Fig 5 - uploaded by Panteleimon Chriskos
Content may be subject to copyright.
Source publication
Sleep is a vital physiological process that is necessary for both physical and mental health. Its importance is highlighted from the large number of research efforts that are ongoing regarding normal and pathological sleep related to specific diseases, such as neurodegeneration, depression, or extreme conditions, such as long term space flight. In...
Context in source publication
Citations
... Numerous methods have been developed relying on a variety of features such as those described in [8], [9] and [10], in all cases reporting sleep staging accuracies over 96%. In [11] and [12] the maximum accuracy rates reported are around 99%. Despite the high accuracy rates that can be attained in all cases these must be used only on a recommendation basis to assist the work of sleep experts. ...
... The bands used were defined in [20] as: 1. very low frequency, VLF, in the range 0.0033 -0.04 Hz, 2. low frequency, LF, defined between 0.04 Hz and 0.15 Hz and 3. high frequency, HF, in the frequency range 0.15 -0.4 Hz. These features are detailed among other features in [11]. Sleep staging was conducted with a two hidden layer artificial neural network (the first with 50 and the second with 30 neurons) attaining an accuracy close to 83.2% (13337 train and 5547 test instances). ...
In this paper we present the first steps in developing SmartHypnos, an easy to use and user friendly graphical user interface, which aims to provide polysomngographic data visualization and the detection and classification of sleep related events. Currently SmartHypnos supports the visualization of EEG, ECG, EOG and EMG signals, and respiratory signals such as nasal pressure, thermistor, oxygen saturation, thoracic and abdominal belt recordings. All these are incorporated into an interface that provides quick and effortless access to the signals mentioned above. The interface displays automatic sleep staging capabilities as well as the detection of apnea events with accuracy rates surpassing 80%. It is expected that SmartHypnos will reduce the time required to analyze sleep data and also reduce possible human errors.
Sleep staging is a vital process conducted in order to analyze polysomnographic data. To facilitate prompt interpretation of these recordings, many automatic sleep staging methods have been proposed. These methods rely on bio-signal recordings, which include electroencephalography, electrocardiography, electromyography, electrooculography, respiratory, pulse oximetry and others. However, advanced, uncomplicated and swift sleep-staging-evaluation is still needed in order to improve the existing polysomnographic data interpretation. The present review focuses on automatic sleep staging methods through bio-signal recording including current and future challenges.
