Identification of Epileptic EEG Signals Through TSK Transfer Learning Fuzzy System

Zhaoliang Zheng; Xuan Dong; Jian Yao; Leyuan Zhou; Yang Ding; Aiguo Chen

doi:10.3389/fnins.2021.738268

Identification of Epileptic EEG Signals Through TSK Transfer Learning Fuzzy System

Front Neurosci. 2021 Sep 10:15:738268. doi: 10.3389/fnins.2021.738268. eCollection 2021.

Authors

Zhaoliang Zheng¹, Xuan Dong², Jian Yao¹, Leyuan Zhou³, Yang Ding³, Aiguo Chen¹

Affiliations

¹ School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China.
² Department of Tuberculosis and Respiratory Diseases, Wuhan Jinyintan Hospital, Wuhan, China.
³ Department of Radiotherapy, Affiliated Hospital, Jiangnan University, Wuxi, China.

Abstract

We propose a new model to identify epilepsy EEG signals. Some existing intelligent recognition technologies require that the training set and test set have the same distribution when recognizing EEG signals, some only consider reducing the marginal distribution distance of the data while ignoring the intra-class information of data, and some lack of interpretability. To address these deficiencies, we construct a TSK transfer learning fuzzy system (TSK-TL) based on the easy-to-interpret TSK fuzzy system the transfer learning method. The proposed model is interpretable. By using the information contained in the source domain and target domains more effectively, the requirements for data distribution are further relaxed. It realizes the identification of epilepsy EEG signals in data drift scene. The experimental results show that compared with the existing algorithms, TSK-TL has better performance in EEG recognition of epilepsy.

Keywords: TSK fuzzy system; epilepsy EEG signals; interpretability; knowledge learning; transfer learning.