Zbigniew Szymański
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zbigniew Szymański has a total of 48 co-authors. Here are the top co-authors by number of shared publications:
Stanislaw Jankowski
Institute of Computer Science, Warsaw University of Technology, Warszawa, Poland
9 shared publicationsStanisław Jankowski
Warsaw University of Technology
8 shared publications- Artur Oręziak3 shared publications
- Ewa Piątkowska-Janko
Nalecz Institute of Biocybernetics and Biomedical Engineering PAS
3 shared publications A. Skorupski
2 shared publications- Jakub Wagner
Warsaw University of Technology
2 shared publications
Latest Publications
- 1 September 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Memristive CNN for trajectory recognition
The paper describes application of CNN with memristive units to simple movement recognition. Each cell of CNN comprised input and output template connected to voltage controlled memristor. The experimental results were obtained by using simulation software. The proposed model proved to be capable of recognizing simple pixel trajectories over a two-dimensional grid.
- 1 September 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Memristive CNN for trajectory recognition
The paper describes application of CNN with memristive units to simple movement recognition. Each cell of CNN comprised input and output template connected to voltage controlled memristor. The experimental results were obtained by using simulation software. The proposed model proved to be capable of recognizing simple pixel trajectories over a two-dimensional grid.
- 7 August 2017
- Published by SPIE-Intl Soc Optical Eng
- Vol. 10445, 104451I-104451I-11
Implementation of reversible gates in FPGA structure
- 7 August 2017
- Published by SPIE-Intl Soc Optical Eng
- Vol. 10445, 104451I-104451I-11
Implementation of reversible gates in FPGA structure
- 1 September 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 3745, 723-727
Deep learning classifier for fall detection based on IR distance sensor data
The goal of research is the fall detection in elderly residents based on infra red depth sensor measurements. Our attention is focused on statistical properties as generalization. The effectiveness of discriminative statistical classifiers (multilayer perceptron) is improved by addition of feature selection block by Gram-Schmidt orthogonalization, which determines the ranking of the features, and NPCA block, which transforms the raw data into a nonlinear manifold and reduces the dimensionality of the data. Performance of our system measured in terms of sensitivity is 92% and precision is 93%, which means it can be used for real life applications.
- 1 September 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 3745, 723-727
Deep learning classifier for fall detection based on IR distance sensor data
The goal of research is the fall detection in elderly residents based on infra red depth sensor measurements. Our attention is focused on statistical properties as generalization. The effectiveness of discriminative statistical classifiers (multilayer perceptron) is improved by addition of feature selection block by Gram-Schmidt orthogonalization, which determines the ranking of the features, and NPCA block, which transforms the raw data into a nonlinear manifold and reduces the dimensionality of the data. Performance of our system measured in terms of sensitivity is 92% and precision is 93%, which means it can be used for real life applications.
- 1 September 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 14, 728-732
Neural network classifier for fall detection improved by Gram-Schmidt variable selection
The paper describes results of research on the fall detection in elderly residents based on infra red depth sensor measurements. We present the methodology of data acquisition, preprocessing and the feature extraction. Multilayer perceptron is used for classification. In order to improve the classifier generalization feature selection block by Gram-Schmidt orthogonalization is added. It determines the ranking of the features and enables to reduce the dimensionality of the data. Performance of our system measured in terms of sensitivity is 92% and precision is 93%, which means it can be used for real life applications.
- 1 September 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 14, 728-732
Neural network classifier for fall detection improved by Gram-Schmidt variable selection
The paper describes results of research on the fall detection in elderly residents based on infra red depth sensor measurements. We present the methodology of data acquisition, preprocessing and the feature extraction. Multilayer perceptron is used for classification. In order to improve the classifier generalization feature selection block by Gram-Schmidt orthogonalization is added. It determines the ranking of the features and enables to reduce the dimensionality of the data. Performance of our system measured in terms of sensitivity is 92% and precision is 93%, which means it can be used for real life applications.
