A semi-supervised adaptive classification method for EEG signals

By employing a semi-supervised adaptive learning strategy, combined with data augmentation, feature alignment, and consistency regularization loss function, the model transfer difficulty in cross-individual EEG signal classification is solved, achieving efficient cross-individual EEG signal classification.

CN116738330BActive Publication Date: 2025-12-02UNIV OF SCI & TECH OF CHINA
2 Cites 0 Cited by

Patent Information

Application Number
CN202310052274.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-02-02
Publication Date
2025-12-02
Estimated Expiration
2043-02-02

AI Technical Summary

Technical Problem

Existing EEG signal classification methods face difficulties in model transfer in cross-individual applications, especially due to inter-individual feature differences and high data costs, making it difficult to effectively utilize unlabeled data for calibration.

Method used

A semi-supervised adaptive learning strategy is adopted. By combining labeled and unlabeled data, data augmentation is performed using random erasure and Gaussian noise enhancement methods. The model is then optimized by combining feature alignment and consistency regularization loss function to achieve cross-individual EEG signal classification.

Benefits of technology

It significantly improved the accuracy of cross-individual EEG signal classification, reduced annotation costs, and enhanced the model's ability to identify target individuals.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

This invention discloses a semi-supervised adaptive EEG signal classification method, comprising: 1. acquiring labeled data from different individuals, acquiring data from the target individual and selecting a portion for labeling, followed by unified preprocessing; 2. designing a data augmentation mechanism to enhance the representation of the samples; 3. building student and teacher models; 4. recording the weights of the student model after each update, and performing a moving average with the historical weights to serve as the weights of the teacher model; 5. calculating the feature alignment loss between existing individuals and the target individual in the feature space; 6. calculating the consistency loss between the output probabilities of the student model and the teacher model; 7. combining the above loss function with cross-entropy loss to jointly optimize the model parameters and obtain the optimal classification model. This invention can fully calibrate the classification model even when only a small portion of the target individual's data is labeled, thereby achieving high-accuracy cross-individual EEG signal classification.
Need to check novelty before this filing date? Find Prior Art