In this study we demonstrate the appropriate use of statistically based filtering methods for feature selection and describe the application to Heart Rate Variability (HRV) features used to distinguish between arrhythmia and normal sinus rhythm electrocardiogram (ECG) signals. The initial set of HRV features is evaluated using both correlation and statistical significance tests. Normality assumption is assessed for each feature in order to select appropriate correlation methods and significance tests. In addition, the impact of outliers on the statistical test results is illustrated by an explorative analysis of correlation before and after outlier removal. Finally, a reduced set of features is selected, and the decision process guided by correlation and statistical significance test results is described and discussed.

The paper evaluates statistical significance of the differences in the feature values necessary to differentiate the signals corresponding to cardiac arrhythmia (AR) and atrial fibrillation (AF). The initial set of heart rate variability (HRV) features includes time and frequency domain metrics, as well as geometric metrics based on the Poincare diagram. Due to non-uniformity of the heart rate signal, frequency domain features are calculated using two approaches: the Lomb-Scargle method for spectral analysis for non-uniform signals, and Welch method for uniform signals, but after the signal interpolation and resampling. Selection of an appropriate statistical test was depending on the distribution of feature values. Normal distribution allowed use of parametric ANOVA test and otherwise non-parametric Wilcoxon–Mann–Whitney test were used. The statistical tests indicated statistically significant difference between the two observed groups of signals of interest with respect to the evaluated feature. The success of the classification depends on the well-chosen features according to their importance. In the paper, statistical tests resulted in selection of 27 features out of the initial 51. The proposed set of features could be used for the classification between the AR and AF signals to assist diagnosis of the mentioned heart diseases.

Detection of atrial fibrillation (AF) presents one of the main tasks of modern cardiology. In the last few years, the deep learning (DL) emerges as the most frequent approach for accomplishing the task. When deciding to apply DL model for AF detection researchers are facing different choices bringing specific advantages but also imposing specific restrictions. The expansion of publishing, and advancements in this field, demand frequent review of the state of the art. The initial set of 370 papers filtered by keywords of interest, were systematically narrowed to 32 papers in focus. The objective of the paper is to present a comprehensive overview of commonly used ECG databases, signal preprocessing techniques, inputs formatting, DL models used, choice of output classes, and performance metrics achieved.

This paper analyzes the problem of DC cable selection in photovoltaic (PV) plants. PV plants can have tens of kilometres of one-way cables that are important parts of the system. The currents flowing through these cables can reach values of several hundred amps. Losses incurred on DC cables are up to 1%, which can be significant when measuring power loss during the operating period. Reduction of these losses can be achieved by increasing the cross-section of the cable. The paper describes the requirements set by the standards for selecting cable cross-sections. An analytical criterion function that connects electricity losses and cable crosssection were deduced. This function depends on several parameters such as electricity price, cable price, the average number of sunny hours per year, average amount of electricity through cable, interest rate, loan repayment period, and plant operation period. Several cases with the analysis of the obtained results are presented.

The application of spectral analysis methods to the heart rate (HR) signal is challenging due to the nature of the signal itself, which is non-uniform. Methods for non-uniform signals can be applied directly, whilst the methods designed for uniform signals can be used after the signal is adequately preprocessed beforehand. Preprocessing consists of interpolation and resampling. In this paper, we have implemented a tool for explorative evaluation of various spectral analysis methods applied to HR signal. The tool is based on heat maps used for visualization of frequency metrics for the ECG signals selected from the MIT-BIH Arrhythmia Database. Evaluated methods are the Lomb-Scargle method for nonuniform signal analysis and Welch's method which is applied in conjunction with different interpolation approaches. A set of frequency-domain metrics are evaluated with the proposed tool for exploratory analysis. The evaluation indicates that the Lomb-Scargle method produces a loss of information in certain frequency bands. Furthermore, Welch method better demonstrates the difference in spectral power metrics for frequency bands of interest, irrespective of the type of interpolation used.

Resistive pressure sensors has become popular and used in different applications. The usage of the pressure sensors in designing wearable solutions requests flexible and light materials. However, these materials are exhibiting challenging behavior in respect to precision, sensitivity and repeatability of measurement. In this paper we present a set of experiments demonstrating typical problems, and also we discuss the causes and possible remedies. The experiments were conducted with pressure sensors implemented using the VelostatTM material and Arduino platform for acquisition of the measurements.