Sleep Disorder Prediction on Polysomnography with EEG Signal using Machine Learning Algorithms

This research study intends to predicts whether the patient is having sleep disorder or not. A dataset of EEG (electroencephalogram) signals, which are measurements of electrical activity in the brain are considered. The obtained signals are pre-processed to filter out any background noise, and then categorized by frequency analysis into four types of brain waves: alpha, beta, theta, and delta. This categorization is accomplished through the use of the Fast Fourier Transformation (FFT), to transfer the signal from the time domain to frequency domain. The next step in the analysis is to extract features from the dataset in order to differentiate between people with insomnia and normal individuals. This is done using logistic regression, which is a statistical technique used to predict the probability of a binary outcome (in this case, whether or not a person has insomnia).Finally, several machine learning algorithms are used to accurately detect insomnia in the dataset. These algorithms include logistic regression, decision tree, random forest, and support vector classifier (SVC). These models employ several methodologies to categorize data and also have the potential to enhance classification accuracy. The purpose of this study is to create a model that can correctly identify persons suffering from insomnia based on their EEG data. This can potentially have important clinical implications, as early detection and intervention can leverage better treatment for people with sleep disorders.