Search

This paper focuses on various possible applications of the GNU General Public License free software functionality. During the lockdown, end users are granted the freedom of studying at home using this license. Our efforts are focused on the use of GNU Octave. This software is a high-level programming language, primarily intended for numerical computations. Octave is suitable for illustrating basic linear and nonlinear problems that occur in telecommunications and are studied on the “Signals and Systems” course. Octave is a good alternative of the most used commercial software in this area, like MA TLAB and Mathematika. Specific features have been considered in the design of exercises. The methodology of exercises for students is described in this paper

This article describes the design and implementation of an Embedded Interactive Timing System. Such systems are used in the therapy of children who have learning problems. The matching of different beats can help the brain work more efficiently. A methodology and architecture of an interactive timing is proposed. Open-source software environment and microcontroller is used for the practical realization of the system. Some results of the program functioning are shown.

This paper presents an approach for automated estimation of human emotions from electroencephalogram data. The used features are principally the Hjorth parameters calculated for theta, alpha, beta and gamma bands taken from certain channels. The classification stage is support vector machine. Since the human emotions are modelled as combinations from physiological elements such as arousal, valence, dominance, liking, etc., these quantities are the classifier's outputs. The best achieved correct classification performance is about 80%.

This paper presents an approach for automated staging of the human sleep. It is based on analysis of two channel electroencephalogram and an electrooculogram. The classifier is trained with two different groups of features separately and in combination as well. Statistic measures of first and higher order serve as features from the first set. The rules of Rechtschaffen and Kales are exploited for extraction of the second group of features. The contextual classifier for the sleep staging combines Support Vector Machine with Hidden Markov Model. This approach is verified and evaluated with an expert annotated database of biomedical signals and the overall accuracy is over 90%.

Capturing the type of physical activity a person is performing thorough his daily life, can inspire the development of new and innovative applications. Examples include monitoring patients' health and physical activity performance, reasoning upon the observed activity to recommend better training strategy, new therapeutic programs, etc. In this work we propose an algorithm for Human Activity Recognition based on the application of a geometrically motivated feature selection method. We test the algorithm on a standard data set and validate its performance by comparing it with the existing results of other known algorithms.

In this paper an approach for personal biometric identification is presented based on extraction of ECG features and classification with RBFNN. We perform denoising and segmentation on the input signal, after which we realize dimensionality reduction and feature extraction based on PCA transform. The separability of the selected features is improved by applying LDA. The final stage of the proposed approach is classification and recognition of the extracted features with classifier score fusion.