Abstract
Few studies have focused on investigating the time interval effects on support vector machine (SVM) model in emotion recognition. This study tested original averaged value models and difference value models with three different time-intervals (5 seconds, 10 seconds, and 30 seconds) for SVM emotion recognition in our developed emotion norm database. Forty one elementary school students were recruited as participants to see some emotion pictures in international affective picture system (IAPS), and to collect their affective information—attention, meditation, electroencephalography (EEG), electrocardiogram (ECG), and SpO2 for developing the affective norm recognition system. This study selected 5480 IPAS photos physiological data as the tested dataset from our emotion norm database. The bio-physiology signals were averaged by seconds or difference the value by second and then to serve as the input variables value for C-SVM with RBF kernel function. The results showed that the original averaged models have better performance than the difference models. In addition, the original averaged value model with 30 seconds time interval is the optimal classification model. This study suggested that future research can adopt 30 seconds as the time interval for determining the size of time interval for their training dataset in emotion recognition problem.
Keywords
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Ben Ammar, M., Neji, M., Alimi, A.M., Gouardères, G.: The Affective Tutoring System. Expert Systems with Applications 37, 3013–3023 (2010)
Wu, C.-H., Tzeng, Y.-L., Kuo, B.-C., Tzeng, G.-H.: Integration of affective computing techniques and soft computing for developing a human affective recognition system for U-learning systems. International Journal of Mobile Learning and Organisation 8, 50–66 (2014)
Rashid, N.A., Taib, M.N., Lias, S., Sulaiman, N., Murat, Z.H., Kadir, R.S.S.A.: Learners’ Learning Style Classification related to IQ and Stress based on EEG. Procedia - Social and Behavioral Sciences 29, 1061–1070 (2011)
Zhang, Q., Lee, M.: Emotion development system by interacting with human EEG and natural scene understanding. Cognitive Systems Research 14, 37–49 (2012)
Berka, C., Levendowski, D.J., Cvetinovic, M.M., Petrovic, M.M., Davis, G., Lumicao, M.N., Zivkovic, V.T., Popovic, M.V., Olmstead, R.: Real-Time Analysis of EEG Indexes of Alertness, Cognition, and Memory Acquired With a Wireless EEG Headset. International Journal of Human-Computer Interaction 17, 151–170 (2004)
Berka, C., Levendowski, D.J., Lumicao, M.N., Yau, A., Davis, G., Zivkovic, V.T., Olmstead, R.E., Tremoulet, P.D., Craven, P.L.: EEG correlates of task engagement and mental workload in vigilance, learning, and memory tasks. Aviat Space Environ Med 78, 231–244 (2007)
Lin, T., Imamiya, A., Mao, X.: Using multiple data sources to get closer insights into user cost and task performance. Interacting with Computers 20, 364–374 (2008)
von Borell, E., Langbein, J., Després, G., Hansen, S., Leterrier, C., Marchant-Forde, J., Marchant-Forde, R., Minero, M., Mohr, E., Prunier, A., Valance, D., Veissier, I.: Heart rate variability as a measure of autonomic regulation of cardiac activity for assessing stress and welfare in farm animals — A review. Physiology & Behavior 92, 293–316 (2007)
Tok, S., Koyuncu, M., Dural, S., Catikkas, F.: Evaluation of International Affective Picture System (IAPS) ratings in an athlete population and its relations to personality. Personality and Individual Differences 49, 461–466 (2010)
Waters, A.M., Lipp, O.V., Spence, S.H.: The effects of affective picture stimuli on blink modulation in adults and children. Biological Psychology 68, 257–281 (2005)
Rantanen, A., Laukka, S.J., Lehtihalmes, M., Seppänen, T.: Heart Rate Variability (HRV) reflecting from oral reports of negative experience. Procedia - Social and Behavioral Sciences 5, 483–487 (2010)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Wu, CH., Kuo, BC., Tzeng, GH. (2015). Investigation of Time Interval Size Effect on SVM Model in Emotion Norm Database. In: Barbucha, D., Nguyen, N., Batubara, J. (eds) New Trends in Intelligent Information and Database Systems. Studies in Computational Intelligence, vol 598. Springer, Cham. https://doi.org/10.1007/978-3-319-16211-9_13
Download citation
DOI: https://doi.org/10.1007/978-3-319-16211-9_13
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-16210-2
Online ISBN: 978-3-319-16211-9
eBook Packages: EngineeringEngineering (R0)