Faculty of Computer Science and Engineering

Permanent URI for this communityhttps://repository.ukim.mk/handle/20.500.12188/5

The Faculty of Computer Science and Engineering (FCSE) within UKIM is the largest and most prestigious faculty in the field of computer science and technologies in Macedonia, and among the largest faculties in that field in the region. The FCSE teaching staff consists of 50 professors and 30 associates. These include many “best in field” personnel, such as the most referenced scientists in Macedonia and the most influential professors in the ICT industry in the Republic of Macedonia.

Browse

Search Results

Now showing 1 - 10 of 1963

Some of the metrics are blocked by your
consent settings
Colonoscopy image analysis for polyp detection: A systematic review of existing approaches and opportunities
(Elsevier BV, 2025)
Albuquerque, Carlos
;
Neves, Paulo Alexandre
;
Godinho, António
;
;
Some of the metrics are blocked by your
consent settings
A low-cost device-based data approach to Eight Hop Test
(Elsevier BV, 2025)
Pimenta, Luís
;
Coelho, Paulo Jorge
;
Gonçalves, Norberto Jorge
;
Lousado, José Paulo
;
Albuquerque, Carlos
Some of the metrics are blocked by your
consent settings
Weather-Aware Deep Reinforcement Learning for Predictive Modeling of Household Energy Dynamics
(Istanbul University, 2026-01-30)
Bajrami, Enes
;
This study proposes a weather-aware deep reinforcement learning (DRL) framework for predictive modelling of household energy dynamics. Using a 14-month high-resolution dataset from a residence in Northeast Mexico, the framework integrates detailed meteorological attributes and next-day forecasts to enhance prediction accuracy. Four DRL algorithms were implemented and evaluated for their performance in forecasting household energy consumption: Proximal Policy Optimisation (PPO), Soft Actor-Critic (SAC), Deep Deterministic Policy Gradient (DDPG), and Asynchronous Advantage Actor-Critic (A3C). Exploratory data analysis revealed significant seasonal trends and variability in energy usage patterns. Results show that DDPG and SAC outperform PPO and A3C, achieving the lowest root mean square error (RMSE) and mean absolute error (MAE), with DDPG recording 0.0011 RMSE and 0.0009 MAE. The framework was tested on moderately equipped hardware, demonstrating the practical feasibility of DRL-based energy forecasting systems. This work contributes original visualisations and comparative insights, advancing smart energy management solutions.
Some of the metrics are blocked by your
consent settings
Modelling and quantifying numerical integration errors in deep reinforcement learning for propulsion dynamics
(Elsevier BV, 2026-10)
Bajrami, Enes
;
Bajrami, Ensar
;
This study investigates how numerical integration accuracy influences the training dynamics and control performance of deep reinforcement learning controllers applied to propulsion system simulations. The propulsion dynamics are represented by a continuous second-order thrust-driven model that is discretised using four numerical integration configurations: Euler (coarse, medium, and fine time steps) and Runge-Kutta fourth order (RK4). Three widely used model-free reinforcement learning algorithms, Proximal Policy Optimization (PPO), Soft Actor-Critic (SAC), and Twin Delayed Deep Deterministic Policy Gradient (TD3), are evaluated together with a linear proportional-derivative baseline controller. A large experimental campaign comprising more than 50,000 simulated episodes was conducted across three training phases to quantify the influence of discretisation accuracy on reward convergence, trajectory stability, and control energy. The results demonstrate that numerical integration fidelity significantly shapes the optimisation landscape experienced by reinforcement learning agents. Under coarse Euler discretisation, PPO exhibits unstable learning behaviour and large oscillatory trajectories, while SAC maintains improved robustness but still shows sensitivity to large time steps. TD3 demonstrates the highest tolerance to discretisation error, maintaining stable closed-loop dynamics even under coarse integration. Higher-accuracy numerical schemes substantially improve learning efficiency. The RK4 configuration produces smoother trajectories, reduced control energy, and faster convergence across all reinforcement learning algorithms. Quantitative analysis of trajectory stability, integrated error metrics, and reward statistics confirms that discretisation error directly propagates through the learning process and alters the resulting control policies. These findings provide new empirical evidence that numerical integration fidelity is a critical design factor for reinforcement learning environments involving dynamical systems. The study highlights the necessity of carefully selecting integration schemes when training reinforcement learning controllers for propulsion dynamics and other physics-based control applications.
Some of the metrics are blocked by your
consent settings
AI Act Compliance Within the MyHealth@EU Framework: Tutorial
(JMIR Publications Inc., 2025-11-10)
;
;
Dobreva, Jovana
;
Bukovec, Djansel
;
Gjorgjioski, Blagojche
Some of the metrics are blocked by your
consent settings
North Macedonia interprofessional dementia care (NOMAD) – personalized care plans for people with dementia and caregiver psychoeducation delivered at home by interprofessional teams
