Touqeer Ahmed Jumani
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Touqeer Ahmed Jumani has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Muhammad I. Masud
Department of Electrical Engineering, College of Engineering, University of Business and Technology, Jeddah 21361, Saudi Arabia
3 shared publications - Zeeshan Ahmad Arfeen
Department of Electrical Engineering, The Islamia University of Bahawalpur (IUB), Bahawalpur 63100, Pakistan
3 shared publications - Abdur Raheem
Department of Electrical Engineering, Faculty of Engineering & Technology, The Islamia University of Bahawalpur, Bahawalpur 63100, Punjab, Pakistan
2 shared publications - Muhammad Rashid
Department of Electrical Engineering, Faculty of Engineering & Technology, The Islamia University of Bahawalpur, Bahawalpur 63100, Punjab, Pakistan
2 shared publications - Rabia Shakoor
Department of Electrical Engineering, Faculty of Engineering & Technology, The Islamia University of Bahawalpur, Bahawalpur 63100, Punjab, Pakistan
2 shared publications - Abdul Basit
Department of Information and Communication Engineering, The Islamia University of Bahawalpur (IUB), Bahawalpur 63100, Southern Punjab, Pakistan
1 shared publication
Latest Publications
- Top Cited PapersOpen Access
A Comprehensive Review of Deepfake Detection Techniques: From Traditional Machine Learning to Advanced Deep Learning Architectures
Deepfake technology is causing unprecedented threats to the authenticity of digital media, and demand is high for reliable digital media detection systems. This systematic review focuses on an analysis of deepfake detection methods using deep learning approaches, machine learning methods, and the classical methods of image processing from 2018 to 2025 with a specific focus on the trade-off between accuracy, computing efficiency, and cross-dataset generalization. Through lavish analysis of a robust peer-reviewed studies using three benchmark data sets (FaceForensics++, DFDC, Celeb-DF) we expose important truths to bring some of the field’s prevailing assumptions into question. Our analysis produces three important results that radically change the understanding of detection abilities and limitations. Transformer-based architectures have significantly better cross-dataset generalization (11.33% performance decline) than CNN-based (more than 15% decline), at the expense of computation (3–5× more). To the contrary, there is no strong reason to assume the superiority of deep learning, and the performance of traditional machine learning methods (in our case, Random Forest) is quite comparable (accuracy of 99.64% on the DFDC) with dramatically lower computing needs, which opens up the prospects for their application in resource-constrained deployment scenarios. Most critically, we demonstrate deterioration of performance (10–15% on average) systematically across all methodological classes and we provide empirical support for the fact that current detection systems are, to a high degree, learning dataset specific compression artifacts, rather than deepfake characteristics that are generalizable. These results highlight the importance of moving from an accuracy-focused evaluation approach toward more comprehensive evaluation approaches that balance either generalization capability, computational feasibility, or practical deployment constraints, and therefore further direct future research efforts towards designing systems for detection that could be deployed in practical applications.
Top Cited PapersOpen AccessA Comprehensive Review of Deepfake Detection Techniques: From Traditional Machine Learning to Advanced Deep Learning Architectures
Deepfake technology is causing unprecedented threats to the authenticity of digital media, and demand is high for reliable digital media detection systems. This systematic review focuses on an analysis of deepfake detection methods using deep learning approaches, machine learning methods, and the classical methods of image processing from 2018 to 2025 with a specific focus on the trade-off between accuracy, computing efficiency, and cross-dataset generalization. Through lavish analysis of a robust peer-reviewed studies using three benchmark data sets (FaceForensics++, DFDC, Celeb-DF) we expose important truths to bring some of the field’s prevailing assumptions into question. Our analysis produces three important results that radically change the understanding of detection abilities and limitations. Transformer-based architectures have significantly better cross-dataset generalization (11.33% performance decline) than CNN-based (more than 15% decline), at the expense of computation (3–5× more). To the contrary, there is no strong reason to assume the superiority of deep learning, and the performance of traditional machine learning methods (in our case, Random Forest) is quite comparable (accuracy of 99.64% on the DFDC) with dramatically lower computing needs, which opens up the prospects for their application in resource-constrained deployment scenarios. Most critically, we demonstrate deterioration of performance (10–15% on average) systematically across all methodological classes and we provide empirical support for the fact that current detection systems are, to a high degree, learning dataset specific compression artifacts, rather than deepfake characteristics that are generalizable. These results highlight the importance of moving from an accuracy-focused evaluation approach toward more comprehensive evaluation approaches that balance either generalization capability, computational feasibility, or practical deployment constraints, and therefore further direct future research efforts towards designing systems for detection that could be deployed in practical applications.
