The paper presents results of machine learning approach accuracy applied analysis of cardiac activity. The study evaluates the diagnostics possibilities of the arterial hypertension by means of the short-term heart rate variability signals. Two groups were studied: 30 relatively healthy volunteers and 40 patients suffering from the arterial hypertension of II-III degree. The following machine learning approaches were studied: linear and quadratic discriminant analysis, k-nearest neighbors, support vector machine with radial basis, decision trees, and naive Bayes classifier. Moreover, in the study, different methods of feature extraction are analyzed: statistical, spectral, wavelet, and multifractal. All in all, 53 features were investigated. Investigation results show that discriminant analysis achieves the highest classification accuracy. The suggested approach of noncorrelated feature set search achieved higher results than data set based on the principal components.

In the paper possibilities of functional research complex for mental status evaluation are shown. The complex consists of neuroheadset Emotiv Epoc+, including 14 channel wireless EEG-system with accelerometer, and ECG-recorder for acquisition of the heart rate variability signals (HRV). The record of biomedical signals was obtained in several functional states for 10 healthy subjects: Background (functional rest), TOVA-test (mental load), Hyperventilation (physical load) and Aftereffect (after test state). It was found that the power of the very low-frequency component of the HRV spectrum was significantly changed, which is caused by influence of the suprasegmentally regulation level on the heart rhythm. Also, the decrease in the control effect of the cerebral cortex (α-rhythm activity) is registered. At the same time, the amplitude of the average accelerometer values increases as result of uncontrolled movements in order to find the most stable position of the head relative to the gravitational vector.