Jacek Leski
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Jacek Leski has a total of 61 co-authors. Here are the top co-authors by number of shared publications:
- Michal Jezewski
Department of Cybernetics, Nanotechnology and Data Processing, Silesian University of Technology, PL44100 Gliwice, Poland
18 shared publications - Robert Czabanski
Department of Cybernetics, Nanotechnology and Data Processing, Silesian University of Technology, PL44100 Gliwice, Poland
11 shared publications - Marian Kotas
Silesian University of Technology
10 shared publications T. Petelenz
8 shared publicationsZ. Czyz
8 shared publicationsN. Henzel
7 shared publications
Latest Publications
- Open Access
- 22 April 2024
- Published by Taylor & Francis
- p. 359-388
A Neuro-Fuzzy System Based on Logical Interpretation of If-Then Rules
Initially, an axiomatic approach to the definition of fuzzy implication has been recalled in this chapter. Based on this definition several important fuzzy implications and their properties have been described. Then, the idea of approximate reasoning using generalized modus ponens and fuzzy implication is considered. The elimination of the non-informative part of a final fuzzy set before defuzzification plays the key role in this chapter. After reviewing well-known fuzzy systems, a new artificial neural network based on logical interpretation of if-then rules (ANBLIR) is introduced. Another novelty incorporated in the system is the moving fuzzy consequent in if-then rules. The location of this fuzzy set is determined by a linear combination of system inputs. Moreover, this system automatically generates rules from numerical data. The proposed system operates with Gaussian membership functions in thepremise part and triangular in the consequence part. Parameter estimation has been made by combination of both gradient and least squares methods. For initialization of unknown parameter values of premises, a preliminary fuzzy c-means clustering method has been employed. The applications of ANBLIR to pattern recognition on numerical examples using benchmark databases (FORENSIC GLASS, IRIS, WINE and MONKS) are shown.
- 22 April 2024
- Published by Taylor & Francis
- p. 359-388
Open AccessA Neuro-Fuzzy System Based on Logical Interpretation of If-Then Rules
Initially, an axiomatic approach to the definition of fuzzy implication has been recalled in this chapter. Based on this definition several important fuzzy implications and their properties have been described. Then, the idea of approximate reasoning using generalized modus ponens and fuzzy implication is considered. The elimination of the non-informative part of a final fuzzy set before defuzzification plays the key role in this chapter. After reviewing well-known fuzzy systems, a new artificial neural network based on logical interpretation of if-then rules (ANBLIR) is introduced. Another novelty incorporated in the system is the moving fuzzy consequent in if-then rules. The location of this fuzzy set is determined by a linear combination of system inputs. Moreover, this system automatically generates rules from numerical data. The proposed system operates with Gaussian membership functions in thepremise part and triangular in the consequence part. Parameter estimation has been made by combination of both gradient and least squares methods. For initialization of unknown parameter values of premises, a preliminary fuzzy c-means clustering method has been employed. The applications of ANBLIR to pattern recognition on numerical examples using benchmark databases (FORENSIC GLASS, IRIS, WINE and MONKS) are shown.
- Open Access
- 22 September 2023
- Published by Elsevier in Information Sciences
- Vol. 651
OWA-based robust fuzzy clustering of time series with typicality degrees
- 22 September 2023
- Published by Elsevier in Information Sciences
- Vol. 651
Open AccessOWA-based robust fuzzy clustering of time series with typicality degrees
- 20 April 2023
- Published by Elsevier in Fuzzy Sets and Systems
- Vol. 465
Fuzzy double-ordered c-regression models based on fuzzy S-estimators
- 20 April 2023
- Published by Elsevier in Fuzzy Sets and Systems
- Vol. 465
Fuzzy double-ordered c-regression models based on fuzzy S-estimators
- 2 March 2021
- Published by SAGE Publications in Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology
- Vol. 40 (3) , 4617-4636
Practical aspects of equivalence of Baldwin’s and Zadeh’s fuzzy inference
The article presents a thorough analysis of fuzzy inference introduced by Baldwin and compares this approach to Zaheh’s compositional rule of inference. The comparison is performed in order to analyze the equivalence of the two methods and describe practical aspects of this fact for simple and compound premises, indicating advantages and disadvantages of both approaches. The main aim of the analysis is focus on the computational complexity of the methods. The most important feature of Baldwin’s inference is transfer of the inference process into a truth space, unified for all input variables. Such environment allows to obtain one fuzzy truth value describing a compound premise in a sequence of low dimensional computations. The article proves equality of such approach with the compositional rule of inference. Therefore, this solution is much more computationally efficient in case of compound cases, for which compositional rule of inference is multidimensional.
