Vesna Dimitrievska Ristovska
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Vesna Dimitrievska Ristovska has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Petar Sekuloski
Ss. Cyril and Methodius University
3 shared publications Petar Sekuloski
2 shared publicationsVassil Grozdanov
2 shared publicationsAleksandra Stojanova Ilievska
Goce Delcev University,Faculty of computer science,Stip,Republic of North Macedonia
1 shared publication- Dimitar Kitanovski
Faculty of Computer Science and Engineering, Ss. Cyril and Methodius University, Skopje, North Macedonia
1 shared publication Emil Stankov
SS. Cyril and Methodius University, Macedonia
1 shared publication
Latest Publications
- Open Access
- 22 January 2026
- Published by MDPI AG in Mathematics
- Vol. 14 (2) , 378
Exploring the Potential of Topological Data Analysis for Explainable Large Language Models: A Scoping Review
Large language models (LLMs) have become central to modern artificial intelligence, yet their internal decision-making processes remain difficult to interpret. As interest grows in making these models more transparent and reliable, topological data analysis (TDA) has emerged as a promising mathematical approach for exploring their structure. This scoping review maps the current landscape of research where TDA tools—such as persistent homology and Mapper—are used to examine LLM components like attention patterns, latent representations, and training dynamics. By analyzing topological features across layers and tasks, these methods provide new ways to understand how language models generalize, respond to unfamiliar inputs, and shift under fine-tuning. The review also considers how TDA-based techniques contribute to broader goals in interpretability and robustness, especially in detecting hallucinations, out-of-distribution behavior, and representational collapse. Overall, the findings suggest that TDA offers a rigorous and versatile framework for studying LLMs, helping researchers uncover deeper patterns in how these models learn and reason.
- 22 January 2026
- Published by MDPI AG in Mathematics
- Vol. 14 (2) , 378
Open AccessExploring the Potential of Topological Data Analysis for Explainable Large Language Models: A Scoping Review
Large language models (LLMs) have become central to modern artificial intelligence, yet their internal decision-making processes remain difficult to interpret. As interest grows in making these models more transparent and reliable, topological data analysis (TDA) has emerged as a promising mathematical approach for exploring their structure. This scoping review maps the current landscape of research where TDA tools—such as persistent homology and Mapper—are used to examine LLM components like attention patterns, latent representations, and training dynamics. By analyzing topological features across layers and tasks, these methods provide new ways to understand how language models generalize, respond to unfamiliar inputs, and shift under fine-tuning. The review also considers how TDA-based techniques contribute to broader goals in interpretability and robustness, especially in detecting hallucinations, out-of-distribution behavior, and representational collapse. Overall, the findings suggest that TDA offers a rigorous and versatile framework for studying LLMs, helping researchers uncover deeper patterns in how these models learn and reason.
- 23 April 2025
- Published by Springer Nature
- p. 147-156
Classification of Some Seismological Images Using Deep Learning and Persistent Homology
The study focuses on using models that integrate deep learning and Persistent Homology to classify images of stars and galaxies obtained from po-werful telescopes. The main result of this paper is that the persistent images captured the essential information from the dataset we used. We get slightly better evaluation results, if we use just persistent images obtained from the original images instead of the original images. Also, in this paper we evaluate models that incorporate Persistent Homology and Deep Learning that we have proposed earlier. From the evaluation, we can say that usage of topological characteristics of data improves the classification.
- 23 April 2025
- Published by Springer Nature
- p. 147-156
Classification of Some Seismological Images Using Deep Learning and Persistent Homology
The study focuses on using models that integrate deep learning and Persistent Homology to classify images of stars and galaxies obtained from po-werful telescopes. The main result of this paper is that the persistent images captured the essential information from the dataset we used. We get slightly better evaluation results, if we use just persistent images obtained from the original images instead of the original images. Also, in this paper we evaluate models that incorporate Persistent Homology and Deep Learning that we have proposed earlier. From the evaluation, we can say that usage of topological characteristics of data improves the classification.
