Bogdan Walek
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Bogdan Walek has a total of 37 co-authors. Here are the top co-authors by number of shared publications:
- Radim Farana
Mendel University in Brno
17 shared publications - Cyril Klimeš
Mendel University in Brno
9 shared publications Ondrej Pektor
University of Ostrava Ostrava, Czech Republic
8 shared publicationsJiri Bartos
Department of informatics and computers, University of Ostrava, Czech Republic
7 shared publicationsIvo Martinik
University of Ostrava, Ostrava, Czech Republic
5 shared publicationsJiří Bartoš
Department of Informatics and Computers, University of Ostrava, 30. dubna 22, 701 03 Ostrava, Czech Republic
4 shared publications
Latest Publications
- Open Access
Encoder Language Models for Zero-Shot Recommender Systems: Cross-Domain and Cross-Lingual Evaluation
This research provides deep insights into the capabilities of encoder models, offering a unique, controlled benchmark of over 20 state-of-the-art models. The aim is to analyze the viability of a potentially advantageous recommender architecture that capitalizes on the progress made in natural language processing (NLP) without the drawbacks of more advanced deep learning models or generative decoder-only large language models. We present a zero-shot recommender architecture used in a training-free setting. In this setting, item embeddings are aggregated into weighted user profiles and scored by cosine similarity against the full candidate pool. This approach makes use of state-of-the-art encoder language models in a frozen, inference-only, context-free state. We employed a temporal evaluation designed to simulate the cold-start problem, ordering user interactions over time and progressively revealing later interactions. We also used three contrasting datasets with specific challenges, as well as baseline methods of similar complexity and resource demands, such as collaborative filtering or content-based TF-IDF methods. For our recommendation task, we also compared the local large language model with the encoder models in a limited experiment. Our results suggest that frozen embedding-based recommendation could be a viable option, particularly when considering the cost/performance ratio. However, model and method selection should be evaluated against domain-specific tasks and protocols, rather than being based on general intuitions about scaling, general-purpose benchmark scores, or even leave-one-out validation methods.
Open AccessEncoder Language Models for Zero-Shot Recommender Systems: Cross-Domain and Cross-Lingual Evaluation
This research provides deep insights into the capabilities of encoder models, offering a unique, controlled benchmark of over 20 state-of-the-art models. The aim is to analyze the viability of a potentially advantageous recommender architecture that capitalizes on the progress made in natural language processing (NLP) without the drawbacks of more advanced deep learning models or generative decoder-only large language models. We present a zero-shot recommender architecture used in a training-free setting. In this setting, item embeddings are aggregated into weighted user profiles and scored by cosine similarity against the full candidate pool. This approach makes use of state-of-the-art encoder language models in a frozen, inference-only, context-free state. We employed a temporal evaluation designed to simulate the cold-start problem, ordering user interactions over time and progressively revealing later interactions. We also used three contrasting datasets with specific challenges, as well as baseline methods of similar complexity and resource demands, such as collaborative filtering or content-based TF-IDF methods. For our recommendation task, we also compared the local large language model with the encoder models in a limited experiment. Our results suggest that frozen embedding-based recommendation could be a viable option, particularly when considering the cost/performance ratio. However, model and method selection should be evaluated against domain-specific tasks and protocols, rather than being based on general intuitions about scaling, general-purpose benchmark scores, or even leave-one-out validation methods.
- 16 November 2025
- Published by Springer Nature
- p. 219-229
CyberKnife and Data Mining: Exploring Opportunities for Clinical Advancements
- 16 November 2025
- Published by Springer Nature
- p. 219-229
CyberKnife and Data Mining: Exploring Opportunities for Clinical Advancements
- Open Access
- 29 August 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (17) , 9518
Comparison of Selected Algorithms in Movie Recommender System
Recommender systems are currently very popular, and their main goal is to propose relevant content to users based on various parameters. The main goal of this paper is to create a comprehensive comparison of selected algorithms in movie recommender systems. The recommender system works with the MovieLens database. The main output of the proposed comparison is finding the best algorithm for selecting movies that are the most relevant to user preferences. The paper contains experimental verification of the performance of the proposed algorithms, with an emphasis on their evaluation based on metrics such as Precision, Recall and F1 score. The goal of the evaluation is to assess how well each algorithm performs in generating accurate and relevant recommendations. The testing process includes analysis of the results achieved on the test set of users.
