This paper addresses the processing of speech data and their utilization in a decision support system. The main aim of this work is to utilize machine learning methods to recognize pathological speech, particularly dysphonia. We extracted 1560 speech features and used these to train the classification model. As classifiers, three state-of-the-art methods were used: K-nearest neighbors, random forests, and support vector machine. We analyzed the performance of classifiers with and without gender taken into account. The experimental results showed that it is possible to recognize pathological speech with as high as a 91.3% classification accuracy.

Intrusion detection is enormously developing field of informatics. This paper provides a survey of actual trends in intrusion detection in academic research. It presents a review about the evolution of intrusion detection systems with usage of general purpose computing on graphics processing units (GPGPU). There are many detection techniques but only some of them bring advantages of parallel computing implementation to graphical processors (GPU). The most common technique transformed into GPU is the technique of pattern matching. There is a number of intrusion detection tools using GPU tested in real network traffic.

In the present security is an important factor of the network protection. Not only intrusion detection system but also intrusion prevention systems are created in order to the system failure due to a deliberate harm or a system intrusion is not occurred. The article deals with an analysis of the intrusion detection systems. The main goal is to point out an advantages and disadvantages of these systems and provide the overview of the possibilities which these systems offer. The article asset is the possibility to implement such a system to the network in its separate levels of the ISO/OSI layered model on the Department of Computers and Informatics of the Faculty of Electrotechnical Engineering and Informatics of the Technical University of Kosice. The main asset should be the network protection by using intrusion detection systems