Analysis of Narcolepsy Based on Single-Channel EEG Signals

A normal person spends about third of his life in sleep. Healthy sleep is vital to people’s normal lives. Sleep analysis can be used to diagnose certain physiological and neurological diseases such as insomnia and narcolepsy. This paper will introduce the sleep stage and the corresponding electroencephalogram (EEG) characteristics at each stage. We used the deep convolutional neural network (CNN) to classify original EEG data with narcolepsy. We use perturbations based on frequency to generate adversarial examples to analyze the characteristics of narcolepsy in different sleep stages. We find that perturbations at specific frequencies affect the classification results of deep learning.

[1]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[2]  Chao Wu,et al.  DeepSleepNet: A Model for Automatic Sleep Stage Scoring Based on Raw Single-Channel EEG , 2017, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[3]  G. Plazzi,et al.  Electroencephalogram paroxysmal θ characterizes cataplexy in mice and children. , 2013, Brain : a journal of neurology.

[4]  Syed Hasan Saeed,et al.  Diagnosis of narcolepsy sleep disorder for different stages of sleep using Short Time Frequency analysis of PSD approach applied on EEG signal , 2016, 2016 International Conference on Computational Techniques in Information and Communication Technologies (ICCTICT).

[5]  E. Mignot,et al.  Narcolepsy with cataplexy , 2007, The Lancet.

[6]  E. Hartmann.  The Functions of Sleep , 1973 .

[7]  Enzo Tagliazucchi,et al.  Narcoleptic Patients Show Fragmented EEG-Microstructure During Early NREM Sleep , 2014, Brain Topography.

[8]  Mark Shein-Idelson,et al.  Slow waves, sharp waves, ripples, and REM in sleeping dragons , 2016, Science.

[9]  N. Kleitman,et al.  Regularly occurring periods of eye motility, and concomitant phenomena, during sleep. , 1953, Science.

[10]  Hubert Cecotti,et al.  Convolutional Neural Network with embedded Fourier Transform for EEG classification , 2008, 2008 19th International Conference on Pattern Recognition.

[11]  Mingyan Liu,et al.  Generating Adversarial Examples with Adversarial Networks , 2018, IJCAI.

[12]  M. Tafti,et al.  How Much Sleep Do We Need? , 2009, Science.

[13]  Laurent Vercueil,et al.  A convolutional neural network for sleep stage scoring from raw single-channel EEG , 2018, Biomed. Signal Process. Control..

[14]  H. Rickards,et al.  Narcolepsy: a review , 2011, Neuropsychiatric disease and treatment.

[15]  Tommi S. Jaakkola,et al.  Learning Sleep Stages from Radio Signals: A Conditional Adversarial Architecture , 2017, ICML.

[16]  E. Mignot,et al.  Diagnostic value of sleep stage dissociation as visualized on a 2-dimensional sleep state space in human narcolepsy , 2017, Journal of Neuroscience Methods.

[17]  Mark W. Mahowald,et al.  Insights from studying human sleep disorders , 2005, Nature.

[18]  S. Uchida,et al.  Spectral analysis of all‐night human sleep EEG in narcoleptic patients and normal subjects , 2003, Journal of sleep research.

[19]  Lawrence Carin,et al.  Analysis of Brain States from Multi-Region LFP Time-Series , 2014, NIPS.