Development of New Machine Learning Based Algorithm for the Diagnosis of Obstructive Sleep Apnea from ECG Data

In this study,a machine learning algorithm is proposed to be used in the detection of Obstructive Sleep Apnea(OSA)from the analysis of single-channel ECG recordings.Eighteen ECG recordings from the PhysioNet Apnea-ECG dataset were used in the study.In the feature extraction stage,dynamic time warping and median frequency features were obtained from the coefficients obtained from different frequency bands of the ECG data by using the wavelet transform-based algorithm.In the classification phase,OSA patients and normal ECG recordings were classified using Random Forest(RF)and Long Short-Term Memory(LSTM)classifier algorithms.The performance of the classifiers was evaluated as 90% training and 10%testing.According to this evaluation,the accuracy of the RF classifier was 82.43% and the accuracy of the LSTM classifier was 77.60%.Considering the results obtained,it is thought that it may be possible to use the proposed features and classifier algorithms in OSA classification and maybe a different alternative to existing machine learning methods.The proposed method and the feature set used are promising because they can be implemented effectively thanks to low computing overhead.

Emotions States Recognition Based on Physiological Parameters by Employing of Fuzzy-Adaptive Resonance Theory

This paper is an investigation on negative emotions states recognition by employing of Fuzzy Adaptive Resonance Theory (Fuzzy-ART) considering the changes in activities of autonomic nervous system (ANS). Specific psychological experiments were designed to induce appropriate physiological responses on individuals in order to acquire a suitable database for training, validating and testing the proposed procedure. In this research, the three physiological applied signals are Galvanic Skin Response (GSR), Heart Rate (HR) and Respiration Rate (RR). The first experiment which is named Shock was designed to determine a criterion for the change of physiological signals of each individual. In the second one, a combination of two sets of questions has been asked from the subjects to induce their emotions. Finally, Physiological responses were analyzed by Fuzzy-ART to recognize which question excites the negative emotions. Detecting negative emotions from neutral is obtained with total accuracy of 94%.