Title：Stream processor for extracting features of stream data in transmission process and implementation method thereof

Country：China

Patent No.：202110433608.3

Legal Status：Authorized

Inventor：Xiangyu Li

Assignee：Tsinghua University

Address：Tsinghua University,Haidian District Beijing 100084, China

Filing Date：2021-04-20

Issue Date：2022-10-04

The invention discloses a single-channel electroencephalogram signal processing device and a method. The processing device comprises a support vector machine classifier, a first number of finite impulse response filters and a first number of frequency band energy feature extraction modules. The finite impulse response filters are used for receiving one of sub-band signals in electroencephalogram signals and filtering the sub-band signal to obtain a filtered signal. The frequency band energy feature extraction modules are used for receiving the filtered signal from the corresponding finite impulse response filters and extracting features of the filtered signal. The support vector machine classifier is used for classifying the features from frequency band energy feature extraction modules to obtain a classification results. According to the processing device, the electroencephalogram signals of a single channel are processed to obtain classification results. The processing device of the present invention is simple in structure, small in area and size, less in energy consumption, convenient for further integration with other modules and beneficial to reducing size of a chip.

Patent Certificate： PDF/Jpg