An article describing Jungryul Seo’s boredom classification model using EEG was recently accepted and has now been published. The details of the publication are:
- Authors: Jungryul Seo, Teemu H. Laine and Kyung-Ah Sohn
- Title: Machine learning approaches for boredom classification using EEG
- Journal: Journal of Ambient Intelligence and Humanized Computing
- Abstract: We propose a boredom classification model using EEG and machine learning methods. In the experiment, we showed three emotion evoking videos (two were for evoking non-boredom, and one was for evoking boredom) to 28 participants. During showing the stimuli, we collected EEG from FP1 and FP2 electrodes on the Muse EEG sensor. We utilized the collected data for extracting features to build models. For building models, we selected three machine learning algorithms – support vector machine, random forest, and k-nearest neighbors (k-NN) – and used 10-fold cross validation for measuring the models’ performance. As a result, we confirmed that the model which was trained by k-NN performed the best with 86.73% of accuracy. According to our literature review and results, we showed that our study has novelty over other studies. Also, we used just two electrodes for boredom classification, thus our proposed model can be used in industry and public services.