Unbalance classification method for electroencephalogram data in epilepsy detection

By generating synthetic samples using covariance-guided transformation and Mahalanobis distance constraints, the imbalanced classification problem of EEG data in epilepsy detection is solved, improving the classification accuracy and robustness of the model, overcoming the limitations of existing technologies, and achieving better epilepsy seizure detection results.

CN121845606APending Publication Date: 2026-04-14NINGBO INST OF TECH ZHEJIANG UNIV ZHEJIANG
0 Cites 0 Cited by

Patent Information

Application Number
CN202610096628.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-01-23
Publication Date
2026-04-14

AI Technical Summary

Technical Problem

Existing imbalanced classification methods for EEG data in epilepsy detection suffer from dataset imbalance, making it difficult for traditional classification methods to effectively identify rare epileptic seizure patterns, affecting the sensitivity and robustness of the model. Furthermore, existing oversampling techniques have limitations, such as local information dependence, insufficient diversity of generated samples, and intra-class imbalance.

Method used

By employing covariance-guided transformation and Mahalanobis distance constraints, synthetic samples are generated through matrix factorization, constructing a generation mechanism oriented towards minority class samples, optimizing the diversity and boundary consistency of synthetic samples, and using Mahalanobis distance ranking for sample pairing. The generated synthetic samples can better reflect the global distribution of the data and the class decision boundary.

Benefits of technology

While preserving the global distribution characteristics of the data, the generated synthetic samples can improve the classification accuracy and robustness of epileptic seizure detection, outperforming the overall performance of existing technologies and enhancing the sensitivity of the classifier and the clarity of the decision boundary.

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

Abstract

The invention discloses an unbalanced classification method for electroencephalogram data in epilepsy detection, and relates to the technical field of data optimization and big data processing. According to the method, firstly, covariance matrixes of majority class samples and minority class samples are calculated, linear transformation is achieved through matrix decomposition, and the minority class samples inherit global distribution characteristics of the majority class samples; and then, in the transformed feature space, sorting samples based on mahalanobis distance and performing partition pairing, selecting sample pairs with large difference to generate convex combination synthesis samples, and ensuring sample diversity and boundary consistency. Experimental results show that on a CHB-MIT electroencephalogram data set, the method effectively solves the problems that a traditional oversampling technology is prone to expanding minority class decision boundaries and generated samples are lack of diversity, and the reliability of epileptic seizure detection is remarkably improved.
Need to check novelty before this filing date? Find Prior Art