Aleksandar Jokic
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Aleksandar Jokic has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Luka Jovanovic
Singidunum University
4 shared publications - Nebojsa Bacanin
Singidunum University, Belgrade, Serbia
4 shared publications - Milos Antonijevic
Singidunum University
3 shared publications - Miodrag Zivkovic
Faculty of Informatics and Computing, Singidunum University, Danijelova 32, Belgrade 11000, Serbia
3 shared publications - Marina Milovanovic
Faculty of Informatics and Computing, Singidunum University, Danijelova 32, 11010 Belgrade, Serbia
2 shared publications - Marko Sarac
Faculty of Informatics and Computing, Singidunum University, Danijelova 32, 11000 Belgrade, Serbia
2 shared publications
Latest Publications
- 24 October 2025
- Published by Springer Nature
- p. 43-57
Ocular Disease Diagnosis Using Convolutional Neural Networks Optimized by Genetic Particle Swarm Optimization
- 24 October 2025
- Published by Springer Nature
- p. 43-57
Ocular Disease Diagnosis Using Convolutional Neural Networks Optimized by Genetic Particle Swarm Optimization
- 1 September 2025
- Published by Springer Nature
- p. 153-167
Optimizing AdaBoost by Modified Metaheuristic for Fake News Detection
- 1 September 2025
- Published by Springer Nature
- p. 153-167
Optimizing AdaBoost by Modified Metaheuristic for Fake News Detection
- 5 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Improving Fake News Detection on Social Media Platforms Using Modified Metaheuristics and Machine Learning
Social networking and emerging technologies have fundamentally reshaped personal connectivity online. Despite the increasing reliance on the internet for everyday tasks, entertainment, and community building by businesses, corporations, and individuals, online social interactions continue to pose challenges. Misuse of social platforms can lead to the spread of misinformation. This issue has brought the emergence of fake news to the forefront of societal concerns. The vast volumes of data and rapidly evolving language used on social media platforms render traditional approaches, like static filter lists, ineffective. This study proposes a data-driven approach leveraging applied AI to detect and mitigate online misinformation using advanced natural language processing (NLP) techniques. A modified particle swarm optimization (PSO) algorithm is introduced for hyperparameter optimization, demonstrating promising results in maximizing performance. A comparative analysis across several contemporary optimizers on a real-world dataset demonstrates the efficacy of the proposed approach, achieving an accuracy of 0.846620 with the best-optimized models.
- 5 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Improving Fake News Detection on Social Media Platforms Using Modified Metaheuristics and Machine Learning
Social networking and emerging technologies have fundamentally reshaped personal connectivity online. Despite the increasing reliance on the internet for everyday tasks, entertainment, and community building by businesses, corporations, and individuals, online social interactions continue to pose challenges. Misuse of social platforms can lead to the spread of misinformation. This issue has brought the emergence of fake news to the forefront of societal concerns. The vast volumes of data and rapidly evolving language used on social media platforms render traditional approaches, like static filter lists, ineffective. This study proposes a data-driven approach leveraging applied AI to detect and mitigate online misinformation using advanced natural language processing (NLP) techniques. A modified particle swarm optimization (PSO) algorithm is introduced for hyperparameter optimization, demonstrating promising results in maximizing performance. A comparative analysis across several contemporary optimizers on a real-world dataset demonstrates the efficacy of the proposed approach, achieving an accuracy of 0.846620 with the best-optimized models.
- 28 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 903-907
Exploring Power Line Arc Detection Using YOLOv8 Computer Vision Models
The power grid stands as a cornerstone of modern living, facilitating infrastructure, industry, and daily conveniences through a reliable supply of electricity. However, the transmission of power is beset by challenges such as maintenance costs, malfunctions, and losses due to resistance. Of particular concern in high voltage transmission lines is the occurrence of electrical arcing, stemming from environmental factors, debris, or grid damage. This study delves into the comparative analysis of various architectures of the YOLOv8 model for arc detection. The results showcase the high accuracy of the YOLOv8 m model, demonstrating its robust performance in accurately detecting and localizing objects in complex and dynamic environments. Future research prospects include the utilization of larger datasets to enhance model performance for broader applicability across diverse scenarios in power grid operations.
- 28 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 903-907
Exploring Power Line Arc Detection Using YOLOv8 Computer Vision Models
The power grid stands as a cornerstone of modern living, facilitating infrastructure, industry, and daily conveniences through a reliable supply of electricity. However, the transmission of power is beset by challenges such as maintenance costs, malfunctions, and losses due to resistance. Of particular concern in high voltage transmission lines is the occurrence of electrical arcing, stemming from environmental factors, debris, or grid damage. This study delves into the comparative analysis of various architectures of the YOLOv8 model for arc detection. The results showcase the high accuracy of the YOLOv8 m model, demonstrating its robust performance in accurately detecting and localizing objects in complex and dynamic environments. Future research prospects include the utilization of larger datasets to enhance model performance for broader applicability across diverse scenarios in power grid operations.
- Open Access
- 2 August 2024
- Published by Atlantis Press SARL
- p. 155-170
Structured query language injection detection with natural language processing techniques optimized by metaheuristics
- 2 August 2024
- Published by Atlantis Press SARL
- p. 155-170
Open AccessStructured query language injection detection with natural language processing techniques optimized by metaheuristics
- Open Access
- 1 January 2023
- Published by Singidunum University
- p. 36-43
Next-generation Firewall and Artificial Intelligence
As cyber threats evolve and become more sophisticated, the need for advanced network security solutions continues to grow
- 1 January 2023
- Published by Singidunum University
- p. 36-43
Open AccessNext-generation Firewall and Artificial Intelligence
As cyber threats evolve and become more sophisticated, the need for advanced network security solutions continues to grow
- Open Access
- 1 January 2022
- Published by Singidunum University
- p. 421-426
Cyber Security and Domain Name Systems Deploy and Protect Network With DNS Sinkhole Blackhole
DNS is a protocol within the standards for how computers exchange data on the Internet, known as TCP/IP protocol suite
- 1 January 2022
- Published by Singidunum University
- p. 421-426
Open AccessCyber Security and Domain Name Systems Deploy and Protect Network With DNS Sinkhole Blackhole
DNS is a protocol within the standards for how computers exchange data on the Internet, known as TCP/IP protocol suite