- 2 March 2021
- Published by SAGE Publications in Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology
- Vol. 40 (3) , 4617-4636
Practical aspects of equivalence of Baldwin’s and Zadeh’s fuzzy inference
The article presents a thorough analysis of fuzzy inference introduced by Baldwin and compares this approach to Zaheh’s compositional rule of inference. The comparison is performed in order to analyze the equivalence of the two methods and describe practical aspects of this fact for simple and compound premises, indicating advantages and disadvantages of both approaches. The main aim of the analysis is focus on the computational complexity of the methods. The most important feature of Baldwin’s inference is transfer of the inference process into a truth space, unified for all input variables. Such environment allows to obtain one fuzzy truth value describing a compound premise in a sequence of low dimensional computations. The article proves equality of such approach with the compositional rule of inference. Therefore, this solution is much more computationally efficient in case of compound cases, for which compositional rule of inference is multidimensional.
- Open Access
Detection of Atrial Fibrillation Episodes in Long-Term Heart Rhythm Signals Using a Support Vector Machine
Atrial fibrillation (AF) is a serious heart arrhythmia leading to a significant increase of the risk for occurrence of ischemic stroke. Clinically, the AF episode is recognized in an electrocardiogram. However, detection of asymptomatic AF, which requires a long-term monitoring, is more efficient when based on irregularity of beat-to-beat intervals estimated by the heart rate (HR) features. Automated classification of heartbeats into AF and non-AF by means of the Lagrangian Support Vector Machine has been proposed. The classifier input vector consisted of sixteen features, including four coefficients very sensitive to beat-to-beat heart changes, taken from the fetal heart rate analysis in perinatal medicine. Effectiveness of the proposed classifier has been verified on the MIT-BIH Atrial Fibrillation Database. Designing of the LSVM classifier using very large number of feature vectors requires extreme computational efforts. Therefore, an original approach has been proposed to determine a training set of the smallest possible size that still would guarantee a high quality of AF detection. It enables to obtain satisfactory results using only 1.39% of all heartbeats as the training data. Post-processing stage based on aggregation of classified heartbeats into AF episodes has been applied to provide more reliable information on patient risk. Results obtained during the testing phase showed the sensitivity of 98.94%, positive predictive value of 98.39%, and classification accuracy of 98.86%.
Open AccessDetection of Atrial Fibrillation Episodes in Long-Term Heart Rhythm Signals Using a Support Vector Machine
Atrial fibrillation (AF) is a serious heart arrhythmia leading to a significant increase of the risk for occurrence of ischemic stroke. Clinically, the AF episode is recognized in an electrocardiogram. However, detection of asymptomatic AF, which requires a long-term monitoring, is more efficient when based on irregularity of beat-to-beat intervals estimated by the heart rate (HR) features. Automated classification of heartbeats into AF and non-AF by means of the Lagrangian Support Vector Machine has been proposed. The classifier input vector consisted of sixteen features, including four coefficients very sensitive to beat-to-beat heart changes, taken from the fetal heart rate analysis in perinatal medicine. Effectiveness of the proposed classifier has been verified on the MIT-BIH Atrial Fibrillation Database. Designing of the LSVM classifier using very large number of feature vectors requires extreme computational efforts. Therefore, an original approach has been proposed to determine a training set of the smallest possible size that still would guarantee a high quality of AF detection. It enables to obtain satisfactory results using only 1.39% of all heartbeats as the training data. Post-processing stage based on aggregation of classified heartbeats into AF episodes has been applied to provide more reliable information on patient risk. Results obtained during the testing phase showed the sensitivity of 98.94%, positive predictive value of 98.39%, and classification accuracy of 98.86%.
- Open Access
- 9 October 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Fuzzy Systems
- Vol. 28 (11) , 2799-2813
Fuzzy Ordered $c$-Means Clustering and Least Angle Regression for Fuzzy Rule-Based Classifier: Study for Imbalanced Data
This article introduces a new classifier design method that is based on a modification of the traditional fuzzy clustering. First, a new fuzzy ordered c-means clustering is proposed. This method can be considered as a generalization of the concept of the conditional fuzzy clustering by introducing ordering and weighting distances from data to cluster prototypes. As a result, a more local impact of data on created groups and increased repulsive force between group prototypes are obtained. The proposed method provides a better representation of the data classes, in particular for classes with small cardinality in the training set (imbalanced data). A special initialization of the prototypes is also introduced. Next, the proposed clustering method is used to construct the premises of if-then rules of a fuzzy classifier. The conclusions of the rules are obtained by the least angle regression algorithm, which selects only those rules, that maximize the generalization ability of a classifier. Each if-then rule is represented in easily interpretable Mamdani-Assilian form. Finally, an extensive experimental analysis on 89 benchmark balanced and imbalanced datasets is performed to demonstrate the validity of the introduced classifier. Its competitiveness to state-of-the-art classifiers, with respect to both performance and interpretability, is shown as well.
