지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
논문 기본 정보
- 자료유형
- 학술대회자료
- 저자정보
- 저널정보
- 한국정보통신학회 INTERNATIONAL CONFERENCE ON FUTURE INFORMATION & COMMUNICATION ENGINEERING 2014 INTERNATIONAL CONFERENCE ON FUTURE INFORMATION & COMMUNICATION ENGINEERING Vo.6 No.1
- 발행연도
- 2014.6
- 수록면
- 130 - 133 (4page)
이용수
초록· 키워드
오류제보하기
As EEG signals are non-stationary, the conventional method of frequency analysis is not highly successful in recognition of alertness level. In this paper, EEG signals were decomposed into the frequency sub-bands using wavelet transform in order to find entropy of a EEG signal segment by wavelet coefficients and a set of statistical features such as skewness, kurtosis, RMS value and power was extracted from the EEG itself. Then these statistical features were used as an input to above mentioned classifiers with four discrete outputs: stage 1, stage 3, stage REM and stage AWAKE. EEG signals were obtained from 20 healthy subjects. The features extracted from EEGs such as entropy, kurtosis, skewness, RMS and power values of each 5 second 75% overlapped EEG segments were used as an input vector for classifiers. The accuracy of the linear Support Vector Machine was 93% stage 1, 82% stage 3, 73% stag R and 96% stage W.
목차
Abstract
I. INTRODUCTION
II. MATERIALS AND METHOD
III. FEATURE SELECTION[FISHER DISCRIMINANT RATIO]
IV. RESULTS
V. DISCUSSION AND CONCLUSIONS
REFERENCES
참고문헌 (0)
참고문헌 신청이 논문의 저자 정보
최근 본 자료
댓글(0)
0
UCI(KEPA) : I410-ECN-0101-2018-004-000962293