- Open Access
- 27 January 2025
- Published by International Journal of Science and Research in International Journal of Science and Research (IJSR)
- Vol. 14 (1) , 93-98
Optimization of Ornstein-Uhlenbeck Models in Pair Trading: Heuristic and Metaheuristic Approaches
Stochastic processes are widely used in describing time dependent sequences of random changes in both physical and
- 27 January 2025
- Published by International Journal of Science and Research in International Journal of Science and Research (IJSR)
- Vol. 14 (1) , 93-98
Open AccessOptimization of Ornstein-Uhlenbeck Models in Pair Trading: Heuristic and Metaheuristic Approaches
Stochastic processes are widely used in describing time dependent sequences of random changes in both physical and
- 27 February 2024
- Published by Springer Nature
- p. 156-170
Image Classification Using Deep Neural Networks and Persistent Homology
- 27 February 2024
- Published by Springer Nature
- p. 156-170
Image Classification Using Deep Neural Networks and Persistent Homology
- 15 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 6-10
Analysis and Visualization of Social Networks
The huge development of social networks opens the need for their analysis. The visualization of social networks is an important and powerful tool for such kind of analysis. There are many software packages which can be used for visualization. In this paper we are using graph theory, Python, and the free software Gephi to make visualization of social networks. Particularly we have made visualization of social network Twitter in order to show the relations between its users. This visualization helps in the analysis of relations and interactions between social media users.
- 15 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 6-10
Analysis and Visualization of Social Networks
The huge development of social networks opens the need for their analysis. The visualization of social networks is an important and powerful tool for such kind of analysis. There are many software packages which can be used for visualization. In this paper we are using graph theory, Python, and the free software Gephi to make visualization of social networks. Particularly we have made visualization of social network Twitter in order to show the relations between its users. This visualization helps in the analysis of relations and interactions between social media users.
- 5 December 2022
- Published by International Journal of Science and Research in International Journal of Science and Research (IJSR)
- Vol. 11 (12) , 1137-1141
A Novel Model for Image Classification based on Persistent Homology
Topological Data Analysis (TDA) is relatively new field of Applied Mathematics that emerged rapidly last years. Th
- 5 December 2022
- Published by International Journal of Science and Research in International Journal of Science and Research (IJSR)
- Vol. 11 (12) , 1137-1141
A Novel Model for Image Classification based on Persistent Homology
Topological Data Analysis (TDA) is relatively new field of Applied Mathematics that emerged rapidly last years. Th
- 1 June 2021
- Published by Vilnius University Press in OLYMPIADS IN INFORMATICS
- p. 91-104
Teaching and Examination Process of Some University Courses before vs during the Corona Crisis
The newly emerged corona crisis in our country, but also much broader – on the entire planet, caused by the pandemic scale of COVID-19 virus, dictated the need for adjustment of the teaching and examination process of many university courses. At our institution, Faculty of Computer Science and Engineering (FCSE) in Skopje, starting from March 17, 2020, until today (March 2021), classes and exams are completely realized through distance learning systems, i.e. using the BigBlueButton video conferencing system, implemented in the Courses and Exams student services – the official FCSE websites on the Moodle e-learning platform. For all faculty courses, lectures, auditory and laboratory exercises, colloquia and exams, all take place via a video conferencing system for distance education. In this paper we present a comparative analysis of the conduction of some courses at FCSE in classical conditions, as opposed to the conditions with distance education. We have considered the analysis mainly from the aspect of the approach to teaching, as well as from the aspect of exam conduction and achieved exam results. The analysis of those aspects leads us to conclusions about several positive and negative sides that we noticed in distance education compared to the classical conditions of classes and exams. Our findings also may apply on the organization of online contests, especially in informatics.
- 1 June 2021
- Published by Vilnius University Press in OLYMPIADS IN INFORMATICS
- p. 91-104
Teaching and Examination Process of Some University Courses before vs during the Corona Crisis
The newly emerged corona crisis in our country, but also much broader – on the entire planet, caused by the pandemic scale of COVID-19 virus, dictated the need for adjustment of the teaching and examination process of many university courses. At our institution, Faculty of Computer Science and Engineering (FCSE) in Skopje, starting from March 17, 2020, until today (March 2021), classes and exams are completely realized through distance learning systems, i.e. using the BigBlueButton video conferencing system, implemented in the Courses and Exams student services – the official FCSE websites on the Moodle e-learning platform. For all faculty courses, lectures, auditory and laboratory exercises, colloquia and exams, all take place via a video conferencing system for distance education. In this paper we present a comparative analysis of the conduction of some courses at FCSE in classical conditions, as opposed to the conditions with distance education. We have considered the analysis mainly from the aspect of the approach to teaching, as well as from the aspect of exam conduction and achieved exam results. The analysis of those aspects leads us to conclusions about several positive and negative sides that we noticed in distance education compared to the classical conditions of classes and exams. Our findings also may apply on the organization of online contests, especially in informatics.