MIND-WANDERING DETECTION MODEL WITH ELECTROENCEPHALOGRAM

Abstract

The study of mind-wandering is popular since it is linked to the emotional problems and working/learning performance. In terms of education, it impacts comprehension during learning which affects academic success. Therefore, we sought to develop a machine learning model for an embedded portable device that can categorize mind-wandering state to assist people in keeping track of their minds. We utilize a low-channel EEG to record the brain state and to build the predictive model because of its practicality and user-friendly. Most machine learning experiments in mind-wandering using EEG exhibit good individual-level performance. For the group-level technique, only a few research has developed a model. As a result, the goal of this research is to achieve a high-accuracy group-level model. Thus, Leave One Participant Out Cross Validation (LOPOCV) was used to assess the model correctness. This study shows that using a baseline normalization technique assists feature extraction and improves performance. The model was built using a support vector machine (SVM), and the best model achieved an accuracy value of 75.6 percent.