Vol. 24, No. 2


Recent Submissions

Now showing 1 - 5 of 12
  • Item
    Particle Swarm Optimization with Distance Based Repulsivity
    (Institute of Automation and Computer Science, Brno University of Technology, 2018-12-21) Pluhacek, Michal; Zelinka, Ivan; Senkerik, Roman; Viktorin, Adam; Kadavy, Tomas
    In this study, we propose a repulsive mechanism for the Particle Swarm Optimization algorithm that improves its performance on multi-modal problems. The repulsive mechanism is further extended with a distance-based modification. The results are presented and tested for statistical significance. We discuss the observations and propose further directions for the research.
  • Item
    The Possibility of Interference Suppression by Correlation Receiver Applied to Marker Localization
    (Institute of Automation and Computer Science, Brno University of Technology, 2018-12-21) Vestenicky, Peter; Vestenicky, Martin
    The actual applications of the radiofrequency identification (RFID) systems in industry are focused not only on the identification but also on the localization of the RFID transponders. The special type of the RFID transponders is used to localize and to identify the underground facility networks such as pipes and cables. In such applications the RFID transponders are called markers. The paper describes an analysis of the correlation receiver for RSSI based localization of the inductive coupled RFID markers. The analysis is performed by the modeling of the localization device and the marker in Matlab – Simulink software. The aim of the analysis is to examine the ability of the correlation receiver to suppress the interfering signals from industrial sources, for example from the long wave telemetry transmitters which have their working frequencies in the same band as the working frequencies of the markers.
  • Item
    Influence of Experiment Design in GPA Investigating with Respect to PRNGs
    (Institute of Automation and Computer Science, Brno University of Technology, 2018-12-21) Brandejsky, Tomas
    This paper analyses the influence of experiment parameters onto the reliability of experiments with genetic programming algorithms. The paper is focused on the required number of experiments and especially on the influence of parallel execution which affect not only the order of thread execution but also behaviors of pseudo random number generators, which frequently do not respect recommendation of C++11 standard and are not implemented as thread safe. The observations and the effect of the suggested improvements are demonstrated on results of 720,000 experiments.
  • Item
    Fire Detection in Video Stream by Using Simple Artificial Neural Network
    (Institute of Automation and Computer Science, Brno University of Technology, 2018-12-21) Janku, Peter; Kominkova Oplatkova, Zuzana; Dulik, Tomas; Snopek, Petr; Liba, Jiri
    This paper deals with the preliminary research of the fire detection in a video stream. Early fire detection can save lives and properties from huge losses and damages. Therefore the surveillance of the areas is necessary. Early fire discovery with high accuracy, i.e. a low number of false positive or false negative cases, is essential in any environment, especially in places with the high motion of people. The traditional fire detection sensors have some drawbacks: they need separate systems and infrastructure to be implemented, to use sensors in the case of the industrial environment with open fire technologies is often impossible, and others. The fire detection in a video stream is one of the possible and feasible solutions suitable for replacement or supplement of conventional fire detection sensors without a need for installation a huge infrastructure. The paper provides the state of the art in the fire detection. The following part of the paper proposes the new system of feature extraction and describes the feedforward neural network which was used for the training and testing of the proposed idea. The promising results are presented with over 93% accuracy on a selected dataset of movies which consist of more and highly varied instances than published by other researchers involved in the fire detection field. The structure of the neural networks promises higher computational speed than currently implemented deep learning systems.
  • Item
    Using Artificial Intelligence to Determine the Type of Rotary Machine Fault
    (Institute of Automation and Computer Science, Brno University of Technology, 2018-12-21) Zuth, Daniel; Marada, Tomas
    The article deals with the possibility of using machine learning in vibrodiagnostics to determine the type of fault of rotating machine. The data source is real measured data from the vibrodiagnostic model. This model allows simulation of some types of faults. The data is then processed and reduced for the use of the Matlab Classication learner app, which creates a model for recognizing faults. The model is ultimately tested on new samples of data. The aim of the article is to verify the ability to recognize similarly rotary machine faults from real measurements in the time domain.