Open Access

ARTICLE

Multi-View & Transfer Learning for Epilepsy Recognition Based on EEG Signals

by Jiali Wang¹, Bing Li², Chengyu Qiu¹, Xinyun Zhang¹, Yuting Cheng¹, Peihua Wang¹, Ta Zhou³, Hong Ge², Yuanpeng Zhang^1,3,*, Jing Cai^3,*

1 Department of Medical Informatics, Nantong University, Nantong, 226001, China
2 The Affiliated Cancer Hospital of Zhengzhou University & Henan Cancer Hospital, Zhengzhou, 450008, China
3 Department of Health Technology and Informatics, Shenzhen Research Institute, The Hong Kong Polytechnic University, Shenzhen, 518057, China

* Corresponding Authors: Yuanpeng Zhang. Email: ; Jing Cai. Email:

Computers, Materials & Continua 2023, 75(3), 4843-4866. https://doi.org/10.32604/cmc.2023.037457

Received 04 November 2022; Accepted 17 February 2023; Issue published 29 April 2023

Abstract

Epilepsy is a central nervous system disorder in which brain activity becomes abnormal. Electroencephalogram (EEG) signals, as recordings of brain activity, have been widely used for epilepsy recognition. To study epileptic EEG signals and develop artificial intelligence (AI)-assist recognition, a multi-view transfer learning (MVTL-LSR) algorithm based on least squares regression is proposed in this study. Compared with most existing multi-view transfer learning algorithms, MVTL-LSR has two merits: (1) Since traditional transfer learning algorithms leverage knowledge from different sources, which poses a significant risk to data privacy. Therefore, we develop a knowledge transfer mechanism that can protect the security of source domain data while guaranteeing performance. (2) When utilizing multi-view data, we embed view weighting and manifold regularization into the transfer framework to measure the views’ strengths and weaknesses and improve generalization ability. In the experimental studies, 12 different simulated multi-view & transfer scenarios are constructed from epileptic EEG signals licensed and provided by the University of Bonn, Germany. Extensive experimental results show that MVTL-LSR outperforms baselines. The source code will be available on .

---

Keywords

---