APSEN: Pre-screening Tool for Sleep Apnea in a Home Environment

This paper describes the APSEN system, a pre-screening tool for detecting sleep apnea in a home environment. The system was designed and evaluated in two parts; the apnea detection using SpO2 and the posture detection using IR images. The two parts can work together or independently. During the preliminary study, the apnea detection algorithm was evaluated using an online database, and the right algorithms for detecting the sleep posture were determined. In the overnight study, both of the subsystems were tested on 10 subjects. The average accuracy for the apnea detection algorithm was 71.51% for apnea conditions, and 98.68% for normal conditions. For the posture detection algorithms, during the overnight study, the average accuracies are 74.91% and 89.71% for SVM and CNN, respectively. The results represented in the paper indicate that the APSEN system could be used to detect apnea and postural apnea in a home environment.