Mitar Miki Tepić

Mitar Miki Tepić

Auto-generated profile, based on publicly available information

Mitar Miki Tepić


Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2025
Verified
Conference Paper
Closed access
MTMitar Miki Tepić
Mitar Miki Tepić
SPStefan Popović
Stefan Popović
Smart cities represent a key concept in modern urban planning, where smart water resource management plays a central role. This paper analyzes current Smart Water projects in Serbia, Bosnia and Herzegovina, Croatia, and Montenegro, with a special focus on the implementation of artificial intelligence (AI) and machine learning (ML). The emphasis is placed on practical examples such as water consumption prediction, leakage detection, and water quality monitoring.Through an analysis of projects like the Green AI initiative, the SMART-Water system, and innovations by the Kolektor Sisteh company, the paper examines the technologies and algorithms utilized. The main findings demonstrate the significant efficiency of AI/ML models in improving the sustainability of water resources and optimizing costs. However, challenges such as technical implementation and the lack of local expertise remain open issues.In conclusion, the paper provides a comprehensive overview of the current state and proposes future steps toward advancing AI/ML technologies within Smart Water projects in the Balkans.

1 January 2026
Verified
Conference Paper
Open access
PDF file
MTMitar Tepić
Mitar Tepić
SPStefan Mirko Popovic
Stefan Mirko Popovic
Contemporary challenges related to the green agenda increasingly highlight the need for simple, accessible, and efficient solutions for resource management. In this context, microcontroller systems play an important role in the design and control of energy-efficient systems, particularly in the fields of water management and heating. This paper examines their application in real-time data acquisition and processing, supported by sensor systems for monitoring key parameters. Special emphasis is placed on mathematical modeling and predictive approaches, which enable improved system control and reduction of losses. The results indicate that such solutions can be sustainable, flexible, and economically viable, while significantly contributing to the rational use of energy and water resources.

8 December 2025 in AlfaTech
Verified
Journal Article
Closed access
MTMitar Miki Tepić
Mitar Miki Tepić
SPSonja Djukić Popović
Sonja Djukić Popović
BTBranka Tepić
Branka Tepić
Smart water management is turning into one of the key elements for a sustainable water infrastructure in the Balkans. Systems based on collected data can solve major problems, such as leakage, pollution and inefficient water distribution. This paper explores the path from data to action using artificial intelligence and machine learning in regional smart water management projects. In the paper, a comparative analysis of the implementation of smart systems in Bosnia and Herzegovina, Croatia, Serbia and Montenegro was carried out, with a focus on predictive analytics, the application of edge AI technology and real-time decision support systems.This study introduces hybrid technologies that combine IoT with machine learning algorithms such as Random Forest,XGBoost, and Deep Q-Learning with the goal of adaptive water distribution.Results indicate that localized AI models can reduce network losses by up to 30 % and improve anomaly detection accuracy by 25 %. Despite financial and infrastructural limitations, the adoption of AI-powered smart water systems demonstrates a measurable impact on sustainability and operational efficiency. The paper concludes with a roadmap for regional collaboration and the standardization of AI-driven water management practices in the Balkans.