Technical University of Ostrava

About: Technical University of Ostrava is a education organization based out in Ostrava, Czechia. It is known for research contribution in the topics: Artificial neural network & Evolutionary algorithm. The organization has 4186 authors who have published 8936 publications receiving 65393 citations. The organization is also known as: Vysoká škola báňská – Technická univerzita Ostrava & VŠB – Technical University of Ostrava.

Machine learning based electric load forecasting for short and long-term period

Abstract: Electricity is currently the most important energy vector in the domestic sector and industry. Unlike fuels, electricity is hard and expensive to store. This creates the need of precise coupling between generation and demand. In addition, the transmission lines of electric power need to be sized for a given maximum power, and overloading them may result in blackout or electrical accidents. For these reasons, energy consumption forecasting is vital. The time scale for forecasting depends on who is interested in such prediction. Grid operators have to predict the electricity demand for the next day, to program the generation accordingly. Grid designers have to predict energy consumption at the scale of years, to ensure that the infrastructure is sufficient. On the other hand, smart grid controllers with almost instant response time may need a prediction on the order of minutes. We have seen that changing the time scale in electricity load forecasting changes the approach, and that depending on the scale different methods should be used to ensure the highest accuracy with the smallest computational cost. We show here how forecasting accuracy decreases with the increase of time scale due to the impossibility of using of all variables. Several well established computational models were compared on three different regression based criteria and the results revealed that boosting model was able to outperform their competitors in most of the comparisons.

Cloud computing environments for biomedical data services

Abstract: The goal of the project we describe in this paper was the cloud computer environment establishment for biomedical data processing services using a security access. The relevant cloud application for user interactive interaction with biomedical data were realized on .NET Framework technology platform by the help of rapid calculating by FPGA technology. Interconnection of these technologies allows a large spectrum of users to quick access to pre-evaluated biomedical data. This article discusses the possible topological solutions and implementation of that system.

Complex Network Analysis of Evolutionary Algorithms Applied to Combinatorial Optimisation Problem

Abstract: This research analyses the development of a complex network in an evolutionary algorithm (EA). The main aim is to evaluate if a complex network is generated in an EA, and how the population can be evaluated when the objective is to optimise an NP-hard combinatorial optimisation problem. The population is evaluated as a complex network over a number of generations, and different attributes such as adjacency graph, minimal cut, degree centrality, closeness centrality, betweenness centrality, k-Clique, k-Club, k-Clan and community graph plots are analysed. From the results, it can be concluded that an EA population does behave like a complex network, and therefore can be analysed as such, in order to obtain information about population development.

The evolution of fuzzy classifier for data mining with applications

Abstract: Fuzzy classifiers and fuzzy rules can be informally defined as tools that use fuzzy sets or fuzzy logic for their operations. In this paper, we use genetic programming to evolve a fuzzy classifier in the form of a fuzzy search expression to predict product quality. We interpret the data mining task as a fuzzy information retrieval problem and we apply a successful information retrieval method for search query optimization to the fuzzy classifier evolution. We demonstrate the ability of the genetic programming to evolve useful fuzzy classifiers on two use cases in which we detect faulty products of a product processing plant and discover intrusions in a computer network.

A continuous double auction method for resource allocation in computational grids

Abstract: In this paper, we introduce a continuous double auction method for grid resource allocation in which resources are considered as provider agents and users as consumer agents. In each time step, each provider agent determines its requested value based on its workload and each consumer agent determines its bid value based on two constraints: the remaining time for bidding, and the remaining resources for bidding. We study this method in terms of economic efficiency and system performance. Experimental results show that the proposed method is better than Earliest Deadline First (EDF) method, which is a default strategy in many schedulers.