Arousal and Valence Classification Model Based on Long Short-Term Memory and DEAP Data for Mental Healthcare Management
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Objectives: Both the valence and arousal components of affect are important considerations when managing mental healthcare because they are associated with affective and physiological responses. Research on arousal and valence analysis, which uses images, texts, and physiological signals that employ deep learning, is actively underway; research investigating how to improve the recognition rate is needed. The goal of this research was to design a deep learning framework and model to classify arousal and valence, indicating positive and negative degrees of emotion as high or low. Methods: The proposed arousal and valence classification model to analyze the affective state was tested using data from 40 channels provided by a dataset for emotion analysis using electrocardiography (EEG), physiological, and video signals (the DEAP dataset). Experiments were based on 10 selected featured central and peripheral nervous system data points, using long short-term memory (LSTM) as a deep learning method. Results: The arousal and valence were classified and visualized on a two-dimensional coordinate plane. Profiles were designed depending on the number of hidden layers, nodes, and hyperparameters according to the error rate. The experimental results show an arousal and valence classification model accuracy of 74.65 and 78%, respectively. The proposed model performed better than previous other models. Conclusions: The proposed model appears to be effective in analyzing arousal and valence; specifically, it is expected that affective analysis using physiological signals based on LSTM will be possible without manual feature extraction. In a future study, the classification model will be adopted in mental healthcare management systems.
Abstract
Objectives: Both the valence and arousal components of affect are important considerations when managing mental healthcare because they are associated with affective and physiological responses. Research on arousal and valence analysis, which uses images, texts, and physiological signals that employ deep learning, is actively underway; research investigating how to improve the recognition rate is needed. The goal of this research was to design a deep learning framework and model to classify arousal and valence, indicating positive and negative degrees of emotion as high or low. Methods: The proposed arousal and valence classification model to analyze the affective state was tested using data from 40 channels provided by a dataset for emotion analysis using electrocardiography (EEG), physiological, and video signals (the DEAP dataset). Experiments were based on 10 selected featured central and peripheral nervous system data points, using long short-term memory (LSTM) as a deep learning method. Results: The arousal and valence were classified and visualized on a two-dimensional coordinate plane. Profiles were designed depending on the number of hidden layers, nodes, and hyperparameters according to the error rate. The experimental results show an arousal and valence classification model accuracy of 74.65 and 78%, respectively. The proposed model performed better than previous other models. Conclusions: The proposed model appears to be effective in analyzing arousal and valence; specifically, it is expected that affective analysis using physiological signals based on LSTM will be possible without manual feature extraction. In a future study, the classification model will be adopted in mental healthcare management systems.
참고문헌 (29)
- Salamon N, "Application of virtual reality for crew mental health in extended-duration space missions", Acta Astronaut, 146, pp.117~122 (2018)
- Valmaggia LR, "Virtual reality in the psychological treatment for mental health problems : an systematic review of recent evidence", Psychiatry Res, 236, pp.189~195 (2016)
- Faust O, "Deep learning for healthcare applications based on physiological signals : a review", Comput Methods Programs Biomed, 161, pp.1~13 (2018)
- Zhang Q, "Respirationbased emotion recognition with deep learning", Comput Ind, 92-93, pp.84~90 (2017)
- Yin Z, "Recognition of emotions using multimodal physiological signals and an ensemble deep learning model", Comput Methods Programs Biomed, 140, pp.93~110 (2017)
- Haeyen S, "Promoting mental health versus reducing mental illness in art therapy with patients with personality disorders : a quantitative study", Arts Psychother, 58, pp.11~16 (2018)
- Zhang L, "Emotion regulation difficulties and moral judgement in different domains : the mediation of emotional valence and arousal", Pers Individ Dif, 109, pp.56~60 (2017)
- Healey J, "Detecting stress during real-world driving tasks using physiological sensors", IEEE trans Intell Transp Syst, 6(2), pp.156~166 (2005)
- Xia L, "A physiological signalbased method for early mental-stress detection", Biomed Signal Process Control, 46, pp.18~32 (2018)
- Lee D, "The study on EEG based emotion recognition using the EMD and FFT", Proceedings of the HCI Society of Korea, pp.127~130 (2013)
- Wang D, "Modeling physiological data with deep belief networks", Int J Inf Educ Technol, 3(5), pp.505~511 (2013)
- "DEAPdataset: a dataset for emotion analysis using EEG, physiological and video signal" (2017)[URL]
- Kim J, "Emotion recognition based on physiological changes in music listening", IEEE Trans Pattern Anal Mach Intell, 30(12), pp.2067~2083 (2008)
- Kreibig SD, "Autonomic nervous system activity in emotion : a review", Biol Psychol, 84(3), pp.394~421 (2010)
- Collet C, "Autonomic nervous system response patterns specificity to basic emotions", J Auton Nerv Syst, 62(1-2), pp.45~57 (1997)
- Ryoo DW, "Wearable systems for service based on physiological signals", Conf Proc IEEE Eng Med Biol Soc, 3, pp.2437~2440 (2005)
- Jerritta S, "Physiological signals based human emotion recognition: a review", Proceedings of 2011 IEEE 7th International Colloquium on Signal Processing and its Applications (CSPA), pp.410~415 (2001)
- Chang CY, "Based on support vector regression for emotion recognition using physiological signals", Proceedings of the 2010 International Joint Conference on Neural Networks (IJCNN), pp.1~7 (2010)
- 김종화, "The study on emotion recognition by time-dependent parameters of autonomic nervous response", 감성과학, 11(4), pp.637~644 (2008), 한국감성과학회
- Vogt T, "Improving automatic emotion recognition from speech via gender differentiation", Proceedings of Language Resources and Evaluation Conference (LREC) (2006)
- Mill A, "Age-related differences in emotion recognition ability : a cross-sectional study", Emotion, 9(5), pp.619~630 (2009)
- Russell JA, "A circumplex model of affect", J Pers Soc Psychol, 39(6), pp.1161~1178 (1980)
- Kwon SJ, "Sentiment analysis of movie reviews using the Word2vec and RNN", Master's, pp.2009
- "Recurrent neural network" (2018)[URL]
- Chanel G, "Short-term emotion assessment in a recall paradigm", Int J Hum Comput Stud, 67(8), pp.607~627 (2009)
- Rainville P, "Basic emotions are associated with distinct patterns of cardiorespiratory activity", Int J Psychophysiol, 61(1), pp.5~18 (2006)
- "Deeplearning4j" (2018)[URL]
- "Machine learning: learning rate, data processing, overfitting" (2017)[URL]
- Song SH., "The emotion analysis based on long short term memory using the central and autonomic nervous system signals", pp.2018