Abstract
Establishing an accurate and rapid electroencephalography (EEG) recognition algorithm is an important research direction in the field of Brain-Computer Interface (BCI). In this paper, EEG recognition algorithm is constructed based on discrete wavelet transform (DWT), common spatial patterns (CSP) and extreme learning machine (ELM). DWT and CSP are used for joint feature extraction, which solves the problem that traditional CSP is sensitive to noise. ELM is used for classification, which improves the real-time performance of the BCI system. Our findings show a classification accuracy of 90% and a classification time of 0.012s for the Data Set III in BCI Competition 2003, which proves the effectiveness of the algorithm.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have