Emotion Classification by EEG Signal Generated by Brain using Discrete Wavelet Transform and Artificial Neural Network Backpropagation with Classical Music Stimulus

  • Aditya Dimas Universitas Teknologi Yogyakarta
Keywords: EEG, Emotion, Discrete Wavelet Transform, Artificial Neural Network, Backpropagation


People feel different emotions when listening to music on certain levels. Such feelings occur because the music stimuli causing reduced or increased brain activity and producing brainwave with specific characteristics. Results of research indicated that classical piano music can influence one’s emotional intelligent. By using Electroenchephalography (EEG) as a brainwave recording instrument, we can assess the effect of stimulation on the emotions generated through brain activity. This study aimed at developing a method that defines the effect of sound to brain activity using an EEG signal that can be used to identify one's emotion based on classical piano music stimulus reaction. Based on its frequency, this signal was the classified using DWT. To train Artificial Neural Network, some features were taken from the signal. This ANN research was carried out using the process of backpropagation

Author Biography

Aditya Dimas, Universitas Teknologi Yogyakarta

Universitas Teknologi Yogyakarta


Basu, Jayanta Kumar (et al). 2010. “Use of Artificial Neural Network in Pattern Recognition”. International Journal of Software Engineering and Its Applications .4 (1738-9984): 23-34
Dhariya, Subhanshu. 2013. “Human Emotion Detection System Using EEG Signals”. International KIET Journal of Software and Communication Technologies (IKJSCT). Volume 1, Issue 1, pp: 25-30
Husheng Lu, Mingshi Wang and Hongqiang Yu, “EEG Model and Location in Brain when Enjoying Music”, in proceedings of the 2005 IEEE in Engineering in Medicine and Biology 27th Annual Conference, Shanghai, 2005, pp. 2695-2698.
Murugappan, Murugappan(et. al.). 2010. “Classification of human emotion from EEG using discrete wavelet transform”. J. Biomedical Science and Engineering 3. 390-396
S. Koelstra, C. Muhl, M. Soleymani, J.S. Lee, A. Yazdani, T. Ebrahimi, T. Pun, and A. Nijholt, “DEAP: a databased for emotion analysis using physiological signals”, IEEE Trans. On Affective Computing, vol. 3, no. 1, pp. 18-31, Jan-Mar 2012.
Wichakam, Itsara and Vateekul. 2014. “An Evaluation of Feature Extraction in EEG-Based Emotion Prediction with Support Vector Machines”, IEEE 11th International Joint Conference on Computer Science and Software Engineering (JCSSE).106-110