Multi-Scale Wavelet Kernel Extreme Learning Machine for EEG Feature Classification Qi Liu 1 , Xiao-guang Zhao 1 , Zeng-guang Hou 1 and Hong-guang Liu 2 1 The State Key Laboratory of Management and Control for Complex Systems Institute of Automation, CAS Beijing, PRC 2 Institute of crime, Chinese People's Public Security University Beijing, PRC Abstract—In this paper, the principle of the kernel extreme learning machine (ELM) is analyzed. Based on that, we introduce a kind of multi-scale wavelet kernel extreme learning machine classifier and apply it to electroencephalographic (EEG) signal feature classification. Experiments show that our classifier achieves excellent performance. Keywords—EEG classification; ELM; multi-scale wavelet kernel I. INTRODUCTION Electroencephalographic (EEG) is a kind of typical and important biological signal. It reflects the electrical activity and the functional status of the brain. Also, it has been proved that