- 29 August 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (17) , 9518
Open AccessComparison of Selected Algorithms in Movie Recommender System
Recommender systems are currently very popular, and their main goal is to propose relevant content to users based on various parameters. The main goal of this paper is to create a comprehensive comparison of selected algorithms in movie recommender systems. The recommender system works with the MovieLens database. The main output of the proposed comparison is finding the best algorithm for selecting movies that are the most relevant to user preferences. The paper contains experimental verification of the performance of the proposed algorithms, with an emphasis on their evaluation based on metrics such as Precision, Recall and F1 score. The goal of the evaluation is to assess how well each algorithm performs in generating accurate and relevant recommendations. The testing process includes analysis of the results achieved on the test set of users.
- Open Access
Intelligent Task Planning System Based on Methods of Fuzzy Natural Logic
In this paper, we present a novel approach to task planning based on an intelligent expert system that makes it possible to obtain a conclusion based on linguistically characterized knowledge. The main goal of the proposed task planning system is to arrange and display tasks for the solver in an effective way. Therefore, the system shows the most important tasks first and then the less important ones (in a determined ordering). The solver has a list of tasks arranged according to their importance at each time the task list is displayed. Another goal of the system is to show the effectiveness of all subordinate workers (solvers) for the manager. The expert knowledge contained in the system is characterized by three linguistic descriptions: determination of the task importance, determination of the final task importance, and determination of the efficiency of the task solvers. The system shows the ordered task list in real time. Evaluation of the relative and final importance of the tasks is performed periodically. The system has been implemented as a WEB application and verified on real data set. We also present experimental results of our system.
Open AccessIntelligent Task Planning System Based on Methods of Fuzzy Natural Logic
In this paper, we present a novel approach to task planning based on an intelligent expert system that makes it possible to obtain a conclusion based on linguistically characterized knowledge. The main goal of the proposed task planning system is to arrange and display tasks for the solver in an effective way. Therefore, the system shows the most important tasks first and then the less important ones (in a determined ordering). The solver has a list of tasks arranged according to their importance at each time the task list is displayed. Another goal of the system is to show the effectiveness of all subordinate workers (solvers) for the manager. The expert knowledge contained in the system is characterized by three linguistic descriptions: determination of the task importance, determination of the final task importance, and determination of the efficiency of the task solvers. The system shows the ordered task list in real time. Evaluation of the relative and final importance of the tasks is performed periodically. The system has been implemented as a WEB application and verified on real data set. We also present experimental results of our system.
- Open Access
- 25 March 2022
- Published by Elsevier in Expert Systems with Applications
- Vol. 200
Privacy risk assessment and privacy-preserving data monitoring
- 25 March 2022
- Published by Elsevier in Expert Systems with Applications
- Vol. 200
Open AccessPrivacy risk assessment and privacy-preserving data monitoring
- Open Access
- 3 October 2021
- Published by MDPI AG in Mathematics
- Vol. 9 (19) , 2475
Data Mining of Job Requirements in Online Job Advertisements Using Machine Learning and SDCA Logistic Regression
There are currently many job portals offering job positions in the form of job advertisements. In this article, we are proposing an approach to mine data from job advertisements on job portals. Mainly, it would concern job requirements mining from individual job advertisements. Our proposed system consists of a data mining module, a machine learning module, and a postprocessing module. The machine learning module is based on the SDCA logistic regression. The postprocessing module includes several approaches to increase the success rate of the job requirements identification. The proposed system was verified on 20 most searched IT job positions from the selected job portal. In total, 9971 job advertisements were analyzed. Our system’s verification is finding all job requirements in 80% of analyzed advertisements. The detected job requirements were also compared with the Open Skills database. Based on this database and the extension of IT job positions with other typical job skills, we created a list of the most frequent job skills in selected IT job positions. The main contribution is the development of a universal system to detect job requirements in job advertisements. The proposed approach can be used not only for IT positions, but also for various job positions. The presented data mining module can also be used for various job portals.
