Deep learning analysis for estimating sleep syndromedetection utilizing the twin convolutional model FTC2

Abstract

Manual sleep stage scoring is frequently performed by sleep specialists by visually evaluating the patient’sneurophysiological signals acquired in sleep laboratories. This is a difficult, time-consuming, and laborious process.Because of the limits of human sleep stage scoring, there is a greater need for creating automatic sleep stageclassification (ASSC) systems. Sleep stage categorization is the process of distinguishing the distinct stagesof sleep and is an important step in assisting physicians in the diagnosis and treatment of associated sleepdisorders. In this research, we offer a unique method and a practical strategy to predict early onset of sleepdisorders, such as restless leg syndrome and insomnia, using the twin convolutional model FTC2, based on analgorithm composed of two modules. To provide localized time-frequency information, 30-second-long epochs ofelectroencephalogram (EEG) recordings are subjected to a fast Fourier transform, and a deep convolutional longshort-term networks neural network is trained for sleep stage categorization. Automating sleep stage detectionfrom EEG data offers a great potential to tackle sleep irregularities on a daily basis. Thereby, a novel approach forsleep stage classification is proposed, which combines the best of signal processing and statistics. In this study,we used the PhysioNet Sleep European Data Format (EDF) database. The code evaluation showed impressiveresults, reaching an accuracy of 90.43, precision of 77.76, recall of 93,32, F1 score of 89.12, and the final meanfalse error loss of 0.09. All the source code is available athttps://github.com/timothy102/eeg..