Classification of the motor imagery EEG signal using vector quantization and K-nearest neighbors' algorithm
- Authors
- Jang, Tae-Ung; Lim, Wansu; Yang, Yeon-Mo; Kim, Byoeng Man
- Issue Date
- Dec-2015
- Publisher
- INST ADVANCED SCIENCE EXTENSION
- Keywords
- Classification; EEG signal; K-nearest neighbors' algorithm
- Citation
- INTERNATIONAL JOURNAL OF ADVANCED AND APPLIED SCIENCES, v.2, no.12, pp.72 - 77
- Journal Title
- INTERNATIONAL JOURNAL OF ADVANCED AND APPLIED SCIENCES
- Volume
- 2
- Number
- 12
- Start Page
- 72
- End Page
- 77
- URI
- https://scholarworks.bwise.kr/kumoh/handle/2020.sw.kumoh/1286
- ISSN
- 2313-626X
- Abstract
- Brain computer interface (BCI) is the mutual communication between the human brain and computers, and it is one of the most popular technologies in the human computer interface (HCI) research. In our propose algorithm, we first analyze time-frequency spectrum of EEG signals using short-time Fourier transform (STFT), and then we apply the LBG algorithm to extract the features of EEG signals via the vector quantization. Next, we calculate the degree of the similarity on the time series pattern of EEG signals. Finally, the motor imagery EEG signal is determined by using the method of the k-nearest neighbors (KNN). In our simulation, BCI competition II data is utilized, and as a result, the maximum performance of 88.57% is obtained. (C) 2015 IASE Publisher. All rights reserved.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - Department of Computer Software Engineering > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.