Automated Sleep Staging Classification System using EEG Signals based on Machine Learning Techniques

Brain-computer interfaces (BCIs) aim to analyze brain activity into control signals for external devices. Sleep staging classification (SSC), the sleep behavior, has been studied extensively in BCIs as a means of decoding user sleep behavior from neural activity. Electroencephalogram (EEG) recordings provide a non-invasive interface for monitoring SSC by detecting irregularities in brain activation. Accurately classifying sleep stages from EEG signals is essential for developing practical SSC-based BCIs. However, existing machine learning techniques require extensive preprocessing and handcrafted feature engineering, limiting accuracy and efficiency. In this work, we propose a stacking learning approach for sleep staging classification from raw EEG signals. Specifically, we extracted time and frequency domain features from the EEG data. The extracted features are then fed into a different classification model to perform classification. We demonstrate that our proposed framework achieves significantly higher accuracy in classifying five-class sleep stages than conventional machine learning classifiers. Our results highlight the potential of stacking ensemble learning to advance SSC-based BCIs by learning highly complex representations of EEG signals. Thus, The proposed stacking model represents a promising step towards more sophisticated BCIs that can translate raw neural data into control signals for identifying and accurately classifying the sleep stages.