文档介绍:Hindawi Publishing putational Intelligence and NeuroscienceVolume 2007, Article ID94397,9pagesdoi: ArticleASemisupervised Support Vector Machines Algorithmfor BCI SystemsJianzhao Qin,1, 2Yuanqing Li,1and Wei Sun31Institute of Automation Science and Engineering, South China University of Technology, Guangzhou 510640, China2Shenzhen Institute of Advanced Integration Technology, Chinese Academy of Sciences,The Chinese University of Hong Kong, Hong Kong3School of Maths, Central-South University, Changsha 410008, ChinaCorrespondence should be addressed to Jianzhao Qin, jz.******@ 30 January 2007; Accepted 18 June mended by Andrzej CichockiAs an emerging technology, puter interfaces (BCIs) bring us munication interfaces which translate brain activ-ities into control signals for devices puters, robots, and so forth. In this study, we propose a semisupervised support vectormachine (SVM) algorithm for puter interface (BCI) systems, aiming at reducing the time-consuming training this algorithm, we apply a semisupervised SVMfor translating the features extracted fromthe electrical recordings of brain intocontrol signals. This SVM classi?er is built froma small labeled data set and a large unlabeled data set. Meanwhile, to reduce thetime for training semisupervised SVM, we propose a batch-mode incremental learning method, which can also be eas