컨볼루션 신경망을 이용한 동작 상상 뇌파 분류

다국어 초록 (Multilingual Abstract)

Brain-computer interface (BCI) is a technology that can be used as augmentative and alternative communication (AAC) for people such as the elderly or the disabled who are restricted or impaired in physical function. In order for BCI to be used as AAC, it is important to select appropriate feature extraction and classification methods because the electroencephalogram (EEG) signal is non-linear and non-stationary. This study proposes a feature extraction and classification method of motor imagery EEG using convolutional neural network (CNN). The CNN, most commonly used in the field of images, uses a large number of training data to avoid the problem of overfitting. If the amount of training data is small, the CNN cause overfitting problems. Therefore, in this study, the CNN suitable with small amount of training data was designed for motor imagery based BCI, and then the motion imaginary EEG was learned and classified. The performance of the proposed method is shown to be about 3.8~4.5% in terms of average accuracy through comparison with existing machine learning methods.

참고문헌 (Reference)

1 B. Binias, "Windowed local area average reference filter for increasing the spatial resolution of EEG signals" 403-408, 2016

2 Q. Zhao, "Temporal and spatial features of single-trial EEG for Brain-Computer Interface" 2007

3 Y. Yang, "Subject-Specific Channel Selection using Time Information for Motor Imagery Brain-Computer Interfaces" 8 (8): 505-518, 2016

4 M. Tangermann, "Review of the BCI competition IV" 6 (6): 2012

5 G. Rosas-Cholula, "On signal P-300 detection for BCI applications based on wavelet analysis and ICA preprocessing. Proceedings of the IEEE Electronics" 360-365, 2010

6 M. Chevalier, "LR-CNN for finegrained classification with varying resolution" 2015

7 R. Olga, "Imagenet large scale visual recognition challenge" 115 (115): 211-252, 2015

8 Y. LeCun, "Gradient-based learning applied to document recognition" 86 (86): 2278-2324, 1998

9 이다빛, "GMM과 SVM을 이용한 움직임 상상 뇌파 분류에 관한 연구" 한국정보기술학회 11 (11): 67-75, 2013

10 Y. Li, "Fpnn: Field probing neural networks for 3d data" 2016

11 N. Brodu, "Exploring two novel features for EEG-based brain–computer interfaces : multifractal cumulants and predictive complexity" 79 (79): 87-94, 2012

12 이다빛, "EMD와 FFT를 이용한 동작 상상 EEG 분류 기법" 한국정보과학회 41 (41): 1050-1057, 2014

13 W. k. Lu, "Deconvolutive shorttime Fourier transform spectrogram" 16 (16): 576-579, 2009

14 R. Manor, "Convolutional neural network for multi-category rapid serial visual presentation BCI" 9 (9): 2015

15 J. J. Shih, "Brain-computer interfaces in medicine" 87 (87): 268-279, 2012

16 G. Blanchard, "BCI competition 2003-data set IIa : spatial patterns of selfcontrolled brain rhythm modulations" 51 (51): 1062-1066, 2004

17 Y. Liu, "A boosting-based spatials-pectral model for stroke patients’ eeg analysis in rehabilitation training" 24 (24): 169-179, 2016

18 M. Ahn, "A Review of Brain-Computer Interface Games and an Opinion Survey from Researchers, Developers and Users" 14 (14): 14601-14633, 2014

19 J. Katona, "A Brain–Computer Interface Project Applied in Computer Engineering" 59 (59): 319-326, 2016