Sleep is not just a passive process, but rather a highly dynamic process that is terminated by waking up. Throughout the night a specific number of sleep stages that are repeatedly changing in various periods of time take place. These specific time intervals and specific sleep stages are very important for the wake up event. It is far more difficult to wake up during the deep NREM (2–4) stage of sleep because the rest of the body is still sleeping. On the other hand if we wake up during the mild (REM, NREM1) sleep stage it is a much more pleasant experience for us and for our bodies. This problem led the authors to undertake this study and develop a Windows Mobile-based device application called wakeNsmile. The wakeNsmile application records and monitors the sleep stages for specific amounts of time before a desired alarm time set by users. It uses a built-in microphone and determines the optimal time to wake the user up. Hence, if the user sets an alarm in wakeNsmile to 7:00 and wakeNsmile detects that a more appropriate time to wake up (REM stage) is at 6:50, the alarm will start at 6:50. The current availability and low price of mobile devices is yet another reason to use and develop such an application that will hopefully help someone to wakeNsmile in the morning. So far, the wakeNsmile application has been tested on four individuals introduced in the final section.

This paper deals with the clustering of metabolism typology based on the energometry tests analysis. Three patients' data sources are used in this work. Large data set of respi ratory quotient measurements and calculated food utilization indicators are used for analysis, along with the data obtained by the biochemical analysis of blood and insulin tests. Lastly, data set comprising bioimpedance measurements and patients' description is utilized. The fuzzy statistical method, Principal component analysis and standard data normalization methods are applied in this paper. The results are subsequently tested and medically evaluated and new research methods are described in conclusion.

ObjectiveThe most important part of signal processing for classification is feature extraction as a mapping from original input electroencephalographic (EEG) data space to new features space with the biggest class separability value. Features are not only the most important, but also the most difficult task from the classification process as they define input data and classification quality. An ideal set of features would make the classification problem trivial. This article presents novel methods of feature extraction processing and automatic epilepsy seizure classification combining machine learning methods with genetic evolution algorithms.MethodsClassification is performed on EEG data that represent electric brain activity. At first, the signal is preprocessed with digital filtration and adaptive segmentation using fractal dimensions as the only segmentation measure. In the next step, a novel method using genetic programming (GP) combined with support vector machine (SVM) confusion matrix as fitness function weight is used to extract feature vectors compressed into lower dimension space and classify the final result into ictal or interictal epochs.ResultsThe final application of GP–SVM method improves the discriminatory performance of a classifier by reducing feature dimensionality at the same time. Members of the GP tree structure represent the features themselves and their number is automatically decided by the compression function introduced in this paper. This novel method improves the overall performance of the SVM classification by dramatically reducing the size of input feature vector.ConclusionAccording to results, the accuracy of this algorithm is very high and comparable, or even superior to other automatic detection algorithms. In combination with the great efficiency, this algorithm can be used in real-time epilepsy detection applications. From the results of the algorithm’s classification, we can observe high sensitivity, specificity results, except for the Generalized Tonic Clonic Seizure (GTCS). As the next step, the optimization of the compression stage and final SVM evaluation stage is in place. More data need to be obtained on GTCS to improve the overall classification score for GTCS.

No abstract

No abstract