기계학습을 이용한 EEG 신호 기반 감정상태 평가 및 분류 검증
Machine Learning based Human emotion state classification using EEG signals
0
조회
0
다운로드
5
인용
0
참고문헌
키워드
초록
감정인식은 인간과 컴퓨터 상호작용 분야에서 다양한 생체신호를 활용하여 지속적으로 연구되고 있다. 특히, 뇌파(Electroencephalogram, EEG)는 음성과 표정보다 객관적이고, 접근이 용이하기 때문에, 감정연구에서 활발하게 활용되고 있다. 본 논문에서는 총 12명의 한국인을 대상으로 6개의 감정범주인 화남(Anger), 흥분(Excitement), 두려움(Fear), 행복(Happiness), 슬픔(Sadness), 그리고 중립(Neutral)로 구성된 4분간의 감정영상을 시청하는 상황에서 뇌파 데이터를 수집하였다. 수집된 데이터는 전처리 과정을 거친 후, 파워스펙트럼(power spectrum)값을 추출하였다. 이를 활용하여 Support Vector Machine(SVM)과 Long Short Term Memory(LSTM) 모델을 통하여 감정분류를 진행하였다. 실험방법은 개인의 차이를 고려하여 실험참가자 독립적(Subject-independent)방식으로 진행되었다. 그 결과, LSTM이 SVM 보다 6개의 감정에 대하여 12.91% 향상된 80.46%의 분류정확도를 얻었다. 또한, LSTM의 레이어(Layer)수를 변경하여 분류를 진행한 결과로, 레이어(Layer)수가 2개일 때, 82.17%로 1.71% 향상되었다. 결론적으로, 본 논문에서는 6개의 감정범주에 대한 감정분류로 82.17%의 높은 정확도를 얻었으며, LSTM은 뇌파와 같은 시간 의존형 데이터에 적합한 알고리즘임을 확인한 데에 의의가 있다.
Abstract
EEG-based emotion recognition is a challenging task in human-computer interaction(HCI). Electroencephalogram(EEG) has significant advantages in emotion recognition since it directly reflects brain activity. This study recorded EEG signals from 12 participants watching Korean movie clips for 4 minutes, defined as six emotions: anger, excitement, fear, happiness, sadness, and neutral state. We also extract spectral power values as the feature using Fast Fourier Transform(FFT). Next, we have performed three classification models, Support Vector Machine(SVM), Long Short Term Memory(LSTM) with subject-dependent experiments. As a result, the best accuracy of 81.46% has been achieved in the LSTM model for classifying six emotional states, while SVM accuracy is 68.64%. In addition, promising results have been obtained for the LSTM model of 82.89% with two layers when applied for different layers. In conclusion, we present that the LSTM model specializes in the time-sequence data processing.
참고문헌 (21)
- Egger, M., "Emotion recognition from physiological signal analysis:A review", Electronic Notes in Theoretical Computer Science, 343, pp.35~55 (2019)
- 손귀영, "EEG 신호 기반의 특징벡터 형성 및 감정인식을 위한 기계학습", 한국차세대컴퓨팅학회 논문지, 16(2), pp.72~79 (2020), 한국차세대컴퓨팅학회[DOI]
- 류제우, "EEG 기반 감정인식을 위한 주석 레이블링과 EEG Topography 레이블링 기법의 비교 고찰", 한국차세대컴퓨팅학회 논문지, 15(3), pp.16~24 (2019), 한국차세대컴퓨팅학회[DOI]
- Shin, D., "Development of emotion recognition interface using complex EEG", ECG bio-signal for interactive contents, 2017, pp.76(9), 11449~11470
- Ferdinando, H., "Comparing features from ECG pattern and HRV analysis for emotion recognition system", 2016 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology(CIBCB), pp.1~6 (2016), IEEE
- Khosla, A., "A comparative analysis of signal processing and classification methods for different applications based on EEG signals", Biocybernetics and Biomedical Engineering, 40(2), pp.649~690 (2020)
- Ekman, P., "An argument for basic emotions", Cognition & emotion, 6(3-4), pp.169~200 (1992)
- Russell, J. A., "A circumplex model of affect", Journal of personality and social psychology, 39(6), pp.1161~ (1980)
- Wang, Z. M., "Channel Selection Method for EEG Emotion Recognition Using Mutual Information", IEEE Access, 7, pp.143303~1433114 (2019)
- Xu, H., "Research on EEG Channel Selection Method for Emotion Recognition", 2019 IEEE International Conference on Robotics and Biomimetics(ROBIO), pp.2528~2535 (2019), IEEE
- Javaid, M. M., "Real time eeg-based human emotion recognition", International Conference on Neural Information Processing, pp.182~190 (2015), Springer
- Zheng, W. L., "Revealing critical channels and frequency bands for emotion recognition from EEG with deep belief network", 2015 7th International IEEE, 2015, 154~157[DOI]
- Moon, S. E., "Convolutional neural network approach for EEG-based emotion recognition using brain connectivity and its spatial information", 2018 IEEE International Conference on Acoustics, Speech and Signal Processing(ICASSP), pp.2556~2560 (2018), IEEE
- Nath, D., "A comparative study of subjectdependent and subject-independent strategies for EEG-based emotion recognition using LSTM network", Proceedings of the 2020the 4th International Conference on Compute and Data Analysis, pp.142~147 (2020)
- Bradley, M. M., "Measuring emotion : the self-assessment manikin and the semantic differential", Journal of behaviortherapy and experimental psychiatry, 25(1), pp.49~59 (1994)
- Delorme, A., "EEGLAB: an open source toolbox for analysis of single trial EEG dynamics including independent component analysis", Journal of neuroscience methods, 134(1), pp.9~21 (2004)
- 최민국, "특징 벡터의 effectiveness 요소 기반의 가중치 SVM 분류기 연구", 한국차세대컴퓨팅학회 논문지, 9(1), pp.63~73 (2013), 한국차세대컴퓨팅학회
- Smola, A., "Introduction to machine learning", Cambridge University, 32(34) (2008)
- Hochreiter, S., "Long short term memory", Neural computation, 9(8), pp.1735~1780 (1997)
- Pedregosa, F., "Scikit-learn: Machine learning in Python", the Journal of machine Learning research, 12, pp.2825~2830 (2011)
- Paszke, A., "Pytorch:An imperative style, high-performance deep learning library", Advances in neural information processing systems, 32, pp.8026~8037 (2019)