Jiří Pospíchal

Prof. Dr. Jiří Pospíchal

University of Ss. Cyril and Methodius in Trnava, Trnava, Trnavský, Slovakia
orcid

Research Focus & Metrics

Academic Career Length

38Years (1989-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 November 1997 in Chemometrics and Intelligent Laboratory Systems
Verified
Journal Article
Closed access
DSDaniel Svozil
Daniel Svozil
VKVladimír Kvasnicka
Vladimír Kvasnicka
JPJiří Pospíchal
Jiří Pospíchal

1 March 2022 in Sensors
Verified
Journal Article
Open access
PDF file
ILIveta Dirgová Luptáková
Iveta Dirgová Luptáková
MKMartin Kubovčík
Martin Kubovčík
JPJiří Pospíchal
Jiří Pospíchal
Computing devices that can recognize various human activities or movements can be used to assist people in healthcare, sports, or human–robot interaction. Readily available data for this purpose can be obtained from the accelerometer and the gyroscope built into everyday smartphones. Effective classification of real-time activity data is, therefore, actively pursued using various machine learning methods. In this study, the transformer model, a deep learning neural network model developed primarily for the natural language processing and vision tasks, was adapted for a time-series analysis of motion signals. The self-attention mechanism inherent in the transformer, which expresses individual dependencies between signal values within a time series, can match the performance of state-of-the-art convolutional neural networks with long short-term memory. The performance of the proposed adapted transformer method was tested on the largest available public dataset of smartphone motion sensor data covering a wide range of activities, and obtained an average identification accuracy of 99.2% as compared with 89.67% achieved on the same data by a conventional machine learning method. The results suggest the expected future relevance of the transformer model for human activity recognition.

2 September 2022 in Applied Sciences
Verified
Journal Article
Open access
PDF file
JPJiří Pospíchal
Jiří Pospíchal
MKMartin Kubovčík
Martin Kubovčík
ILIveta Dirgová Luptáková
Iveta Dirgová Luptáková
Solar energy is one of the most popular sources of renewable energy today. It is therefore essential to be able to predict solar power generation and adapt energy needs to these predictions. This paper uses the Transformer deep neural network model, in which the attention mechanism is typically applied in NLP or vision problems. Here, it is extended by combining features based on their spatiotemporal properties in solar irradiance prediction. The results were predicted for arbitrary long-time horizons since the prediction is always 1 day ahead, which can be included at the end along the timestep axis of the input data and the first timestep representing the oldest timestep removed. A maximum worst-case mean absolute percentage error of 3.45% for the one-day-ahead prediction was obtained, which gave better results than the directly competing methods.

1 November 1992 in Journal of Chemical Information and Computer Sciences
Verified
Journal Article
Closed access
VKVladimir Kvasnicka
Vladimir Kvasnicka
SSStepan Sklenak
Stepan Sklenak
JPJiří Pospíchal
Jiří Pospíchal

9 August 2019 in Applied Sciences
Verified
Journal Article
Open access
PDF file
MŠMarek Šimon
Marek Šimon
Ladislav HurajLadislav Huraj
Ladislav Huraj
ILIveta Dirgová Luptáková
Iveta Dirgová Luptáková
JPJiří Pospíchal
Jiří Pospíchal
This paper provides heuristic methods for obtaining a burning number, which is a graph parameter measuring the speed of the spread of alarm, information, or contagion. For discrete time steps, the heuristics determine which nodes (centers, hubs, vertices, users) should be alarmed (in other words, burned) and in which order, when afterwards each alarmed node alarms its neighbors in the network at the next time step. The goal is to minimize the number of discrete time steps (i.e., time) it takes for the alarm to reach the entire network, so that all the nodes in the networks are alarmed. The burning number is the minimum number of time steps (i.e., number of centers in a time sequence alarmed “from outside”) the process must take. Since the problem is NP complete, its solution for larger networks or graphs has to use heuristics. The heuristics proposed here were tested on a wide range of networks. The complexity of the heuristics ranges in correspondence to the quality of their solution, but all the proposed methods provided a significantly better solution than the competing heuristic.

1 September 1995 in Journal of Chemical Information and Computer Sciences
Verified
Journal Article
Closed access
DSDaniel Svozil
Daniel Svozil
JPJiří Pospíchal
Jiří Pospíchal
VKVladimir Kvasnicka
Vladimir Kvasnicka