@Article{Vrban2026,
author={Vrban, Branislav
and Vrtalov{\'a}, Vendula
and Kne{\v{z}}evi{\'{c}}, Du{\v{s}}ica
and Savi{\'{c}}, Milo{\v{s}}
and Kurbalija, Vladimir
and Jakoveti{\'{c}}, Du{\v{s}}an
and {\v{C}}erba, {\v{S}}tefan
and L{\"u}ley, Jakub},
title={The application of machine learning techniques to data from solid-state nuclear track detector CR-39},
journal={The European Physical Journal Special Topics},
year={2026},
month={May},
day={09},
abstract={The study presents an application of classification-based machine learning techniques to a dataset comprising the radiation dose measurements with solid-state nuclear track detectors of poly(allyl diglycol carbonate) type. The detectors were irradiated with alpha particles and fast neutrons in various experimental configurations making the final dataset complex and suitable for machine learning methods. The most suitable experiment is chosen as a stepping stone, and the proposed evaluation method is tested. The detectors are analysed with the commercially available TASLImage system and the final performance in dose determination is compared to the machine learning efforts. Moreover, the uncertainty quantification algorithm is applied to better judge the future applicability of the new evaluation method.},
issn={1951-6401},
doi={10.1140/epjs/s11734-026-02349-0},
url={https://doi.org/10.1140/epjs/s11734-026-02349-0}
}

The study presents an application of classification-based machine learning techniques to a dataset comprising the radiation dose measurements with solid-state nuclear track detectors of poly(allyl diglycol carbonate) type. The detectors were irradiated with alpha particles and fast neutrons in various experimental configurations making the final dataset complex and suitable for machine learning methods. The most suitable experiment is chosen as a stepping stone, and the proposed evaluation method is tested. The detectors are analysed with the commercially available TASLImage system and the final performance in dose determination is compared to the machine learning efforts. Moreover, the uncertainty quantification algorithm is applied to better judge the future applicability of the new evaluation method.

@article{babic2024machine,
  title={Machine Learning Optimizations of BioMeld-Voxelyze Simulator},
  author={Babi{\'c}, Jela and Kne{\v{z}}evi{\'c}, Du{\v{s}}ica and Savi{\'c}, Milo{\v{s}} and Kurbalija, Vladimir and Bala{\v{z}}, Igor},
  year={2024}
}

@article{knevzevic2024local,
  title={Local Intrinsic Dimensionality for Dynamic Graph Embeddings},
  author={Kne{\v{z}}evi{\'c}, Du{\v{s}}ica and Savi{\'c}, Milo{\v{s}} and Radovanovi{\'c}, Milo{\v{s}}},
  journal={arXiv preprint arXiv:2411.16145},
  year={2024}
}

@inproceedings{knevzevic2022evaluation,
  title={Evaluation of LID-aware graph embedding methods for node clustering},
  author={Kne{\v{z}}evi{\'c}, Du{\v{s}}ica and Babi{\'c}, Jela and Savi{\'c}, Milo{\v{s}} and Radovanovi{\'c}, Milo{\v{s}}},
  booktitle={International Conference on Similarity Search and Applications},
  pages={222--233},
  year={2022},
  organization={Springer International Publishing Cham}
}

@inproceedings{knezevic2020analysis,
  title={Analysis of scientific fields using journal citation networks: An empirical study},
  author={Kne{\v{z}}evi{\'c}, Du{\v{s}}ica and Savi{\'c}, Milo{\v{s}}},
  booktitle={2020 International Conference on INnovations in Intelligent SysTems and Applications (INISTA)},
  pages={1--7},
  year={2020},
  organization={IEEE}
}