Application of Independent Component Analysis Approach for Multi-variant Neurobiological Signals
Electroencephalograms (EEG) can provide a unique window on the human brain. Contamination of EEG recording with artifacts, caused by muscular activity, eye movements,cardiac rhythm and power noise etc., can decrease the efficiency of diagnosis procedure. A kind of fast independent component analysis (ICA) approach present here is applied to analyze the real multi-variant EEG recorded signals. The removal of cardiac rhythm, comparison of before and after artifact removal, and comparison between ICA and a second order statistic (SOS) algorithm are analyzed respectively.The experiments based on the real measurement data demonstrate ICA is a powerful tool in neurophysiological interpretation.
Independent Component Analysis EEG Multi-variant Second Order Statistic Artifact Removal
Jing Hu Jie Hu
College of Information Engineering, Zhejiang University of Technology Hangzhou, 310032, China Dept.of Equipment, First Affiliated Hospital, Zhejiang University Hangzhou, 310003, China
国际会议
杭州
英文
1162-1164
2006-10-12（万方平台首次上网日期，不代表论文的发表时间）