Robert Szmurlo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Robert Szmurlo has a total of 31 co-authors. Here are the top co-authors by number of shared publications:
- Jacek Starzyński
Electrical Engineering Department, Warsaw University of Technology, 00-661 Warsaw, Poland
11 shared publications - Bartosz Sawicki
Warsaw University of Technology
4 shared publications Bartosz Chaber
Warsaw University of Technology, Koszykowa 75, 00-662 Warszawa, Poland
3 shared publicationsS. Wincenciak
3 shared publications- Zuzanna Krawczyk
Warsaw University of Technology, Koszykowa 75, 00-662 Warszawa, Poland
3 shared publications - Anna Zawadzka
Department of Medical Physics, Maria Sklodowska-Curie National Research Institute of Oncology, Warsaw, Poland
2 shared publications
Latest Publications
- Open Access
- 18 September 2024
- Published by Vilnius University Press in Informatica
- p. 99-124
Bi-Level Optimization to Enhance Intensity Modulated Radiation Therapy Planning
Intensity Modulated Radiation Therapy is an effective cancer treatment. Models based on the Generalized Equivalent Uniform Dose (gEUD) provide radiation plans with excellent planning target volume coverage and low radiation for organs at risk. However, manual adjustment of the parameters involved in gEUD is required to ensure that the plans meet patient-specific physical restrictions. This paper proposes a radiotherapy planning methodology based on bi-level optimization. We evaluated the proposed scheme in a real patient and compared the resulting irradiation plans with those prepared by clinical planners in hospital devices. The results in terms of efficiency and effectiveness are promising.
- 18 September 2024
- Published by Vilnius University Press in Informatica
- p. 99-124
Open AccessBi-Level Optimization to Enhance Intensity Modulated Radiation Therapy Planning
Intensity Modulated Radiation Therapy is an effective cancer treatment. Models based on the Generalized Equivalent Uniform Dose (gEUD) provide radiation plans with excellent planning target volume coverage and low radiation for organs at risk. However, manual adjustment of the parameters involved in gEUD is required to ensure that the plans meet patient-specific physical restrictions. This paper proposes a radiotherapy planning methodology based on bi-level optimization. We evaluated the proposed scheme in a real patient and compared the resulting irradiation plans with those prepared by clinical planners in hospital devices. The results in terms of efficiency and effectiveness are promising.
- Open Access
Bi-Level Optimization to Enhance Intensity Modulated Radiation Therapy Planning
Intensity Modulated Radiation Therapy is an effective cancer treatment. Models based on the Generalized Equivalent Uniform Dose (gEUD) provide radiation plans with excellent planning target volume coverage and low radiation for organs at risk. However, manual adjustment of the parameters involved in gEUD is required to ensure that the plans meet patient-specific physical restrictions. This paper proposes a radiotherapy planning methodology based on bi-level optimization. We evaluated the proposed scheme in a real patient and compared the resulting irradiation plans with those prepared by clinical planners in hospital devices. The results in terms of efficiency and effectiveness are promising.
Open AccessBi-Level Optimization to Enhance Intensity Modulated Radiation Therapy Planning
Intensity Modulated Radiation Therapy is an effective cancer treatment. Models based on the Generalized Equivalent Uniform Dose (gEUD) provide radiation plans with excellent planning target volume coverage and low radiation for organs at risk. However, manual adjustment of the parameters involved in gEUD is required to ensure that the plans meet patient-specific physical restrictions. This paper proposes a radiotherapy planning methodology based on bi-level optimization. We evaluated the proposed scheme in a real patient and compared the resulting irradiation plans with those prepared by clinical planners in hospital devices. The results in terms of efficiency and effectiveness are promising.
- Open Access
- 17 May 2022
- Published by Polish Academy of Sciences Chancellery in Bulletin Of The Polish Academy Of Sciences-Technical Sciences
- Vol. 70 (3) , 141004
Ensemble of classifiers based on CNN for increasing generalization ability in face image recognition
The paper considers the problem of increasing the generalization ability of classification systems by creating an ensemble of classifiers based on the CNN architecture. Different structures of the ensemble will be considered and compared. Deep learning fulfills an important role in the developed system. The numerical descriptors created in the last locally connected convolution layer of CNN flattened to the form of a vector, are subjected to a few different selection mechanisms. Each of them chooses the independent set of features, selected according to the applied assessment techniques. Their results are combined with three classifiers: softmax, support vector machine, and random forest of the decision tree. All of them do simultaneously the same classification task. Their results are integrated into the final verdict of the ensemble. Different forms of arrangement of the ensemble are considered and tested on the recognition of facial images. Two different databases are used in experiments. One was composed of 68 classes of greyscale images and the second of 276 classes of color images. The results of experiments have shown high improvement of class recognition resulting from the application of the properly designed ensemble.
