, a time difference between every two of the training audio files is associated with the second parameter, and the sound recognition model is used for determining a sound classification.

Abstract: Abstract of Disclosure A feature enhancement and data augmentation method for detecting at least one action of at least one tested subject is provided. The feature enhancement and data augmentation method includes obtaining at least one spectrogram; and performing a feature enhancement processing on the at least one spectrogram, to enhance at least one feature corresponding to at least one action in the at least one spectrogram and generate at least one feature enhanced spectrogram. The feature enhancement processing comprises a directional filtering.

Abstract: The present invention provides a signal quality detection method for an ear-chip physiological measurement device. The signal quality detection method includes receiving a sensing signal from the ear-clip physiological measurement device; filtering the sensing signal to generate a pre-processed signal; calculating a physiological index according to the pre-processed signal; and calculating a similarity of a red light alternating current (AC) component and an infrared light AC component of the pre-processed signal and a plurality of correlation coefficients of the red light AC component, and generating a reliability index of the physiological index accordingly. The reliability index indicates one of a plurality of signal qualities.

Abstract: A sound recognition model training method comprises determining a relationship between a sound event and first parameter and deciding a second parameter in response to the relationship, performing sampling on the sound event using the first parameter and the second parameter to generate training audio files, and inputting at least part of the training audio files to a sound recognition model for training the sound recognition model, wherein a length of each of the training audio files is associated with the first parameter, a time difference between every two of the training audio files is associated with the second parameter, and the sound recognition model is used for determining a sound classification.