- 3 October 2021
- Published by MDPI AG in Mathematics
- Vol. 9 (19) , 2475
Open AccessData Mining of Job Requirements in Online Job Advertisements Using Machine Learning and SDCA Logistic Regression
There are currently many job portals offering job positions in the form of job advertisements. In this article, we are proposing an approach to mine data from job advertisements on job portals. Mainly, it would concern job requirements mining from individual job advertisements. Our proposed system consists of a data mining module, a machine learning module, and a postprocessing module. The machine learning module is based on the SDCA logistic regression. The postprocessing module includes several approaches to increase the success rate of the job requirements identification. The proposed system was verified on 20 most searched IT job positions from the selected job portal. In total, 9971 job advertisements were analyzed. Our system’s verification is finding all job requirements in 80% of analyzed advertisements. The detected job requirements were also compared with the Open Skills database. Based on this database and the extension of IT job positions with other typical job skills, we created a list of the most frequent job skills in selected IT job positions. The main contribution is the development of a universal system to detect job requirements in job advertisements. The proposed approach can be used not only for IT positions, but also for various job positions. The presented data mining module can also be used for various job portals.
- Open Access
- 27 July 2021
- Published by MDPI AG in Mathematics
- Vol. 9 (15) , 1773
Decision Support System for Evaluating Suitable Job Applicants
This paper describes a novel approach in the area of evaluating suitable job applicants for various job positions, and specifies typical areas of requirement and their usage. Requirements for this decision-support system are defined in order to be used in middle-size companies. Suitable tools chosen were fuzzy expert systems, primarily the inference system Takagi-Sugeno type, which were then supplied with implementation of methods of variant multi-criteria analysis. The resulting system is a variable tool with the possibility to simply set the importance of individual selection criteria so that it can be used in various situations, primarily in repeated selection procedures for similar job positions. A strong emphasis is devoted to the explanatory module, which enables the results of the expert system to be used easily. Verification of the system on real data in cooperation with a collaborating company has proved that the system is easily usable.
- 27 July 2021
- Published by MDPI AG in Mathematics
- Vol. 9 (15) , 1773
Open AccessDecision Support System for Evaluating Suitable Job Applicants
This paper describes a novel approach in the area of evaluating suitable job applicants for various job positions, and specifies typical areas of requirement and their usage. Requirements for this decision-support system are defined in order to be used in middle-size companies. Suitable tools chosen were fuzzy expert systems, primarily the inference system Takagi-Sugeno type, which were then supplied with implementation of methods of variant multi-criteria analysis. The resulting system is a variable tool with the possibility to simply set the importance of individual selection criteria so that it can be used in various situations, primarily in repeated selection procedures for similar job positions. A strong emphasis is devoted to the explanatory module, which enables the results of the expert system to be used easily. Verification of the system on real data in cooperation with a collaborating company has proved that the system is easily usable.
- 27 October 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
A Data Mining Approach for Finding Similar Job Positions to Upgrade a Job Position in a System for Evaluating Competencies
This article focuses on creating an approach to find similar job positions based on an existing job position in a system for evaluating competencies. The proposed method uses data mining methods to find similar job positions on a job portal based on input data. The input data is the job position title and the list of competencies. The proposed approach then accesses the relevant job positions in a job portal and compares them with the entered inputs. The output of the approach is a list of the most similar job positions in the job portal, including their description. Then HR manager should use this output for completing the assigned job position and its competencies. The proposed approach is then experimentally verified.
- 27 October 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
A Data Mining Approach for Finding Similar Job Positions to Upgrade a Job Position in a System for Evaluating Competencies
This article focuses on creating an approach to find similar job positions based on an existing job position in a system for evaluating competencies. The proposed method uses data mining methods to find similar job positions on a job portal based on input data. The input data is the job position title and the list of competencies. The proposed approach then accesses the relevant job positions in a job portal and compares them with the entered inputs. The output of the approach is a list of the most similar job positions in the job portal, including their description. Then HR manager should use this output for completing the assigned job position and its competencies. The proposed approach is then experimentally verified.
- 8 August 2020
- Published by Springer Nature
- p. 127-136
An Approach for Creating Data Structure of a Hierarchical Competency Model
- 8 August 2020
- Published by Springer Nature
- p. 127-136
An Approach for Creating Data Structure of a Hierarchical Competency Model
- 10 December 2019
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2186 (1) , 060001
Preface of the International Symposium on Computer Science and Information Technology (ISCSIT 2019)
- 10 December 2019
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2186 (1) , 060001
Preface of the International Symposium on Computer Science and Information Technology (ISCSIT 2019)