Recognition of Seizure and Nonseizure EEG Signals Using a Transfer Support Vector Machine
Automatic recognition of seizure and nonseizure EEG Signals is an important means for epilepsy detection. In this study, a transfer-learning-based support vector machine (TrSVM) method is proposed for epileptic electroencephalogram recognition. The proposed transfer SVM model aims to
significantly improve the recognition performance using the transductive transfer learning mechanism. In this study, we mainly integrate a large-margin-projected mechanism into a classical SVM model, which can be utilized to resist the loss of performances caused by the differences between
data distributions. The experimental results indicate that the TrSVM method obtains promising results compared with those of related non-transfer and transfer methods for epileptic EEG recognition.
Keywords: EPILEPTIC EEG RECOGNITION; LARGE-MARGIN-PROJECTED MECHANISM; SUPPORT VECTOR MACHINE; TRANSDUCTIVE TRANSFER LEARNING; TRANSFER LEARNING
Document Type: Research Article
Publication date: 01 September 2019
- Journal of Medical Imaging and Health Informatics (JMIHI) is a medium to disseminate novel experimental and theoretical research results in the field of biomedicine, biology, clinical, rehabilitation engineering, medical image processing, bio-computing, D2H2, and other health related areas.
- Editorial Board
- Information for Authors
- Subscribe to this Title
- Ingenta Connect is not responsible for the content or availability of external websites
- Access Key
- Free content
- Partial Free content
- New content
- Open access content
- Partial Open access content
- Subscribed content
- Partial Subscribed content
- Free trial content