[논문]뇌파신호를 이용한 감정분류 연구

무하마드 주바이르; 김진술; 윤장우

doi:10.9728/dcs.2018.19.4.821

뇌파신호를 이용한 감정분류 연구
Research on Classification of Human Emotions Using EEG Signal 원문보기

디지털콘텐츠학회 논문지 = Journal of Digital Contents Society, v.19 no.4, 2018년, pp.821 - 827

무하마드 주바이르 (과학기술연합대학원대학교 정보통신네트워크과) , 김진술 (전남대학교 전자컴퓨터공학과) , 윤장우 (한국전자통신연구원 초연결통신연구소)

초록
AI-Helper

Affective Computing은 HCI (Human Computer Interaction) 및 건강 관리 분야에서 다양한 애플리케이션이 개발됨에 따라 최근 몇 년 동안 관심이 높아지고 있다. 이에 필수적으로 필요한 인간의 감정 인식에 대한 중요한 연구가 있었지만, 언어 및 표정과 비교하여 심전도 (ECG) 또는 뇌파계 (EEG) 신호와 같은 생리적 신호 분석에 따른 감정 분석에 대한 관심은 적었다. 본 논문에서는 이산 웨이블릿 변환을 이용한 EEG 기반 감정 인식 시스템을 제안하고 감정 관련 정보를 얻기 위해 다른 뇌파와 뇌 영역을 연구 하였으며, 웨이블릿 계수에 기초한 특징 세트가 웨이블릿 에너지 특징과 함께 추출되었다. 중복성을 최소화하고 피처 간의 관련성을 극대화하기 위해 mRMR 알고리즘이 피쳐 선택에 적용된다. 다중클래스 Support Vector Machine을 사용하여 4 가지 종류의 인간 감정을 크게 분류하였으며 공개적으로 이용 가능한 "DEAP"데이터베이스의 뇌파 기록이 실험에서 사용되었다. 제안 된 접근법은 기존의 알고리즘에 비해 향상된 성능을 보여준다.

Abstract ▼ AI-Helper

Affective computing has gained increasing interest in the recent years with the development of potential applications in Human computer interaction (HCI) and healthcare. Although momentous research has been done on human emotion recognition, however, in comparison to speech and facial expression less attention has been paid to physiological signals. In this paper, Electroencephalogram (EEG) signals from different brain regions were investigated using modified wavelet energy features. For minimization of redundancy and maximization of relevancy among features, mRMR algorithm was deployed significantly. EEG recordings of a publically available "DEAP" database have been used to classify four classes of emotions with Multi class Support Vector Machine. The proposed approach shows significant performance compared to existing algorithms.

주제어

AI 본문요약
AI-Helper

* AI 자동 식별 결과로 적합하지 않은 문장이 있을 수 있으니, 이용에 유의하시기 바랍니다.

문제 정의

In this paper, we illustrated the development of an efficient emotions recognition system using electroencephalogram signals. DEAP database which includes 32 subjects’ data, was employed.

제안 방법

For the elimination of eye blink artifacts blind source separation technique was adopted. In the last of experiment every subject performed self-assessment using Self-Assessment Manikins to evaluate and rate each music video in term of levels of arousal, valence, like/dislike, dominance and familiarity according to the level they experienced. The preprocessed EEG data released by Koelstra et al.
In this paper, we used a five levels “Daubechies” wavelet of order 4 in order to extract five different frequency bands (delta, theta, alpha, beta and gamma) from an EEG signal of 128 Hz.
In terms of classification, Gamma band classified all classes of emotions efficiently compare to other bands. In this study, we also found a strong correlation between emotions and the gamma signals acquired from frontal lobe of the brain which validates the role of frontal lobe in emotion recognition system. Future work includes the fusion of EEG and ECG signals for higher classification performance.
The selected features were feed into “Support Vector Machine” for the classification of four levels of emotion.

대상 데이터

DEAP database which includes 32 subjects’ data, was employed.
The set of selected features from EEG recording of 32 participants was used to classify four classes of emotions. The stimulus rating (valence and arousal score) gathered during self-assessment was divided into two categories of low and high.

성능/효과

“Quadratic Discriminant Analysis” and “Support Vector Machine” was employed with Grid search technique for parameters optimization in order to classify emotion data. In this experiment, SVM performed better comparative to QDA with an overall classification accuracy of 49.7%.

