Improvement of EEG-based motor imagery classification using ring topology-based particle swarm optimization

详细信息    查看全文

• 作者：Hamid Mirvaziri ; ^{h.vaziri@gmail.com} ; ^{hmirvaziri@uk.ac.ir} ; Zabihollah Saberi Mobarakeh
• 关键词：EEG ; electroencephalogram ; BCI ; brain-computer interface ; RTPSO ; ring topology based particle swarm optimization ; CV ; cross validation ; FFNN ; feed forward neural network ; SVM ; support vector machine ; MI ; mutual information
• 刊名：Biomedical Signal Processing and Control
• 出版年：2017
• 出版时间：February 2017
• 年：2017
• 卷：32
• 期：Complete
• 页码：69-75
• 全文大小：1279 K
• 卷排序：32

文摘

Accuracy of neural network is better than SVM classifier in motor imagery based brain computer interface. Performance of DWT feature extraction from EEG motor imagery signals is different in various paradigms. Tuning of classifier parameters by R3PSO could increase the accuracy of classifier. Proposed R3PSO together with 10-Fold CV leads to promising results for classifier tuning in motor imagery classification.