- 9 October 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Fuzzy Systems
- Vol. 28 (11) , 2799-2813
Open AccessFuzzy Ordered $c$-Means Clustering and Least Angle Regression for Fuzzy Rule-Based Classifier: Study for Imbalanced Data
This article introduces a new classifier design method that is based on a modification of the traditional fuzzy clustering. First, a new fuzzy ordered c-means clustering is proposed. This method can be considered as a generalization of the concept of the conditional fuzzy clustering by introducing ordering and weighting distances from data to cluster prototypes. As a result, a more local impact of data on created groups and increased repulsive force between group prototypes are obtained. The proposed method provides a better representation of the data classes, in particular for classes with small cardinality in the training set (imbalanced data). A special initialization of the prototypes is also introduced. Next, the proposed clustering method is used to construct the premises of if-then rules of a fuzzy classifier. The conclusions of the rules are obtained by the least angle regression algorithm, which selects only those rules, that maximize the generalization ability of a classifier. Each if-then rule is represented in easily interpretable Mamdani-Assilian form. Finally, an extensive experimental analysis on 89 benchmark balanced and imbalanced datasets is performed to demonstrate the validity of the introduced classifier. Its competitiveness to state-of-the-art classifiers, with respect to both performance and interpretability, is shown as well.
- Open Access
- 8 October 2019
- Published by Association for Computing Machinery (ACM)
- p. 67-72
Application of Spatio-Temporal Filtering for Atrial Activity Waveforms Enhancement
- 8 October 2019
- Published by Association for Computing Machinery (ACM)
- p. 67-72
Open AccessApplication of Spatio-Temporal Filtering for Atrial Activity Waveforms Enhancement
- 1 March 2019
- Published by Elsevier in Expert Systems with Applications
- Vol. 118, 109-126
Fuzzy classifier based on clustering with pairs of ε-hyperballs and its application to support fetal state assessment
- 1 March 2019
- Published by Elsevier in Expert Systems with Applications
- Vol. 118, 109-126
Fuzzy classifier based on clustering with pairs of ε-hyperballs and its application to support fetal state assessment
- Open Access
- 1 September 2018
- Published by University of Zielona Góra, Poland in International Journal of Applied Mathematics and Computer Science
- Vol. 28 (3) , 545-557
Linguistically Defined Clustering of Data
This paper introduces a method of data clustering that is based on linguistically specified rules, similar to those applied by a human visually fulfilling a task. The method endeavors to follow these remarkable capabilities of intelligent beings. Even for most complicated data patterns a human is capable of accomplishing the clustering process using relatively simple rules. His/her way of clustering is a sequential search for new structures in the data and new prototypes with the use of the following linguistic rule: search for prototypes in regions of extremely high data densities and immensely far from the previously found ones. Then, after this search has been completed, the respective data have to be assigned to any of the clusters whose nuclei (prototypes) have been found. A human again uses a simple linguistic rule: data from regions with similar densities, which are located exceedingly close to each other, should belong to the same cluster. The goal of this work is to prove experimentally that such simple linguistic rules can result in a clustering method that is competitive with the most effective methods known from the literature on the subject. A linguistic formulation of a validity index for determination of the number of clusters is also presented. Finally, an extensive experimental analysis of benchmark datasets is performed to demonstrate the validity of the clustering approach introduced. Its competitiveness with the state-of-the-art solutions is also shown.
- 1 September 2018
- Published by University of Zielona Góra, Poland in International Journal of Applied Mathematics and Computer Science
- Vol. 28 (3) , 545-557
Open AccessLinguistically Defined Clustering of Data
This paper introduces a method of data clustering that is based on linguistically specified rules, similar to those applied by a human visually fulfilling a task. The method endeavors to follow these remarkable capabilities of intelligent beings. Even for most complicated data patterns a human is capable of accomplishing the clustering process using relatively simple rules. His/her way of clustering is a sequential search for new structures in the data and new prototypes with the use of the following linguistic rule: search for prototypes in regions of extremely high data densities and immensely far from the previously found ones. Then, after this search has been completed, the respective data have to be assigned to any of the clusters whose nuclei (prototypes) have been found. A human again uses a simple linguistic rule: data from regions with similar densities, which are located exceedingly close to each other, should belong to the same cluster. The goal of this work is to prove experimentally that such simple linguistic rules can result in a clustering method that is competitive with the most effective methods known from the literature on the subject. A linguistic formulation of a validity index for determination of the number of clusters is also presented. Finally, an extensive experimental analysis of benchmark datasets is performed to demonstrate the validity of the clustering approach introduced. Its competitiveness with the state-of-the-art solutions is also shown.
- 1 July 2018
- Published by Elsevier in Biomedical Signal Processing and Control
- Vol. 44, 237-246
On clustering based nonlinear projective filtering of biomedical signals
- 1 July 2018
- Published by Elsevier in Biomedical Signal Processing and Control
- Vol. 44, 237-246
On clustering based nonlinear projective filtering of biomedical signals