Emotion recognition system based on EEG signals using relative wavelet energy features and a modified radial basis function neural networks

Bharasaka Krisnandhika, Akhmad Faqih, Prima Dewi Purnamasari, Benyamin Kusumo Putro

Research output: Chapter in Book/Report/Conference proceedingConference contribution

9 Citations (Scopus)

Abstract

Emotion recognition is very important, especially on its application for patient monitoring and in the treatment management system of that patient. In this paper, an EEG-based emotion recognition system is developed that consists of a feature extraction subsystem and a classifier subsystem. In this research, we have studied the utilization of a relative wavelet energy as the feature extraction, and a modified radial basis function neural networks is then implemented as the classifier. Experimental result shows that the relative wavelet energy and the modified radial basis function neural networks achieved an average recognition rate of 76% when using a 50% of the data in the training stage.

Original languageEnglish
Title of host publication2017 International Conference on Consumer Electronics and Devices, ICCED 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages50-54
Number of pages5
ISBN (Electronic)9781538604038
DOIs
Publication statusPublished - 29 Aug 2017
Event1st International Conference on Consumer Electronics and Devices, ICCED 2017 - London, United Kingdom
Duration: 14 Jul 201717 Jul 2017

Publication series

Name2017 International Conference on Consumer Electronics and Devices, ICCED 2017

Conference

Conference1st International Conference on Consumer Electronics and Devices, ICCED 2017
CountryUnited Kingdom
CityLondon
Period14/07/1717/07/17

Keywords

  • emotion classification
  • emotion recognition
  • modified radial basis function neural networks
  • relative wavelet energy

Fingerprint Dive into the research topics of 'Emotion recognition system based on EEG signals using relative wavelet energy features and a modified radial basis function neural networks'. Together they form a unique fingerprint.

  • Cite this

    Krisnandhika, B., Faqih, A., Purnamasari, P. D., & Putro, B. K. (2017). Emotion recognition system based on EEG signals using relative wavelet energy features and a modified radial basis function neural networks. In 2017 International Conference on Consumer Electronics and Devices, ICCED 2017 (pp. 50-54). [8019990] (2017 International Conference on Consumer Electronics and Devices, ICCED 2017). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCED.2017.8019990