arXiv subjects

Agnieszka Szczęsna

Publications and source records attributed to Agnieszka Szczęsna.

3 recordsLinked to original sources

arXiv2024

Propagation of weakly advantageous mutations in cancer cell population

Research into somatic mutations in cancer cell DNA and their role in tumour growth and progression between successive stages is crucial for improving our understanding of cancer evolution. Mathematical and computer modelling can provide valuable insights into the scenarios of cancer growth, the roles of somatic mutations, and the types and strengths of evolutionary forces they introduce. Previous studies have developed mathematical models of cancer evolution, incorporating driver and passenger somatic mutations. Driver mutations were assumed to have a strong advantageous effect on the growth of the cancer cell population, while passenger mutations were considered fully neutral or mildly deleterious. However, according to several studies, passenger mutations may have a weakly advantageous effect on tumour growth. In this paper, we develop models of cancer evolution with somatic mutations that introduce a weakly advantageous force to the evolution of cancer cells. The models used in this study can be classified into two categories: deterministic and stochastic. Deterministic models are based on systems of differential equations that balance the average number of cells and mutations during evolution. To verify the results of our deterministic modelling, we use a stochastic model based on the Gillespie algorithm. We compare the predictions of our modelling with some observational data on cancer evolution.

q-bio.PE↗

arXiv2023

Development of a Realistic Crowd Simulation Environment for Fine-grained Validation of People Tracking Methods

Generally, crowd datasets can be collected or generated from real or synthetic sources. Real data is generated by using infrastructure-based sensors (such as static cameras or other sensors). The use of simulation tools can significantly reduce the time required to generate scenario-specific crowd datasets, facilitate data-driven research, and next build functional machine learning models. The main goal of this work was to develop an extension of crowd simulation (named CrowdSim2) and prove its usability in the application of people-tracking algorithms. The simulator is developed using the very popular Unity 3D engine with particular emphasis on the aspects of realism in the environment, weather conditions, traffic, and the movement and models of individual agents. Finally, three methods of tracking were used to validate generated dataset: IOU-Tracker, Deep-Sort, and Deep-TAMA.

cs.CV↗

arXiv2023

CrowdSim2: an Open Synthetic Benchmark for Object Detectors

Data scarcity has become one of the main obstacles to developing supervised models based on Artificial Intelligence in Computer Vision. Indeed, Deep Learning-based models systematically struggle when applied in new scenarios never seen during training and may not be adequately tested in non-ordinary yet crucial real-world situations. This paper presents and publicly releases CrowdSim2, a new synthetic collection of images suitable for people and vehicle detection gathered from a simulator based on the Unity graphical engine. It consists of thousands of images gathered from various synthetic scenarios resembling the real world, where we varied some factors of interest, such as the weather conditions and the number of objects in the scenes. The labels are automatically collected and consist of bounding boxes that precisely localize objects belonging to the two object classes, leaving out humans from the annotation pipeline. We exploited this new benchmark as a testing ground for some state-of-the-art detectors, showing that our simulated scenarios can be a valuable tool for measuring their performances in a controlled environment.

cs.CV↗