Design of Classification of Human Stress Levels Based on Brain Wave Observation Using EEG with K-NN Algorithm

Abstract

Stress is a condition that can suppress the person’s psychic state in achieving something. Stress, at some level, can harm human health since it can cause various diseases that humans often underestimate. These diseases include headaches, cramps, heart attacks, high blood pressure, and even strokes can occur. Stress levels are detected by manually filling out questionnaires or conducting self-assessment tests. However, it seems subjective because the results depend on honesty in answering the questionnaire. Therefore, in this study, we conduct a study to classify human stress levels by observing brain wave activity using an Electroencephalogram (EEG). Since EEG signals can directly reflect the brain’s electrical activity, they can be used as an objective measure for classifying stress levels. In this study, the method used in classification is K-Nearest Neighbour. The signal processing stages include pre-processing, feature extraction using Independent Component Analysis (ICA), and then classification using K-Nearest Neighbour. This research used 62 data as training and testing data. After testing the system, it was concluded that the K-Nearest Neighbour method could classify stress into normal and high levels with an accuracy of 75% with a k-value of 7.