(Frontiers Media SA, 2024-04-10)
Novotni, Gabriela
;
Taneska, Marija
;
;
Fischer, Julia
;
Iloski, Svetlana
Introduction The increasing number of people living with dementia and its burden on families and systems particularly in low- and middle-income countries require comprehensive and efficient post-diagnostic management. This study aimed to explore the acceptability and efficacy of a multi-professional case management and psychoeducation model (North Macedonia Interprofessional Dementia Care, or NOMAD) delivered by mobile teams for people with dementia and their caregivers in North Macedonia. Method We conducted a two-arm randomized controlled trial comparing the intervention with treatment as usual. Participants were recruited from 12 general practitioner (GP) offices in the Skopje region. The NOMAD intervention included the delivery of a personalized care plan over four home visits to dyads of people with dementia and their caregivers by a team including a dementia nurse and a social worker, in collaboration with GPs and dementia experts, and the introduction of a caregiver manual. We assessed caregivers' depressive symptoms, burden, and quality of life and the neuropsychiatric symptoms, daily living activities, and service utilization of people with dementia at baseline and follow-up; we also assessed the acceptability of the intervention by analyzing case notes and attendance rates. Results One hundred and twenty dyads were recruited and randomized to either the control (n = 60) or the intervention group (n = 60). At follow-up, caregivers in the intervention group had, on average, scores that were 2.69 lower for depressive symptoms (95% CI [−4.75, −0.62], p = 0.012), and people with dementia had, on average, 11.32 fewer neuropsychiatric symptoms (95% CI [−19.74, −2.90], p = 0.009) and used, on average, 1.81 fewer healthcare services (95% CI [−2.61, −1.00], p < 0.001) compared to the control group. The completion of the home visits was 100%, but the intervention's acceptability was underpinned by relationship building, GP competencies, and resources to support families with dementia. There were no differences in the caregivers' quality of life and burden levels or daily living activities in people with dementia. NOMAD is the first case management, non-pharmacological, and multi-professional intervention tested in North Macedonia. Discussion The trial showed that it is effective in reducing caregivers' depressive symptoms and neuropsychiatric symptoms in people with dementia and the burden on health and social care services, and it is acceptable for families. Implementing NOMAD in practice will require building primary care capacity and recognizing dementia as a national priority.
Some of the metrics are blocked by your
consent settings
On dementia, duties, and daughters. An ethical analysis of healthcare professionals being confronted with conflicts regarding filial duties in informal dementia care
(Frontiers Media SA, 2024-10-01)
Dogan, Vildan
;
Taneska, Marija
;
Novotni, Gabriela
;
Iloski, Svetlana
;
Background Existing literature on moral conflicts that healthcare professionals encounter in dementia care has explored, amongst others, issues related to autonomy, decision-making capacity, privacy, and more. Notably, conflicts related to healthcare professionals who support informal dementia caregiving and who are confronted with family members being overburdened with their care responsibly remains an underexplored topic in the current literature, particularly in the context of Low-and Middle-Income Countries. The present paper introduces such an encounter, presenting an ethical case analysis of a conflict that occurred during a larger research project conducted in North Macedonia. Case to be studied Due to the absence of formal care services that could have relieved an overburdened family caregiver, healthcare professionals felt compelled to reach out to the uninvolved adult daughters, requesting them to participate in their parents’ care. Wondering about whether their reaching out to the daughters might count as an attempt of pressure and undue interference, professionals conflicted over the appropriateness of their action. This paper follows up on their concern, ethically assessing the professionals’ action. To answer the question on whether the healthcare professionals acted appropriately or not, and to what extent, theories of filial duties are applied, embedding their action in the larger context of dementia care in North Macedonia. Results and conclusion It is argued that the lack of formal care services in North Macedonia is of utmost relevance to the conflict. Thus, the conclusion is that the ethical inappropriateness of the case is to be located not so much with the action of the healthcare professionals but with the state because of its failure to provide professional care services that allow healthcare professionals to take ethically sound actions to counteract overarching burdens that family members face when providing informal dementia care
Some of the metrics are blocked by your
consent settings
AI in Software Testing: Revolutionizing Quality Assurance
(IEEE, 2024-11-26)
Trifunova, Andrea
;
;
;