- 1 January 2014
- Published by Springer Nature in Communications in Computer and Information Science
- p. 147-158
Modeling Engineering-Geological Layers by k-nn and Neural Networks
- 1 January 2014
- Published by Springer Nature in Communications in Computer and Information Science
- p. 147-158
Modeling Engineering-Geological Layers by k-nn and Neural Networks
- 25 October 2013
- Published by SPIE-Intl Soc Optical Eng
- Vol. 8903, 89032S
Implementation aspects of Graph Neural Networks
This article summarises the results of implementation of a Graph Neural Network classi er. The Graph Neural Network model is a connectionist model, capable of processing various types of structured data, including non- positional and cyclic graphs. In order to operate correctly, the GNN model must implement a transition function being a contraction map, which is assured by imposing a penalty on model weights. This article presents research results concerning the impact of the penalty parameter on the model training process and the practical decisions that were made during the GNN implementation process.
- 25 October 2013
- Published by SPIE-Intl Soc Optical Eng
- Vol. 8903, 89032S
Implementation aspects of Graph Neural Networks
This article summarises the results of implementation of a Graph Neural Network classi er. The Graph Neural Network model is a connectionist model, capable of processing various types of structured data, including non- positional and cyclic graphs. In order to operate correctly, the GNN model must implement a transition function being a contraction map, which is assured by imposing a penalty on model weights. This article presents research results concerning the impact of the penalty parameter on the model training process and the practical decisions that were made during the GNN implementation process.
- 15 October 2012
- Published by SPIE-Intl Soc Optical Eng
- p. 845422-845422-8
Reconstruction of environment model by using radar vector field histograms
- 15 October 2012
- Published by SPIE-Intl Soc Optical Eng
- p. 845422-845422-8
Reconstruction of environment model by using radar vector field histograms
- 15 October 2012
- Published by SPIE-Intl Soc Optical Eng
- Vol. 8454, 84541W-84541W-7
Feature selection from short amino acid sequences in phosphorylation prediction problem
- 15 October 2012
- Published by SPIE-Intl Soc Optical Eng
- Vol. 8454, 84541W-84541W-7
Feature selection from short amino acid sequences in phosphorylation prediction problem
- 15 October 2012
- Published by SPIE-Intl Soc Optical Eng
- p. 84541U-84541U-10
Optimization of short amino acid sequences classifier
- 15 October 2012
- Published by SPIE-Intl Soc Optical Eng
- p. 84541U-84541U-10
Optimization of short amino acid sequences classifier
- 15 October 2012
- Published by SPIE-Intl Soc Optical Eng
- Vol. 8454, 845420
Environment model for unmanned flying vehicles based on simulated radar data
The main goal of AURA (Autonomous collision avoidance system for unmanned flying vehicles based on active teledetection method) project is to create an collision avoidance system (comparable to see-and-avoid requirements for manned aircraft) that can be used in unmanned aerial vehicles. For testing purposes there was necessity to develop simulation environment, which could be used to generate the data required for testing of collision avoidance algorithms. The program allows adjusting of the operating parameters of the simulated device to ensure optimal efficiency. It gives us the possibility of preparing such test cases which would be very difficult or even impossible to prepare when using real aircraft. This paper includes description of developed simulator and its graphical user interface.
- 15 October 2012
- Published by SPIE-Intl Soc Optical Eng
- Vol. 8454, 845420
Environment model for unmanned flying vehicles based on simulated radar data
The main goal of AURA (Autonomous collision avoidance system for unmanned flying vehicles based on active teledetection method) project is to create an collision avoidance system (comparable to see-and-avoid requirements for manned aircraft) that can be used in unmanned aerial vehicles. For testing purposes there was necessity to develop simulation environment, which could be used to generate the data required for testing of collision avoidance algorithms. The program allows adjusting of the operating parameters of the simulated device to ensure optimal efficiency. It gives us the possibility of preparing such test cases which would be very difficult or even impossible to prepare when using real aircraft. This paper includes description of developed simulator and its graphical user interface.