Developing a simplified system for home monitoring
Las Vegas, Feburary 2016. Sleep is an important part of our life, since we spend, on average, one third of it sleeping. Studies have shown that essential health functions like memory consolidation, organ repair and growth occur almost completely during sleep. To evaluate the quality of a person´s sleep it is necessary to identify the sleep stages and their durations.
Prof. Dr. Martínez Madrid presenting results from the research on Sleep Quality Analysis
Currently, the gold standard in terms of sleep assessment is the overnight polysomnography (PSG), during which electroencephalography (EEG), electrooculography (EOG), electromyography (EMG), oximetry, cardiovascular measures and respiration are recorded. Some commercial systems record and store the data on the wearable device, but the user needs to transfer and import it into specialised software applications or return it to the doctor, for clinical evaluation of the data set. Thus an immediate feedback mechanism or the possibility of remote control and supervision are lacking. Furthermore, many such systems only distinguish between sleep and wake states, or between wake, light sleep and deep sleep. It is not always clear how these stages are mapped to the four known sleep stages: REM, NREM1, NREM2, NREM3-4. The goal of this research is to find a reduced complexity method to process a minimum number of bio vital signals, while providing accurate sleep classification results. The model we propose offers remote control and real time supervision capabilities, by using Internet of Things (IoT) technology. The contribution focuses on the data processing method and the sleep classification logic. Our solution showed promising results and a good potential to overcome the limitations of existing products. Further improvements will be made and subjects with different age and health conditions will be tested.