Automated detection of cyclic alternating pattern and classification of sleep stages using deep neural network

The visual sleep stages scoring by human experts is the current gold standard for sleep analysis. However, this method is tedious, time-consuming, prone to human errors, and unable to detect microstructure of sleep such as cyclic alternating pattern (CAP) which is an important diagnostic factor for the detection of sleep disorders such as insomnia and obstructive sleep apnea (OSA). The CAP is only observed as subtle changes in the electroencephalogram (EEG) signals during non-rapid eye movement (NREM) sleep, making it very difficult for human experts to discern. Hence, it is important to have an automated system developed using artificial intelligence for accurate and robust detection of CAP and sleep stages classification. In this study, a deep learning model based on 1-dimensional convolutional neural network (1D-CNN) is proposed for CAP detection and homogenous 3-class sleep stages classification, namely wakefulness (W), rapid eye movement (REM) and NREM sleep. The proposed model is developed using standardized EEG recordings. Our developed CNN network achieved good model performance for 3-class sleep stages classification with a classification accuracy of 90.46%. Our proposed model also yielded a classification accuracy of 73.64% using balanced CAP dataset, and sensitivity of 92.06% with unbalanced CAP dataset. Our proposed model correctly identified majority of A-phases which comprised of only 12.6% in the unbalanced dataset. The performance of the developed prototype is ready to be tested with more data before clinical application.

     

3D Modelling of Superconductor Enabled Magnetic Induction Transmitter and Relay Coil for Non-conventional Media Communication

The well established way of communication using radio frequency (RF) waves do not perform well in Non-Conventional (Non-Con) media viz. underground and underwater. Herein, the medium of soil or water is dynamic thus the use of RF technique is unusable. To establish a more effective communication in Non-Con media, researches showed that Magnetic Induction (MI) communication to be more suitable. In MI communication, parameters like number of turns, size and coil orientation have a significant effect on transceiver coil model. In this paper, a novel MI transmitter model using superconductor (SC) in one directional (1D) and in three directional (3D) is proposed. The model provides an enhanced magnetic field strength over a given distance. Further, SC based relay coils which collectively known as waveguide structure is also proposed to increase the MI communication range with intensified field strength. The performance evaluations are quantified in terms of communication range and received power for Non-Con medias. The frequency response for SC based transmitter model is given for maximum power transfer. Besides, the performance of traditional MI systems and waveguide are quantitatively compared with our improved SC based MI system and waveguide. The results show that the system has stronger magnetic field strength and greater communication range than the traditional ones.