A Study on Training Data Selection Method for EEG Emotion Analysis Using Artificial Neural Network
Jong-Seob Yun,Department of Electronics & Computer Engineering, Seokyeong University
Jin Heon Kim,Department of Computer Engineering, Seokyeong University
The learning of the artificial neural network is performed in the process of modeling using the acquired data set. At this time, erroneous selection of training data makes it difficult to stabilize the model, leading to a decrease in recognition rate. In this paper, we investigate how to select the training data in order to improve the recognition rate in constructing artificial neural network for emotion classification using DEAP (Database for Emotion Analysis using Physiological Signals). EEG was recorded on two channels of FP1 and FP2 among 32 channels during viewing of images which cause pleasure, sadness and shock feeling. PSD (Power Spectral Density) values obtained by applying FFT (Fast Fourier Transform) to EEG data were used as feature data of brain waves to be input to the artificial neural network. Finally, emotion classification was performed by modeling artificial neural network by selecting training data from EEG data based on Valence and Arousal values determined using SAM (Self-Assessment Manikin) method.
Artificial Neural Network, DEAP, EEG, Emotion Analysis, PSD.
 W. Zheng, IEEE. Transactions. Cognitive. Developmental. Systems. 9, 3 (2017)
 M. Z. Ahmad, M. Saeed, S. Saleem, and A. M. Kamboh. International Conference on Emerging Technologies, (2016) October 18-19; Islamabad, Pakistan
 M. Bachmann, J. Lass, and H. Hinrikus, Biomedical. Signal. Processing. Control. 31, (2017)
 Y. Wastanabe, Y. Kobayashi, M. Tanaka, T. Asada, K. Ishii, and T. Yagi. Biomedical Engineering International Conference, (2017) August 31-September 2; Hokkaido, Japan
 S. Bisgaard, B. D. Christensen, L. Kempfner, H. B. D. Sorensen, and P. Jennum. Annual International Conference of the IEEE Engineering in Medicine and Biology Society, (2015) August 25-29; Milan, Italy
 D. E. Kim, T. J. Lee, S. M. Park, K. E. Ko, and K. B. Sim, J. Korean. Institute. Inteligent. Systems. 23, 2 (2013)
 Y. H. Kim, K. E. Ko, S. M. Park, and K. B. Sim, J. Institute. Control. Robotics. Systems. 19, 3 (2013)
 D. E. Kim, J. H. Yu, and K. B. Sim, J. Korean. Institute. Intelligent. Systems. 25, 1 (2015)
 H. J. Lee, D. I. Shin, and D. K. Shin, J. Korean. Institute. Communications. Information. Sciences. 39, 2 (2014)
 D. J. Kim, and H. M. Lee, J. Korea. Institute. Information. Electronics. Communication. Technology. 2, 2 (2009)
 N. Jatupaiboon, S. Pan-ngum, and P. Israsena, The. Scientific. World. Journal. 2013, (2013)
 S. Koelstra, C. Muhl, M. Soleymani, J. S. Lee, A. Yazdani, T. Ebrahimi, T. Pun, A. Nijholt, and I. Patras, IEEE. Transactions. Affective. Computing. 3, 1 (2012)
© 2018 Yun Jong-Seob et al. Published by Global Vision Press. This is an open access article distributed under the terms of the Creative Commons Attribution 4.0 International License (CCBY4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.