멀티모달 감정인식률 향상을 위한 웨이블릿 기반의통계적 잡음 검출 및 감정분류 방법 연구
Wavelet-based Statistical Noise Detection and Emotion Classification Method for Improving Multimodal Emotion Recognition
3
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
최근 인간의 감정을 인식하는 연구 중 딥러닝 모델을 사용하여 복합적인 생체 신호를 분석하는 방법론이 대두되고 있다. 이때 학습하고자 하는 데이터의 종류에 따른 평가 방법 및 신뢰성은 감정 분류의 정확성에 있어 중요한 요소이다. 생체 신호의 경우 데이터의 신뢰성이 잡음 비율에 따라 결정되므로 잡음 검출 방법이 우수할수록 신뢰도가 올라가며, 감정을 정의하는방법론에 따라 그에 맞는 적절한 감정 평가 방법이 수반될 때보다 정확하게 감정을 분류할 수 있다. 본 논문에서는 Valence와 Arousal로 라벨링 된 멀티모달 생체 신호 데이터에 대해 데이터의 신뢰성을 검증하기 위한 웨이블릿 기반의 잡음 임곗값설정 알고리듬 및 감정 평가 시 데이터 신뢰도와 Valence-Arousal 값에 따른 가중치를 부여하여 감정 인식률을 향상하는 방법을 제안한다. 웨이블릿 변환을 이용해 신호의 웨이블릿 성분을 추출 후, 해당 성분의 왜도와 첨도를 구하여 햄펄 식별자를통해 계산된 임곗값으로 잡음을 검출한 후, 원신호에 대한 잡음 비율을 고려하여 데이터의 신뢰성을 평가하고 가중치로 환산한다. 더불어 감정 데이터 분류 시 Valence-Arousal 평면의 중앙값과의 유클리디언 거리를 가중치로 환산하고, 감정 인식률에 대한 종합 평가 시 두 요소를 반영한다. ASCERTAIN 데이터셋을 활용하여 나타난 감정 인식률 개선 정도를 통해 제안된알고리듬의 성능을 검증한다.
Abstract
Recently, a methodology for analyzing complex bio-signals using a deep learning model has emerged among studiesthat recognize human emotions. At this time, the accuracy of emotion classification may be changed depending on theevaluation method and reliability depending on the kind of data to be learned. In the case of biological signals, thereliability of data is determined according to the noise ratio, so that the noise detection method is as important as that. Also, according to the methodology for defining emotions, appropriate emotional evaluation methods will be needed. Inthis paper, we propose a wavelet -based noise threshold setting algorithm for verifying the reliability of data formultimodal bio-signal data labeled Valence and Arousal and a method for improving the emotion recognition rate byweighting the evaluation data. After extracting the wavelet component of the signal using the wavelet transform, thedistortion and kurtosis of the component are obtained, the noise is detected at the threshold calculated by the hampelidentifier, and the training data is selected considering the noise ratio of the original signal. In addition, weighting isapplied to the overall evaluation of the emotion recognition rate using the euclidean distance from the median value ofthe Valence-Arousal plane when classifying emotional data. To verify the proposed algorithm, we use ASCERTAIN dataset to observe the degree of emotion recognition rate improvement.
참고문헌 (24)
- M. Soleymani, "A Multimodal Database for Affect Recognition and Implicit Tagging", IEEE Transactions on Affective Computing, 3(1), pp.42~55 (2012), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- Gabriele Fanelli, "A 3-D Audio-Visual Corpus of Affective Communication", IEEE Transactions on Multimedia, 12(6), pp.591~598 (2010), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- Zhong Yin, "Operator functional state classification using least-square support vector machine based recursive feature elimination technique", Computer Methods and Programs in Biomedicine, 113(1), pp.101~115 (2014), Elsevier BV[DOI]
- J. Kim, "Emotion-specific dichotomous classification and feature-level fusion of multichannel biosignals for automatic emotion recognition", Pro-ceedings of IEEE Inter-national Conference on Multisensor Fusion and Integration for Intelligent Systems 2008 (2008)
- Hyejeen Lee, "Test-retest reliability of voluntary emotion regulation", Psychophysiology, 46(4), pp.874~879 (2009), Wiley[DOI]
- Omar AlZoubi, "Detecting Naturalistic Expressions of Nonbasic Affect Using Physiological Signals", IEEE Transactions on Affective Computing, 3(3), pp.298~310 (2012), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- L. Brown, "Towards wireless emotional valence de-tection from EEG", Proceedings of Engineering in Medicine and Biology Society (2011), EMBC
- Richard J. Davidson, "Affective neuroscience and psychophysiology: Toward a synthesis", Psychophysiology, 40(5), pp.655~665 (2003), Wiley[DOI]
- Zhong Yin, "Identification of temporal variations in mental workload using locally-linear-embedding-based EEG feature reduction and support-vector-machine-based clustering and classification techniques", Computer Methods and Programs in Biomedicine, 115(3), pp.119~134 (2014), Elsevier BV[DOI]
- Gyanendra K. Verma, "Multimodal fusion framework: A multiresolution approach for emotion classification and recognition from physiological signals", NeuroImage, 102, pp.162~172 (2014), Elsevier BV[DOI]
- Mahdi Khezri, "Reliable emotion recognition system based on dynamic adaptive fusion of forehead biopotentials and physiological signals", Computer Methods and Programs in Biomedicine, 122(2), pp.149~164 (2015), Elsevier BV[DOI]
- Chao Li, "Analysis of physiological for emotion recognition with the IRS model", Neurocomputing, 178, pp.103~111 (2016), Elsevier BV[DOI]
- Senthil, "Removal of ocular artifacts in the EEG through wavelet transform without using an EOG reference channel", Int.J. Open Problems Compt. Math, 1(3) (2008)[DOI]
- Mrs V Baby Deepa, "Investigating the performance improvement by sampling techniques in EEG data", International Journal on Computer Science and Engineering, 2, pp.2025~2028 (2010)
- J. Hernandez, "Call center stress recognition with person-specific models", Proceedings of the Affective Computing and Intelligent Interaction (2011)
- Ming-Zher Poh, "A Wearable Sensor for Unobtrusive, Long-Term Assessment of Electrodermal Activity", IEEE Transactions on Biomedical Engineering, 57(5), pp.1243~1252 (2010), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- M. Poh, "Continuous monitoring of electrodermal activity during epileptic seizures using a wearable sensor", Annual Int. Conf. of the IEEE Engineering in Medicine and Biology Society (EMBC), pp.5625988~ (2010)[DOI]
- R. R. Coifman, "Wavelets and statistics, Vol.103", pp.281~299 (1995)
- D. Puthankattil Subha, "EEG Signal Analysis: A Survey", Journal of Medical Systems, 34(2), pp.195~212 (2010), Springer Nature[DOI]
- Chmelka, "Wavelet-based Wiener Filter for electrocardiogram signal denoising", Comput. Cardiol, 32, pp.771~774 (2005)[DOI]
- Maarten Jansen, "wavelet Thresholding and Noise Reductionm", Leuven-Faculteit Toegepaste Wetenschappen, pp.2000
- R. Subramanian, "ASCERTAIN : Emotion and Personality Recognition using Commercial Sensors", IEEE Transactions on Affective Computing, pp.1~14 (2016)
- P. Baldi, "Boolean AutoEncoder", 37~50 (2012)
- R. Memisevic, "Advances in Neural", pp.1~9 (2010)