Artificial intelligence (AI) is an area of tremendous potential, especially in the software testing domain, where it has changed the dynamics of the process, storms in efficiency, accuracy, and flexibility in a given SDLC. This paper presents findings from recent investigations of AI in the testing and quality assurance focusing on its transformational potential. Particular attention is paid to such issues as automation of testing processes through AI, testing process enhancement, and possible changes in software engineering due to AI implementation. In this paper, various research perspectives have been integrated to reveal the effectiveness of AI in enhancing the perceived quality assurance processes, improving product quality, and adopting principles of agile methodology in today's software development.
Some of the metrics are blocked by your
consent settings
Cross‐cultural Adaptation and Psychometric Evaluation of the Macedonian C‐DEMQOL: A Carer Quality of Life Measure using data from the NOMAD Trial
(Wiley, 2025-12)
Ivanovska, Andrea
;
Taneska, Marija
;
Farina, Nicolas
;
;
Iloski, Svetlana
Background Caregivers of people with dementia face reduced quality of life, especially in Low‐ and Middle‐Income Countries, due to various systemic, social, and cultural challenges. Accurate measurement of their quality of life is essential for shaping policies and evaluating interventions. In North Macedonia, over 30,000 people with dementia rely mainly on family caregivers, who receive little to no support, resulting in significant stress and burden. However, no validated tools currently exist to measure caregivers’ quality of life. This study aimed to assess the psychometric properties of C‐DEMQOL, a reliable and valid tool for evaluating caregiver quality of life, in a North Macedonian context. Method The C‐DEMQOL was back‐translated, and three cognitive interviews with caregivers were conducted to confirm cultural relevance and face validity. Then it was administered to 120 dyads of individuals with dementia and their caregivers as part of the NOMAD (North Macedonia Interprofessional Dementia Care) trial. The internal consistency (Omega) was reported for the entire C‐DEMQOL measure and each subscale. Data were limited to baseline responses. Intraclass correlation was used to estimate the test‐retest reliability of control data by comparing baseline and follow‐up measurements. Convergent validity was assessed through correlations with the Patient Health Questionnaire (PHQ) and the Zarit Burden Inventory (ZBI), while discriminant validity was evaluated by examining correlations with the age and gender of the person with dementia. Result C‐DEMQOL demonstrated excellent internal consistency, with four of the five subdomains showing acceptable to excellent internal consistency. The total C‐DEMQOL score also demonstrated good test‐retest reliability, and most subdomains reached acceptable levels. Only the “Feeling supported” subdomain showed weaker internal consistency and test‐retest reliability. Convergent validity was indicated by moderate to large negative correlations with the PHQ and ZBI, while near‐zero correlations with the person with dementia's age and gender supported discriminant validity. Conclusion The Macedonian C‐DEMQOL is the first caregiver quality‐of‐life measure in Macedonian to demonstrate satisfactory validity and reliability. Further qualitative and quantitative analyses could help enhance the psychometric properties and optimize the final measure. Validating the C‐DEMQOL paves the way for accurately assessing the effectiveness of initiatives aimed at improving caregivers' quality of life.
Some of the metrics are blocked by your
consent settings
Advancing AI in Higher Education: A Comparative Study of Large Language Model-Based Agents for Exam Question Generation, Improvement, and Evaluation
(MDPI AG, 2025-03-04)
Nikolovski, Vlatko
;
;
The transformative capabilities of large language models (LLMs) are reshaping educational assessment and question design in higher education. This study proposes a systematic framework for leveraging LLMs to enhance question-centric tasks: aligning exam questions with course objectives, improving clarity and difficulty, and generating new items guided by learning goals. The research spans four university courses—two theory-focused and two application-focused—covering diverse cognitive levels according to Bloom’s taxonomy. A balanced dataset ensures representation of question categories and structures. Three LLM-based agents—VectorRAG, VectorGraphRAG, and a fine-tuned LLM—are developed and evaluated against a meta-evaluator, supervised by human experts, to assess alignment accuracy and explanation quality. Robust analytical methods, including mixed-effects modeling, yield actionable insights for integrating generative AI into university assessment processes. Beyond exam-specific applications, this methodology provides a foundational approach for the broader adoption of AI in post-secondary education, emphasizing fairness, contextual relevance, and collaboration. The findings offer a comprehensive framework for aligning AI-generated content with learning objectives, detailing effective integration strategies, and addressing challenges such as bias and contextual limitations. Overall, this work underscores the potential of generative AI to enhance educational assessment while identifying pathways for responsible implementation.

Faculty of Computer Science and Engineering

Browse

Filters

Settings

Sort By

Results per page

Search Results