Abstract
Brain computer interfaces (BCIs) are rapidly gaining a lot of momentum within the biomedical engineer's sphere. The BCI is a link between the brain's electrical activity and a device that monitors actions and functions based on its input. In this paper, we have created a prediction algorithm for BCI systems that takes in EEG data (i.e., data classified based on actions) using machine learning (ML) techniques. Furthermore, EEG data is obtained and subsequently examined under specific conditions. This is necessary as the data would otherwise lack significance for computation. This is due to the fact that EEG data mostly consists of highly disordered electrical brain wave activity. In the analysis phase of this study, many Python libraries could be used ranging from the MNE library which is an essential tool used in EEG analysis to scikit which is used in many branches of ML. This project has a special emphasis on the use of Pandas for ML. The project's EEG data has been obtained from workers and interns of the Turkish government agency called scientific and technological research council of Türkiye (TÜBİTAK). While the data was being recorded, a special EEG recording software has been used that assigns condition inputs that attach them to the epoched time data.