Nikola Stanić
Research Subjects
Nikola Stanić has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Katarina Karić3 shared publications
- Stefan Ćirković
University of Kragujevac
3 shared publications - Andrijana Gaborović
Faculty of Technical Sciences Cacak, University of Kragujevac, 32000 Cacak, Serbia
2 shared publications - Jelena Plašić
Faculty of Technical Sciences Cacak, University of Kragujevac, 32000 Cacak, Serbia
2 shared publications
Latest Publications
- 1 January 2026
- Published by University Library in Kragujevac
- p. 216-222
Identifying Associations Between Patient Symptoms and Diseases Using the Apriori Algorithm
This paper applies association rule mining techniques, with a focus on the Apriori algorithm, to analyze relationships between symptoms and diseases in medical datasets. The study aims to identify meaningful combinations of symptoms that indicate the presence of specific diseases and to demonstrate the capability of data mining methods in potentially informing clinical reasoning, subject to further validation. The dataset used in this study contains patient information, including symptoms, demographic characteristics, and diagnostic outcomes. After data preprocessing and transformation into a suitable format using one-hot encoding, the Apriori algorithm was applied to extract frequent itemsets and generate association rules. The rules were evaluated using standard metrics such as support, confidence, and lift, allowing the identification of the most relevant and strongly associated patterns. The results reveal notable associations between symptoms and diagnoses. The derived rules demonstrate strong, marked associations between multiple symptoms and disease presence, particularly asthma, as well as potentially important factors such as gender and blood pressure. The findings suggest that association rule mining can serve as a valuable tool in healthcare analytics, contributing to improved understanding of disease patterns and potentially informing clinical decisions, subject to validation.
- 1 January 2026
- Published by University Library in Kragujevac
- p. 216-222
Identifying Associations Between Patient Symptoms and Diseases Using the Apriori Algorithm
This paper applies association rule mining techniques, with a focus on the Apriori algorithm, to analyze relationships between symptoms and diseases in medical datasets. The study aims to identify meaningful combinations of symptoms that indicate the presence of specific diseases and to demonstrate the capability of data mining methods in potentially informing clinical reasoning, subject to further validation. The dataset used in this study contains patient information, including symptoms, demographic characteristics, and diagnostic outcomes. After data preprocessing and transformation into a suitable format using one-hot encoding, the Apriori algorithm was applied to extract frequent itemsets and generate association rules. The rules were evaluated using standard metrics such as support, confidence, and lift, allowing the identification of the most relevant and strongly associated patterns. The results reveal notable associations between symptoms and diagnoses. The derived rules demonstrate strong, marked associations between multiple symptoms and disease presence, particularly asthma, as well as potentially important factors such as gender and blood pressure. The findings suggest that association rule mining can serve as a valuable tool in healthcare analytics, contributing to improved understanding of disease patterns and potentially informing clinical decisions, subject to validation.
- 4 August 2025
- Published by Akademska Misao
- p. 54-59
Exploring AI tools in education: Analyzing benefits, challenges, and student engagement
Artificial Intelligence (AI) tools are transforming education by enhancing learning, improving efficiency, and supporting educators. This paper explores AI-powered educational tools, analyzing their benefits, challenges, and impact on learning. Key applications, such as personalized learning platforms, intelligent tutoring systems, automated grading, and content generation, are evaluated for effectiveness and limitations. A survey of Information Technology students at the Faculty of Technical Sciences in Čačak shows a high level of familiarity and use of AI tools, with most students viewing them as beneficial. However, concerns about misinformation, over-reliance, and ethics highlight the need for responsible AI integration. The paper suggests strategies for incorporating AI into education, emphasizing transparency, ethics, and guidance. By ensuring a structured approach, AI can complement education without replacing critical thinking and problem-solving skills.
- 4 August 2025
- Published by Akademska Misao
- p. 54-59
Exploring AI tools in education: Analyzing benefits, challenges, and student engagement
Artificial Intelligence (AI) tools are transforming education by enhancing learning, improving efficiency, and supporting educators. This paper explores AI-powered educational tools, analyzing their benefits, challenges, and impact on learning. Key applications, such as personalized learning platforms, intelligent tutoring systems, automated grading, and content generation, are evaluated for effectiveness and limitations. A survey of Information Technology students at the Faculty of Technical Sciences in Čačak shows a high level of familiarity and use of AI tools, with most students viewing them as beneficial. However, concerns about misinformation, over-reliance, and ethics highlight the need for responsible AI integration. The paper suggests strategies for incorporating AI into education, emphasizing transparency, ethics, and guidance. By ensuring a structured approach, AI can complement education without replacing critical thinking and problem-solving skills.
