An in silico model to simulate the evolution of biological aging

A Šajina, DR Valenzano - arXiv preprint arXiv:1602.00723, 2016 - arxiv.org
Biological aging is characterized by an age-dependent increase in the probability of death
and by a decrease in the reproductive capacity. Individual age-dependent rates of survival …

AEGIS: An In Silico Tool to model Genome Evolution in Age-Structured Populations

WJ Bradshaw, A Šajina, DR Valenzano - bioRxiv, 2019 - biorxiv.org
AEGIS (Ageing of Evolving Genomes In Silico) is a versatile population-genetics numerical-simulation
tool that enables the evolution of life history trajectories under sexual and asexual …

[HTML][HTML] 3D Pose Estimation and Tracking in Handball Actions Using a Monocular Camera

R Šajina, M Ivašić-Kos - Journal of imaging, 2022 - mdpi.com
Player pose estimation is particularly important for sports because it provides more accurate
monitoring of athlete movements and performance, recognition of player actions, analysis of …

Peer-to-peer deep learning with non-IID data

R Šajina, N Tanković, I Ipšić - Expert systems with applications, 2023 - Elsevier
Collaborative training of deep neural networks using edge devices has attracted substantial
research interest recently. The two main architecture approaches for the training process are …

Multi-task peer-to-peer learning using an encoder-only transformer model

R Šajina, N Tanković, I Ipšić - Future generation computer systems, 2024 - Elsevier
Peer-to-peer (P2P) learning is a decentralized approach to organizing the collaboration
between end devices known as agents. Agents contain heterogeneous data, and that …

MPFSIR: An Effective Multi-Person Pose Forecasting Model With Social Interaction Recognition

R Šajina, M Ivasic-Kos - IEEE access, 2023 - ieeexplore.ieee.org
In recent years, multi-person pose forecasting has gained significant attention due to its
potential applications in various fields such as computer vision, robotics, sports analysis, and …

A review on generating random numbers in decentralised environments

SD Simić, R Šajina, N Tanković… - 2020 43rd International …, 2020 - ieeexplore.ieee.org
Recent advances in blockchain gained significant social attention, mainly due to substantial
price fluctuations of Bitcoin and Ethereum cryptocurrencies. By its design, blockchain is an …

Decentralized trustless gossip training of deep neural networks

R Šajina, N Tanković, D Etinger - 2020 43rd International …, 2020 - ieeexplore.ieee.org
Novel machine learning techniques apply decentralized model training in order to mitigate
data volume and privacy issues. Current approaches assume (a) node performance …

Classification of Visual Perception EEG Signals for a 2D Platformer Game

A Žužić, R Šajina, N Tanković - 2023 IEEE 21st Jubilee …, 2023 - ieeexplore.ieee.org
This research focuses on classifying visual perception brain signals using an OpenBCI
headset to capture the EEG signals from the participants. The headset comprises 16 re-…

Development and evaluation of an application for sharing information about courses

R Šajina, T Orehovacki - 2018 41st International Convention on …, 2018 - ieeexplore.ieee.org
Learning Management Systems (LMSs) such as Moodle are nowadays widely employed in
higher education institutions. They enable teachers to publish educational materials and …