Nowadays, sleep disorders e.g. sleep apnea —the cessation of airflow at the nose and mouth lasting at least 10 second— are a broadly problem around the world. Direct and indirect costs associated to sleep problems are outsize and the quality of patient life is deteriorated because of it. In addition, Sleep is a fundamental part of everyday life, the lack of it or the poor quality of sleep may lead into the development of important diseases. Sleep studies are usually carried out by specialists by means of polysomnography. Polysomnography is a type of sleep study which is consisting of EEG, EOG, EMG, ECG, respiratory signals and/or many other biosignals which together can be used to determine the state of patient’s sleep and any other issue. Nowadays, visual inspection of these signals forms the “gold standard” in sleep clinics. The cost of monitoring a person overnight, the scarcity of beds available and the uncertainty of whether the results are representative of a normal nights’ sleep means that a move to home diagnostics is likely to be advantageous. Therefore, a necessity for home recorders systems capable of perform this kind of analysis has come out. A state machine based automatic scorer is developed and evaluated in Matlab by using 12 recordings of apnoeic patients from sleep heart health study (SHHS) database. By the analysis of EEG, EOG, EMG, Oxygen saturation (Sao2) and respiratory movements signals, the implemented algorithm is trained and evaluated to detect the five stages of subject’s sleep (Wake, N1, N2, N3, or REM) as well as apnoeic episodes according to guidelines from American Academy of Sleep Medicine (AASM). In the final evaluation of algorithms, the automatic scorer achieved 74±5.27% accuracy for all five stages and Cohen’s kappa of 0.5 for the overall set of 12 patients, being the accuracy better for healthier subjects and reaching in this case 78±4.05%. The analysis of the sleep apnea concluded with a sensitivity of 47.08%, a specificity of 83.38%, and an accuracy of 78.1%. Differences in the performance among patients according to their apnea/hypopnea index were significant.   Key Words: Polysomnography, AASM, Sleep apnea/hypopnea.

Sleep is an important part of life as it affects the performance of one's activities during all awake hours. The study of sleep and wakefulness is therefore of great interest, particularly to the clinical and medical fields where sleep disorders are diagnosed. When studying sleep, it is common to talk about different types, or stages, of sleep. A common task in sleep research is to determine the sleep stage of the sleeping subject as a function of time. This process is known as sleep stage scoring. In this study, I seek to determine whether there is any benefit to using unsupervised feature learning in the context of electroencephalogram-based (EEG) sleep scoring. More specifically, the effect of generating and making use of new feature representations for hand-crafted features of sleep data – meta-features – is studied. For this purpose, two scoring algorithms have been implemented and compared. Both scoring algorithms involve segmentation of the EEG signal, feature extraction, feature selection and classification using a support vector machine (SVM). Unsupervised feature learning was implemented in the form of a dimensionality-reducing deep-belief network (DBN) which the feature space was processed through. Both scorers were shown to have a classification accuracy of about 76 %. The application of unsupervised feature learning did not affect the accuracy significantly. It is speculated that with a better choice of parameters for the DBN in a possible future work, the accuracy may improve significantly. / Sömnen är en viktig del av livet eftersom den påverkar ens prestation under alla vakna timmar. Forskning om sömn and vakenhet är därför av stort intresse, i synnerhet för de kliniska och medicinska områdena där sömnbesvär diagnostiseras. I forskning om sömn är det är vanligt att tala om olika typer av sömn, eller sömnstadium. En vanlig uppgift i sömnforskning är att avgöra sömnstadiet av den sovande exemplaret som en funktion av tiden. Den här processen kallas sömnmätning. I den här studien försöker jag avgöra om det finns någon fördel med att använda oövervakad inlärning av särdrag för att utföra elektroencephalogram-baserad (EEG) sömnmätning. Mer specifikt undersöker jag effekten av att generera och använda nya särdragsrepresentationer som härstammar från handgjorda särdrag av sömndata – meta-särdrag. Två sömnmätningsalgoritmer har implementerats och jämförts för det här syftet. Sömnmätningsalgoritmerna involverar segmentering av EEG-signalen, extraktion av särdragen, urval av särdrag och klassificering genom användning av en stödvektormaskin (SVM). Oövervakad inlärning av särdrag implementerades i form av ett dimensionskrympande djuptrosnätverk (DBN) som användes för att bearbetasärdragsrymden. Båda sömnmätarna visades ha en klassificeringsprecision av omkring 76 %. Användningen av oövervakad inlärning av särdrag hade ingen signifikant inverkan på precisionen. Det spekuleras att precisionen skulle kunna höjas med ett mer lämpligt val av parametrar för djuptrosnätverket.