Human Activity Recognition Using Machine Learning Technique

ABSTRACT

COVID has made education shift towards online mode. In online mode, instructors have a hard time keeping track of their students. Students' performance in online classes falls considerably below the level of learning due to a lack of attention. This initiative aids in the supervision of students during online classes. Artificial Intelligence (AI) models are being developed to better recognize student activities during online sessions. Many applications rely on determining an individual's mental state. When evaluating which subtask is the most challenging, a quantitative measure of human activity while executing a task can be helpful. Thus, the goal of this research is to create an algorithm that uses EEG data gathered with a Muse headset to measure the amount of cognitive intelligence of students during online classes. The data collected by the Muse headset is multidimensional, and it is pre-processed before being fed into machine learning algorithms. Using feature selection, the dataset's dimension is now reduced. The model's precision and recall were calculated, and a confusion matrix was created. The Support Vector Machine produces better outcomes in the experiment. © 2022 IEEE.