후속연구

In this study, we also found a strong correlation between emotions and the gamma signals acquired from frontal lobe of the brain which validates the role of frontal lobe in emotion recognition system. Future work includes the fusion of EEG and ECG signals for higher classification performance.

참고문헌 (20)

Bilal, Muhammad, and Shin-Gak Kang. "An Authentication Protocol for Future Sensor Networks." Sensors 17.5 (2017): 979.

상세보기
Paul Ekman, Emotions Revealed. TIMES BOOKS, 2003.
L. Zhang, D. Tjondronegoro, "Facial expression recognition using facial movement features," IEEE Transactions on Affective Computing, vol. 2, pp. 219-229, 2011.

상세보기
K. Wang, A. Ning, B.N. Li and Y. Zhang, "Speech emotion recognition using Fourier parameters," IEEE Transactions on Affective Computing, vol. 6, pp. 69-75, 2015.

상세보기
J. Anttonen and V. Surakka, "Emotions and Heart Rate While Sitting on a Chair," Proc. SIGCHI Conf. Human Factors in Computing Systems, pp. 491-499. 2005.
C.M. Jones and T. Troen, "Biometric Valence and Arousal Recognition," Proc. 19th Australasian Conf. Computer-Human Interaction, pp. 191-194, 2007.
Posner et al. The circumplex model of affect: An integrative approach to affective neuroscience, cognitive development, and psychopathology.Dev. Psychopathol. 17, (2005).

상세보기
P. J. Lang, M. M. Bradley, and B. N. Cuthbert, "International affective picture system (IAPS): Affective ratings of pictures and instruction manual," Tech. Rep. A-8, 2008.
M. M. Bradley and P. J. Lang, "The international affective digitized sounds (; iads-2): Affective ratings of sounds and instruction manual," Univ. of Florida, Gainesville, FL, USA, Tech. Rep. B-3, 2007.
Sourina, Olga, and Yisi Liu. "A Fractal-based Algorithm of Emotion Recognition from EEG using Arousal-Valence Model." BIOSIGNALS. 2011.
Petrantonakis et al. "Emotion recognition from EEG using higher order crossings." IEEE Transactions on Information Technology in Biomedicine 14.2 (2010): 186-197.

상세보기
Lan, Tian, et al. "Estimating cognitive state using EEG signals." Signal Processing Conference, 2005 13th European. IEEE, 2005.
Murugappan et al."Classification of human emotion from EEG using discrete wavelet transform." Journal of Biomedical Science and Engineering 3.04 (2010): 390.

상세보기
S.Koelstraet al., "Single trial classificationof EEG and peripheral physiological signals for recognitionof emotions induced by music videos," in Proceeding of the International Conference on Brain Informatics (BI '10), pp. 89-100, Toronto, Canada, 2010.
U. Wijeratneet al, "Intelligent emotion recognition system using electroencephalography and active shapemodels," in Proceedings of the IEEE EMBS Conference on Biomedical Engineering and Sciences (IECBES '12), pp. 636-641, 2012.
Z. Khalili and M. H. Moradi, "Emotion recognition system using brain and peripheral signals: using correlation dimension to improve the results of EEG," in Proceedings of the International Joint Conference on Neural Networks (IJCNN '09), pp.1571-1575, Atlanta, Ga, USA, June 2009.
M. Soleymani et al. A multimodal database for affect recognition and implicit tagging. IEEE Transactions on Affective Computing, 2012, 3. Jg., Nr. 1, S. 42-55.

상세보기
Subramanian R, Wache J, Abadi M, Vieriu R, Winkler S, Sebe N. ASCERTAIN: Emotion and personality recognition using commercial sensors. IEEE Transactions on Affective Computing. 2016 Nov 4.
Koelstra, Sander, et al. "Deap: A database for emotion analysis; using physiological signals." IEEE Transactions on Affective Computing 3.1 (2012): 18-31.

상세보기
Daimi, Syed Naser, and GoutamSaha. "Classification of emotions induced by music videos and correlation with participants' rating." Expert Systems with Applications 41.13 (2014): 6057-6065.

상세보기

저자의 다른 논문 :

LOADING...

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증