CLASSIFICATION OF MENTAL FATIGUE BASED ON EEG SIGNAL ANALYSIS USING THE K-NN ALGORITHM

Abstract

Mental fatigue is a condition that can impact an individual's productivity and health. Commonly used diagnostic methods are subjective, making it difficult to accurately and in real-time detect a person's level of mental fatigue. Using electroencephalogram (EEG) signals, a technology for measuring brain activity, objective data related to mental fatigue can be obtained. The K-Nearest Neighbor (K-NN) algorithm is used to classify fatigue levels by analyzing patterns formed from EEG signals. The dataset was obtained from the open-source resource Kaggle, which provides data related to mental fatigue, including EEG signals from healthy and mentally fatigued individuals. This platform provides several EEG datasets for classification and research purposes. The K-NN model can classify mental fatigue with high accuracy based on EEG patterns.This provides the basis for the development of practical and efficient EEG-based fatigue detection technology