Abstract: The present disclosure relates to the field of bioengineering technology, and particularly to an electrical signal communication platform for mimicking cardiomyocyte clusters. The transmitting end employs an Arduino Mega 2560™ main control board and an L298N motor drive module, the main control board sends a pulse signal to the motor drive module, and outputs a pulse waveform to a communication channel through the motor drive module; the communication channel employs a plurality of cell clusters, configured for receiving the pulse waveform output by the motor drive module and transmitting it to the receiving end; and the receiving end employs an oscilloscope to receive the pulse waveform passing through the communication channel, to demodulate the pulse waveform and send a demodulation result to a display device. The present disclosure provides multi-angle data acquisition to enhance the comprehensiveness of analysis, and facilitates a more accurate simulation of cardiomyocyte pacing and communication.

Abstract: The invention discloses an emotion recognition method based on spatio-temporal multi-scale attention convolutional neural network, which comprises: collecting EEG data of subjects for preprocessing to obtain EEG data containing spatial dimension and temporal dimension; constructing a lightweight convolutional neural network including two-stream spatio-temporal feature construction layer, hybrid attention mechanism layer, high-order fusion layer and classification layer; wherein the two-stream spatio-temporal feature construction layer comprises a temporal feature extraction module and a parallel spatial feature extraction module; the high-order fusion layer is used to re-learn from the learned global convolution kernel to the representation of the local hemisphere convolution kernel; the trained lightweight convolutional neural network is used to identify EEG data, and the emotion recognition results of the subjects are obtained.