Ms Zoja Scekic, University of Donja Gorica
M1-M10, full internship with Faculty of Appied Sciences UDG in 2023.
Zoja participated in various training activities to enhance her expertise while conducting advanced research as part of her Master’s program in Artificial Intelligence. Her thesis focused on applying deep learning models for day-ahead electricity price prediction, addressing the growing challenges of accuracy and efficiency in electricity markets increasingly influenced by renewable energy sources. Zoja explored multiple deep learning approaches, including Artificial Neural Networks (ANN), Long Short-Term Memory (LSTM), Convolutional Neural Networks (CNN), and hybrid models like CNN-LSTM, comparing their performance against traditional forecasting methods. Her work highlighted the potential of these models to improve market decision-making for participants, grid operators, and policymakers. Despite promising results, she identified key challenges, such as data quality, model complexity, and resource demands, and emphasized the importance of further research to enhance model efficiency and broaden their applicability to diverse energy markets.
Mr Elvis Taruh, University of Donja Gorica
M13-M22, , full internship with Faculty for Information Systems and Technologies in 2024.
Elvis actively engaged in skill-building activities while conducting innovative research aimed at improving agricultural efficiency and productivity. His work addressed key challenges in the livestock sector, such as high labor costs, inefficiencies in resource management, and the lack of access to modern technologies for farmers. To tackle these issues, Elvis proposed and developed a real-time livestock detection and tracking system using cameras connected to a Jetson Nano device and the YOLOv8 model for animal recognition. This system leverages edge computing and machine learning to provide farmers with accurate, real-time data on livestock movement and condition, enabling timely decision-making and reducing labor costs. The model training was accelerated using HPC servers and tools, ensuring efficient development and high-performance outcomes. By processing data locally on the energy-efficient Jetson Nano, the system minimizes the need for extensive data transmission, making it suitable for rural environments. The technology enhances farm safety and management by sending alerts when livestock behavior deviates from the norm, such as a cow straying from the herd.
Ms Anesa Abazovic, University of Donja Gorica
M13-M22, , full internship with Faculty for Information Systems and Technologies in 2024.
During her internship, Anesa actively participated in training activities to enhance her technical skills while conducting advanced research as part of her Master’s program in Artificial Intelligence. Her work focused on applying AI and deep learning in computer vision for the detection of ovarian cancer. She developed and evaluated computer vision models using YOLOv8, the state-of-the-art in object detection, and YOLOv7, an established model in the field, to determine their effectiveness in this medical context. Additionally, Anesa benchmarked the models against other machine learning approaches, underscoring the practical impact of her research in advancing AI-driven solutions for healthcare. Anesa was involved in promo activities for HPC/AI in S3 domains.
Mr Arnad Lekic, University of Donja Gorica
M13-M22, , full internship with Faculty for Information Systems and Technologies in 2024.
During his internship, Arnad engaged in various training activities to enhance his skills while also participating in hands-on research projects. As a student enrolled in a Master’s program in Artificial Intelligence, he focused on optimizing solar energy management in hybrid energy systems through advanced AI techniques. His research involved developing a predictive model using Long Short-Term Memory (LSTM) neural networks to forecast solar radiation, enabling efficient energy usage planning and savings. Additionally, Arnad worked on integrating this model into a practical application with web and mobile interfaces, incorporating IoT devices and spatiotemporal data analysis using LSTM and CNN models. This work demonstrated his ability to apply theoretical knowledge to real-world sustainability challenges while expanding his expertise in AI-driven solutions.