TKTomáš Kasanický

Tomáš Kasanický

*This is an algorithmically generated author record based on publicly available information.

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


Tomáš Kasanický has a total of 21 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Kinship and age influence dawn co-swarming associations in Daubenton’s bats

    by Romana Ružinská, Denisa Lőbbová, Tomáš Kasanický, Ján Zelenka, Peter Kaňuch

    In the fission-fusion dynamics of tree-dwelling bats, frequent roost switching maintains social bonds among colony members. It is hypothesised that the ritualised swarming or rallying behaviour of bats near a roost signals its location and that this transmission of information prevents the disintegration of the social group. We investigated swarming co-occurrences (i.e. the joint occurrence of two bats at the roost during swarming) in a maternity colony of Daubenton’s bats, Myotis daubentonii , using automated PIT tag readers that monitored bat activity at the entrances of tree roosts from midnight to sunrise. Over three summer seasons, we recorded 4736 dyadic co-occurrences in 5-second time windows by 259 individuals, with high variation in the number of swarming events and mates per an individual. Using a multi-membership multilevel model we found that dyads involving juveniles, particularly juvenile–juvenile and juvenile–adult pairs, showed significantly higher co-occurrence rates than adult–adult dyads. Relatedness had minimal overall effects but influenced co-swarming when juveniles were involved, indicating kin-biased interactions early in life. The swarming index, used to identify individuals that preferentially initiate co-swarming, showed that old females have more swarming events recorded relative to possible interactions detected, suggesting they might be more likely to serve as signallers whereas juveniles are more likely to function as receivers. Significance statement: The exchange of information in tree-dwelling bat species is particularly important for sharing knowledge about their numerous roosts. The swarming behaviour of these bats at dawn consists of various visual displays, including multiple landing trials before entry, and broadband vocalisations. However, the function of swarming remains unclear and there is no knowledge about the interactions between swarming individuals. The frequency with which two Daubenton’s bats appear at the roost entrance within a short period of 5 s was used as an indication of co-swarming. We investigated how individual characteristics, such as genetic relatedness or age, may influence this behaviour, which is assumed to involve decision-making. We show that age plays a dominant role in shaping swarming co-occurrences; however, the effect of relatedness emerges in juvenile contexts. We suggest that dawn swarming may be one of the mechanisms that promote long-lasting social bonds between colony members.

  • Studies of the Usability of Satellite Images in the Identification of Forest Stands in Slovakia

    by Ján Zelenka, Tomáš Kasanický, Ján Mojžiš, Martin Kenyeres, Peter Krammer, Ladislav Hluchý

  • Open Access

    Crop Mapping without Labels: Investigating Temporal and Spatial Transferability of Crop Classification Models Using a 5-Year Sentinel-2 Series and Machine Learning

    by Tomáš Rusňák, Tomáš Kasanický, Peter Malík, Ján Mojžiš, Ján Zelenka, Michal Sviček, Dominik Abrahám, Andrej Halabuk

    Multitemporal crop classification approaches have demonstrated high performance within a given season. However, cross-season and cross-region crop classification presents a unique transferability challenge. This study addresses this challenge by adopting a domain generalization approach, e.g., by training models on multiple seasons to improve generalization to new, unseen target years. We utilize a comprehensive five-year Sentinel-2 dataset over different agricultural regions in Slovakia and a diverse crop scheme (eight crop classes). We evaluate the performance of different machine learning classification algorithms, including random forests, support vector machines, quadratic discriminant analysis, and neural networks. Our main findings reveal that the transferability of models across years differs between regions, with the Danubian lowlands demonstrating better performance (overall accuracies ranging from 91.5% in 2022 to 94.3% in 2020) compared to eastern Slovakia (overall accuracies ranging from 85% in 2022 to 91.9% in 2020). Quadratic discriminant analysis, support vector machines, and neural networks consistently demonstrated high performance across diverse transferability scenarios. The random forest algorithm was less reliable in generalizing across different scenarios, particularly when there was a significant deviation in the distribution of unseen domains. This finding underscores the importance of employing a multi-classifier analysis. Rapeseed, grasslands, and sugar beet consistently show stable transferability across seasons. We observe that all periods play a crucial role in the classification process, with July being the most important and August the least important. Acceptable performance can be achieved as early as June, with only slight improvements towards the end of the season. Finally, employing a multi-classifier approach allows for parcel-level confidence determination, enhancing the reliability of crop distribution maps by assuming higher confidence when multiple classifiers yield similar results. To enhance spatiotemporal generalization, our study proposes a two-step approach: (1) determine the optimal spatial domain to accurately represent crop type distribution; and (2) apply interannual training to capture variability across years. This approach helps account for various factors, such as different crop rotation practices, diverse observational quality, and local climate-driven patterns, leading to more accurate and reliable crop classification models for nationwide agricultural monitoring.


  • Open Access

    Long-Exposure RGB Photography with a Fixed Stand for the Measurement of a Trajectory of a Dynamic Impact Device in Real Scale

    by Ľudovít Kovanič, Ľubomír Ambriško, Daniela Marasová, Peter Blišťan, Tomáš Kasanický, Michal Cehlár

    The present manuscript proposes a novel method for the measurement of a trajectory of a falling impact hammer in the dynamic loading of conveyor belts and the determination of their impact resistance. The proposed method has been experimentally tested and the results of the measurements are presented in this manuscript. The proposed method is based on the long-exposure photography with a long-duration opened shutter of the Nikon D5000 DSLR camera. Results of the experimental research were compared with direct reference measurements performed using the L-GAGE LT3 laser distance sensor. Differences between values, obtained by the new method and by the reference measurements were up to ±3 mm. The standard deviation identified in all the experiments was 1 mm.


  • Open Access

    Self-Adaptation of a Heterogeneous Swarm of Mobile Robots to a Covered Area

    by Ján Zelenka, Tomáš Kasanický, Marek Bundzel, Rudolf Andoga

    An original swarm-based method for coordination of groups of mobile robots with a focus on the self-organization and self-adaptation of the groups is presented in this paper. The method is a nature-inspired decentralized algorithm that uses artificial pheromone marks and enables the cooperation of different types of independent reactive agents that operate in the air, on the ground, or in the water. The advantages of our solution include scalability, adaptability, and robustness. The algorithm worked with variable numbers of agents in the groups. It was resistant against failures of the individual robots. A transportation control algorithm that ensured the spreading of different types of agents across exploration space with different types of environments was introduced and tested. We established that our swarm control algorithm was able to successfully control three basic behaviors: space exploration, population management, and transportation. The behaviors were able to run simultaneously, and space exploration (the main goal) was never stopped or interrupted. All these features combined in a single algorithmic package represent a framework for future development of swarm-based agent systems applicable in a broad scope of environments. The results confirmed that the algorithm can be applied to monitoring, surveillance, patrolling, or search and rescue tasks.