- 17 May 2022
- Published by Polish Academy of Sciences Chancellery in Bulletin Of The Polish Academy Of Sciences-Technical Sciences
- Vol. 70 (3) , 141004
Open AccessEnsemble of classifiers based on CNN for increasing generalization ability in face image recognition
The paper considers the problem of increasing the generalization ability of classification systems by creating an ensemble of classifiers based on the CNN architecture. Different structures of the ensemble will be considered and compared. Deep learning fulfills an important role in the developed system. The numerical descriptors created in the last locally connected convolution layer of CNN flattened to the form of a vector, are subjected to a few different selection mechanisms. Each of them chooses the independent set of features, selected according to the applied assessment techniques. Their results are combined with three classifiers: softmax, support vector machine, and random forest of the decision tree. All of them do simultaneously the same classification task. Their results are integrated into the final verdict of the ensemble. Different forms of arrangement of the ensemble are considered and tested on the recognition of facial images. Two different databases are used in experiments. One was composed of 68 classes of greyscale images and the second of 276 classes of color images. The results of experiments have shown high improvement of class recognition resulting from the application of the properly designed ensemble.
- Open Access
Neural Approaches to Short-Time Load Forecasting in Power Systems—A Comparative Study
Background: The purpose of the paper is to propose different arrangements of neural networks for short-time 24-h load forecasting in Power Systems. Methods: The study discusses and compares different techniques of data processing, applying the feedforward and recurrent neural structures. They include such networks as multilayer perceptron, radial basis function, support vector machine, self-organizing Kohonen networks, deep autoencoder, and recurrent deep LSTM structures. The important point in getting high-quality results is the composition of many solutions in the common ensemble and their fusion to create the final forecast of time series. The paper considers and compares different methods of fusing the individual results into the final forecast, including the averaging, application of independent component analysis, dynamic integration, and wavelet transformation. Results: The numerical experiments have shown a high advantage of using many individual predictors integrated into the ensemble which are responsible for the final forecast. Especially efficient is the application of non-standard wavelet application in the formation of an ensemble, as well as the use of LSTM as the basic prediction unit. The novelty of the paper is the critical comparative analysis of the time series prediction methods applied for load forecasting in the power system. The presented approach may be useful for the users involved in power system operation management.
Open AccessNeural Approaches to Short-Time Load Forecasting in Power Systems—A Comparative Study
Background: The purpose of the paper is to propose different arrangements of neural networks for short-time 24-h load forecasting in Power Systems. Methods: The study discusses and compares different techniques of data processing, applying the feedforward and recurrent neural structures. They include such networks as multilayer perceptron, radial basis function, support vector machine, self-organizing Kohonen networks, deep autoencoder, and recurrent deep LSTM structures. The important point in getting high-quality results is the composition of many solutions in the common ensemble and their fusion to create the final forecast of time series. The paper considers and compares different methods of fusing the individual results into the final forecast, including the averaging, application of independent component analysis, dynamic integration, and wavelet transformation. Results: The numerical experiments have shown a high advantage of using many individual predictors integrated into the ensemble which are responsible for the final forecast. Especially efficient is the application of non-standard wavelet application in the formation of an ensemble, as well as the use of LSTM as the basic prediction unit. The novelty of the paper is the critical comparative analysis of the time series prediction methods applied for load forecasting in the power system. The presented approach may be useful for the users involved in power system operation management.
- 23 September 2017
- Published by Springer Nature
- p. 395-412
A Method of Design and Optimization for SiC-Based Grid-Connected AC-DC Converters
- 23 September 2017
- Published by Springer Nature
- p. 395-412
A Method of Design and Optimization for SiC-Based Grid-Connected AC-DC Converters
- Open Access
- 1 December 2016
- Published by Walter de Gruyter GmbH in Bulletin Of The Polish Academy Of Sciences-Technical Sciences
- Vol. 64 (4) , 897-905
Dedicated system for design, analysis and optimization of AC-DC converters
This paper presents an originally-developed system for design and optimization of AC-DC converters dedicated in particular to operation in distributed generation systems. The proposed procedure is based on a multi-objective discrete optimization and expert knowledge of electrical engineering, especially power electronics. The required accuracy of calculations is obtained by using the database with real components, while the parameters applied in calculations are based on parameters provided by the manufacturer. The paper presents the foundations and basic system properties, the design and optimization process, and selected optimization results, obtained with a fully functional prototype of the design and optimization system (DaOS).