- Open Access
An Efficient Hybrid Evolutionary Algorithm for Enhanced Wind Energy Capture
An optimal topographical arrangement of wind turbines (WTs) is essential for increasing the total power production of a wind farm (WF). This work introduces PSO-GA, a newly formulated algorithm based on the hybrid of Particle Swarm Optimization (PSO) and the Genetic Algorithm (GA) method, to provide the best possible and reliable WF layout (WFL) for enhanced output power. Because GA improves on PSO-found solutions while PSO investigates several regions; therefore, hybrid PSO-GA can effectively handle issues involving multiple local optima. In the first phase of the framework, PSO improves the original variables; in the second phase, the variables are changed for improved fitness. The goal function takes into account both the power production of the WF and the cost per power while analyzing the wake loss using the Jenson wake model. To evaluate the robustness of this strategy, three case studies are analyzed. The algorithm identifies the best possible position of turbines and strictly complies with industry-standard separation distances to prevent extreme wake interference. This comparative study on the past layout improvement process models demonstrates that the proposed hybrid algorithm enhanced performance with a significant power improvement of 0.03–0.04% and a 24–27.3% reduction in wake loss. The above findings indicate that the proposed PSO-GA can be better than the other innovative methods, especially in the aspects of quality and consistency of the solution.
Open AccessAn Efficient Hybrid Evolutionary Algorithm for Enhanced Wind Energy Capture
An optimal topographical arrangement of wind turbines (WTs) is essential for increasing the total power production of a wind farm (WF). This work introduces PSO-GA, a newly formulated algorithm based on the hybrid of Particle Swarm Optimization (PSO) and the Genetic Algorithm (GA) method, to provide the best possible and reliable WF layout (WFL) for enhanced output power. Because GA improves on PSO-found solutions while PSO investigates several regions; therefore, hybrid PSO-GA can effectively handle issues involving multiple local optima. In the first phase of the framework, PSO improves the original variables; in the second phase, the variables are changed for improved fitness. The goal function takes into account both the power production of the WF and the cost per power while analyzing the wake loss using the Jenson wake model. To evaluate the robustness of this strategy, three case studies are analyzed. The algorithm identifies the best possible position of turbines and strictly complies with industry-standard separation distances to prevent extreme wake interference. This comparative study on the past layout improvement process models demonstrates that the proposed hybrid algorithm enhanced performance with a significant power improvement of 0.03–0.04% and a 24–27.3% reduction in wake loss. The above findings indicate that the proposed PSO-GA can be better than the other innovative methods, especially in the aspects of quality and consistency of the solution.
- Open Access
- 15 December 2025
- Published by MDPI AG in Preprints.org
An Efficient Hybrid Evolutionary Algorithm for Enhanced Wind Energy Capture
An optimal topographical arrangement of Wind Turbines (WTs) is essential for increasing the total power production of a Wind Farm (WF). This work introduces PSO-GA, a newly formulated algorithm based on the hybrid of Particle Swarm Optimization (PSO) and the Genetic Algorithm (GA) method, to provide the best possible and reliable WF Layout (WFL) for enhanced output power. Because GA improves on PSO-found solutions while PSO investigates several regions, PSO-GA can effectively handle issues with multiple local optima. In the first phase of the framework, PSO improves the original variables; in the second phase, variables are changed for improved fitness. The goal function takes into account both the power production of the WF and the total cost of WTs while analyzing wake upshot using the Jenson-Wake model. To evaluate the robustness of this strategy, three case studies are analyzed. The algorithm identifies the best possible position of turbines and strictly complies with industry-standard separation distances to prevent extreme wake interference. The comparative study with the past layout improvement process models demonstrates that the proposed hybrid algorithm has enhanced performance with the power improvement of 0.03-0.04% with the p value< 0.01 and 24-27.3% reduction in the wake loss. The above findings indicate that the proposed PSO-GA can be better than the other innovative methods, especially in the aspects of quality and consistency of the solution.
- 15 December 2025
- Published by MDPI AG in Preprints.org
Open AccessAn Efficient Hybrid Evolutionary Algorithm for Enhanced Wind Energy Capture
An optimal topographical arrangement of Wind Turbines (WTs) is essential for increasing the total power production of a Wind Farm (WF). This work introduces PSO-GA, a newly formulated algorithm based on the hybrid of Particle Swarm Optimization (PSO) and the Genetic Algorithm (GA) method, to provide the best possible and reliable WF Layout (WFL) for enhanced output power. Because GA improves on PSO-found solutions while PSO investigates several regions, PSO-GA can effectively handle issues with multiple local optima. In the first phase of the framework, PSO improves the original variables; in the second phase, variables are changed for improved fitness. The goal function takes into account both the power production of the WF and the total cost of WTs while analyzing wake upshot using the Jenson-Wake model. To evaluate the robustness of this strategy, three case studies are analyzed. The algorithm identifies the best possible position of turbines and strictly complies with industry-standard separation distances to prevent extreme wake interference. The comparative study with the past layout improvement process models demonstrates that the proposed hybrid algorithm has enhanced performance with the power improvement of 0.03-0.04% with the p value< 0.01 and 24-27.3% reduction in the wake loss. The above findings indicate that the proposed PSO-GA can be better than the other innovative methods, especially in the aspects of quality and consistency of the solution.