Data enhancement method and system for electroencephalogram signal classification and recognition

• Main Authors: SHU JUN, LI HUIMIN, YAN BIN, YANG KAI, LU RUNNAN, TONG LI, ZENG YING, ZHANG RONGKAI
• Format: Patent
• Language: Chinese; English
• Published: 26.03.2021
• Subjects: DIAGNOSIS; HUMAN NECESSITIES; HYGIENE; IDENTIFICATION; MEDICAL OR VETERINARY SCIENCE; SURGERY

The invention belongs to the technical field of electroencephalogram signal processing, and particularly relates to a data enhancement method and system for electroencephalogram signal classificationand recognition. The method includes the steps that electroencephalogram signals in a training task state and electroencephalogram signals in a resting state are collected, and artificial electroencephalogram signal data is generated through adversarial generative network fitting training; and the artificial electroencephalogram signal data is subjected to amplitude scaling, real electroencephalogram signals are mixed to obtain sample data containing diversity, and the sample data is used for training and learning a classifier, so that the purpose of classifying and identifying the electroencephalogram signals of a testee by using a classifier after training and learning is achieved. According to the data enhancement method and system for electroencephalogram signal classification and recognition, the problems of