- 1 December 2016
- Published by Walter de Gruyter GmbH in Bulletin Of The Polish Academy Of Sciences-Technical Sciences
- Vol. 64 (4) , 897-905
Open AccessDedicated system for design, analysis and optimization of AC-DC converters
This paper presents an originally-developed system for design and optimization of AC-DC converters dedicated in particular to operation in distributed generation systems. The proposed procedure is based on a multi-objective discrete optimization and expert knowledge of electrical engineering, especially power electronics. The required accuracy of calculations is obtained by using the database with real components, while the parameters applied in calculations are based on parameters provided by the manufacturer. The paper presents the foundations and basic system properties, the design and optimization process, and selected optimization results, obtained with a fully functional prototype of the design and optimization system (DaOS).
- 10 November 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Computer simulation as a way of usable volume estimation in TEM waveguides
Striplines are common waveguides used for susceptibility tests. Standards as 61000-4-20 describe procedures for finding volumes with a uniform, strong electric field, but only for frequencies below the first cut-off frequency of the stripline. For higher frequencies modes other than TEM start to propagate and an analytical determination of the field between a stripline's plates is hard or even impossible (i.e. for non-homogenous interior of the stripline). The solution of electric field in a stripline could be found by means of a numerical approximation (e. g. using Finite Element Method) of Helmholtz equation. In this paper such a numerical simulation is presented. The numerical model is verified against the measurements in the frequency range above the first cut-off frequency of a stripline. On the basis of numerical simulation an electric field is determined in the stripline and a usable volume for an extended frequency range is estimated. Such a numerical simulation can be used to take into account also large metallic objects in the vicinity of the stripline.
- 10 November 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Computer simulation as a way of usable volume estimation in TEM waveguides
Striplines are common waveguides used for susceptibility tests. Standards as 61000-4-20 describe procedures for finding volumes with a uniform, strong electric field, but only for frequencies below the first cut-off frequency of the stripline. For higher frequencies modes other than TEM start to propagate and an analytical determination of the field between a stripline's plates is hard or even impossible (i.e. for non-homogenous interior of the stripline). The solution of electric field in a stripline could be found by means of a numerical approximation (e. g. using Finite Element Method) of Helmholtz equation. In this paper such a numerical simulation is presented. The numerical model is verified against the measurements in the frequency range above the first cut-off frequency of a stripline. On the basis of numerical simulation an electric field is determined in the stripline and a usable volume for an extended frequency range is estimated. Such a numerical simulation can be used to take into account also large metallic objects in the vicinity of the stripline.
- 10 November 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Accuracy of numerical model of coaxial impulse voltage divider validated with measurements
The paper presents a numerical model and measurements of the high voltage impulse voltage coaxial divider. The numerical simulation are obtained both for two and three dimensional models in COMSOL Multiphysics. The paper discusses the accuracy of an electrostatic numerical model and compares the results with measurements. Numerical experiments are calculated to analyse the precision of assembly of an in-house manufactured voltage divider. Both uncertainty of the simulations due to electric permittivity and precision of the mechanical realisation of the divider are analysed.
- 10 November 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Accuracy of numerical model of coaxial impulse voltage divider validated with measurements
The paper presents a numerical model and measurements of the high voltage impulse voltage coaxial divider. The numerical simulation are obtained both for two and three dimensional models in COMSOL Multiphysics. The paper discusses the accuracy of an electrostatic numerical model and compares the results with measurements. Numerical experiments are calculated to analyse the precision of assembly of an in-house manufactured voltage divider. Both uncertainty of the simulations due to electric permittivity and precision of the mechanical realisation of the divider are analysed.
- 1 September 2015
- Published by Elsevier in Applied Mathematics and Computation
- Vol. 267, 655-663
Morphing algorithm for building individualized 3D skeleton model from CT data
- 1 September 2015
- Published by Elsevier in Applied Mathematics and Computation
- Vol. 267, 655-663
Morphing algorithm for building individualized 3D skeleton model from CT data
- 1 September 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 204-206
Open access system for radiotherapy planning
The recent trends in software development transform classical desktop-based programs into distributed systems offered over the Internet. The authors adapt this approach to the radiotherapy planning software. A general concept and necessary components of such a system are presented.
- 1 September 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 204-206
Open access system for radiotherapy planning
The recent trends in software development transform classical desktop-based programs into distributed systems offered over the Internet. The authors adapt this approach to the radiotherapy planning software. A general concept and necessary components of such a system are presented.