- 1 January 2025
- Published by University Library in Kragujevac
- p. 118-121
A Computationally Implemented Method for Assessing Air Pollution in Urban Traffic Based on Traffic Density Analysis
Monitoring and assessing air pollution levels in urban areas represents a key challenge in environmental protection and traffic management. This paper proposes a computationally implemented method for indirect air pollution assessment based on traffic density analysis, eliminating the need for direct sensor-based measurements of pollutant concentrations. The proposed system employs computer vision for real-time vehicle detection and classification, while air pollution levels are estimated using a mathematical model that accounts for the average emission rates per vehicle. The system architecture includes an embedded computer (Raspberry Pi) for video data processing, network infrastructure connectivity, and data transmission to a central server for further analysis and visualization. Experimental results confirm that the proposed approach enables reliable and efficient air pollution assessment under real-world conditions, opening avenues for enhancing environmental monitoring strategies and optimizing traffic flow in urban environments.
- 1 January 2025
- Published by University Library in Kragujevac
- p. 118-121
A Computationally Implemented Method for Assessing Air Pollution in Urban Traffic Based on Traffic Density Analysis
Monitoring and assessing air pollution levels in urban areas represents a key challenge in environmental protection and traffic management. This paper proposes a computationally implemented method for indirect air pollution assessment based on traffic density analysis, eliminating the need for direct sensor-based measurements of pollutant concentrations. The proposed system employs computer vision for real-time vehicle detection and classification, while air pollution levels are estimated using a mathematical model that accounts for the average emission rates per vehicle. The system architecture includes an embedded computer (Raspberry Pi) for video data processing, network infrastructure connectivity, and data transmission to a central server for further analysis and visualization. Experimental results confirm that the proposed approach enables reliable and efficient air pollution assessment under real-world conditions, opening avenues for enhancing environmental monitoring strategies and optimizing traffic flow in urban environments.
- 1 January 2024
- Published by University Library in Kragujevac
- p. 53-59
Analysis of Approaches to Developing Kotlin Multiplatform Applications and Their Impact on Software Engineering
This paper explores the concept of Kotlin Multiplatform and analyzes the approach to developing multiplatform applications using this tool. The research aims to analyze the key features of Kotlin Multiplatform, including its ability to share code across different platforms such as Android, iOS, and web. Through a detailed analysis of existing literature and case studies, the paper will explore the advantages and challenges of developing multiplatform applications using Kotlin Multiplatform, as well as their impact on software engineering. Special attention will be paid to performance, scalability, and code management within Kotlin Multiplatform projects. Based on the gathered data, the paper will also explore future perspectives of multiplatform application development, including potential trends, technological advancements and other cross platform solutions.
- 1 January 2024
- Published by University Library in Kragujevac
- p. 53-59
Analysis of Approaches to Developing Kotlin Multiplatform Applications and Their Impact on Software Engineering
This paper explores the concept of Kotlin Multiplatform and analyzes the approach to developing multiplatform applications using this tool. The research aims to analyze the key features of Kotlin Multiplatform, including its ability to share code across different platforms such as Android, iOS, and web. Through a detailed analysis of existing literature and case studies, the paper will explore the advantages and challenges of developing multiplatform applications using Kotlin Multiplatform, as well as their impact on software engineering. Special attention will be paid to performance, scalability, and code management within Kotlin Multiplatform projects. Based on the gathered data, the paper will also explore future perspectives of multiplatform application development, including potential trends, technological advancements and other cross platform solutions.
- 1 January 2024
- Published by University Library in Kragujevac
- p. 83-88
Application of the YOLO algorithm for Medical Purposes in the Detection of Skin Cancer
Skin cancer is one of the most common forms of cancer worldwide. Exposure to ultraviolet (UV) radiation increases the risk of its development. Early preventive examinations and early detection of suspicious skin changes are key factors for successful treatment. Due to the rapid development of AI technologies, neural networks have found application in various fields, including medicine. Neural networks can be used to create various applications, which would facilitate self-examination for patients and alert them to potential problems. This method would further save time and reduce healthcare costs. The paper presents the application of a neural network using the YOLO (You Only Look Once) algorithm on a dataset of mole images with the aim of identifying and classifying moles, which facilitates early intervention and improves treatment outcomes.
- 1 January 2024
- Published by University Library in Kragujevac
- p. 83-88
Application of the YOLO algorithm for Medical Purposes in the Detection of Skin Cancer
Skin cancer is one of the most common forms of cancer worldwide. Exposure to ultraviolet (UV) radiation increases the risk of its development. Early preventive examinations and early detection of suspicious skin changes are key factors for successful treatment. Due to the rapid development of AI technologies, neural networks have found application in various fields, including medicine. Neural networks can be used to create various applications, which would facilitate self-examination for patients and alert them to potential problems. This method would further save time and reduce healthcare costs. The paper presents the application of a neural network using the YOLO (You Only Look Once) algorithm on a dataset of mole images with the aim of identifying and classifying moles, which facilitates early intervention and improves treatment outcomes.