Computer Aided Detection of Obstructive Sleep Apnea from EEG Signals

Sleep Apnea is an anomaly in sleeping characterized by short pause breathing. Failure to treat sleep apnea leads fatal complications both psychological and physiological being of human. Electroencephalogram (EEG) performs important task probing for through identifying recording the brain’s activities while sleeping. In this study, computer aided detection from EEG signals developed optimize increase prompt recognition diagnosis patients. The time domain, wavelets, frequency domain were computed, features extracted these domains. These are inputted into two machine learning algorithms: Support Vector Machine K-Nearest Neighbors different kernel functions orders. Evaluation metrics such as specificity, accuracy, sensitivity computed analyzed classifiers. KNN classifier outperforms SVM classifying non-apnea events order 3 shows highest performance 85.92%, specificity 80% accuracy 82.69%.