Ali A. Elrowayati
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Ali A. Elrowayati has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Mohammad Faiz Liew Abdullah
Universiti Tun Hussein Onn Malaysia
3 shared publications Azizah Abd Manaf
Faculty of Electrical and Electronic Engineering, Universiti Tun Hussein Onn Malaysia (UTHM), Malaysia
2 shared publicationsAbd. S. Alfagi
Universiti Teknologi Malaysia
1 shared publicationAbdalrahman S. Alfagi
Faculty of Electrical and Electronic Engineering, Universiti Tun Hussein Onn Malaysia (UTHM), Malaysia
1 shared publication- Abdulbaset Albaour
Misurata University, Faculty of IT
1 shared publication Ali Abdrhman M. Ukasha
1 shared publication
Latest Publications
- Open Access
- 6 January 2026
- Published by Digitodontics International Academy in Journal of Technology Research
- Vol. 4 (special) , 865-879
Arabic Fake News Detection Using Genetically Optimized Deep Learning Models
In recent years, the proliferation of fake news across social media and digital platforms has significantly undermined public trust in traditional media outlets, raising serious challenges at the social, political, and health levels. Within the Arabic context, this problem is further exacerbated by the scarcity of effective tools for Arabic language processing. This study proposes a hybrid model that combines AraBERT for extracting deep contextual representations, Convolutional Neural Networks (CNN) for capturing local features, and a Genetic Algorithm (GA) for hyperparameter optimization. The model was evaluated on an Arabic dataset consisting of real and fake news articles, while class imbalance was addressed using class weights. Experimental results show that the GA-optimized AraBERT-CNN hybrid model outperformed both traditional (LSTM) and modern (pure AraBERT) baselines, achieving an overall accuracy more than 96% and higher F1-scores for the minority class (real news). The significance of this study lies in presenting a comprehensive framework that integrates the contextual power of transformer-based models with the adaptive optimization of evolutionary algorithms, thereby contributing to ongoing efforts to combat misinformation in Arabic and to develop more reliable intelligent news verification systems.
- 6 January 2026
- Published by Digitodontics International Academy in Journal of Technology Research
- Vol. 4 (special) , 865-879
Open AccessArabic Fake News Detection Using Genetically Optimized Deep Learning Models
In recent years, the proliferation of fake news across social media and digital platforms has significantly undermined public trust in traditional media outlets, raising serious challenges at the social, political, and health levels. Within the Arabic context, this problem is further exacerbated by the scarcity of effective tools for Arabic language processing. This study proposes a hybrid model that combines AraBERT for extracting deep contextual representations, Convolutional Neural Networks (CNN) for capturing local features, and a Genetic Algorithm (GA) for hyperparameter optimization. The model was evaluated on an Arabic dataset consisting of real and fake news articles, while class imbalance was addressed using class weights. Experimental results show that the GA-optimized AraBERT-CNN hybrid model outperformed both traditional (LSTM) and modern (pure AraBERT) baselines, achieving an overall accuracy more than 96% and higher F1-scores for the minority class (real news). The significance of this study lies in presenting a comprehensive framework that integrates the contextual power of transformer-based models with the adaptive optimization of evolutionary algorithms, thereby contributing to ongoing efforts to combat misinformation in Arabic and to develop more reliable intelligent news verification systems.
- 1 December 2025
- Published by Digitodontics International Academy in Journal of Technology Research
- Vol. 3 (2) , 92-102
An Efficient Hybrid MobileNetV3–LightGBM Framework for Image-Based Malware Detection
Traditional signature-based malware detection techniques have become inadequate in addressing the complexity of modern cybersecurity threats. To overcome these limitations, this paper presents an intelligent malware classification framework that leverages computer vision and deep learning. The Malimg dataset, consisting of grayscale images representing diverse malware families, was utilized to facilitate structural and behavioural feature extraction. The hybrid MobileNetV3–LightGBM model proposed in this paper combines the lightweight MobileNetV3 architecture for efficient deep feature representation with the Light Gradient Boosting Machine (LightGBM) for robust and accurate classification. Experimental results demonstrate that the proposed model outperforms conventional deep learning approaches such as CNN and CNN–SVM, achieving an accuracy of 97.6%, with precision, recall, and F1-score averaging 98%. These findings confirm that integrating lightweight convolutional networks with gradient-boosted decision techniques significantly enhances malware detection performance and generalization. The proposed framework provides a scalable and effective solution for real-time malware analysis and establishes a foundation for future research on adaptive and explainable AI-driven cybersecurity systems.
- 1 December 2025
- Published by Digitodontics International Academy in Journal of Technology Research
- Vol. 3 (2) , 92-102
An Efficient Hybrid MobileNetV3–LightGBM Framework for Image-Based Malware Detection
Traditional signature-based malware detection techniques have become inadequate in addressing the complexity of modern cybersecurity threats. To overcome these limitations, this paper presents an intelligent malware classification framework that leverages computer vision and deep learning. The Malimg dataset, consisting of grayscale images representing diverse malware families, was utilized to facilitate structural and behavioural feature extraction. The hybrid MobileNetV3–LightGBM model proposed in this paper combines the lightweight MobileNetV3 architecture for efficient deep feature representation with the Light Gradient Boosting Machine (LightGBM) for robust and accurate classification. Experimental results demonstrate that the proposed model outperforms conventional deep learning approaches such as CNN and CNN–SVM, achieving an accuracy of 97.6%, with precision, recall, and F1-score averaging 98%. These findings confirm that integrating lightweight convolutional networks with gradient-boosted decision techniques significantly enhances malware detection performance and generalization. The proposed framework provides a scalable and effective solution for real-time malware analysis and establishes a foundation for future research on adaptive and explainable AI-driven cybersecurity systems.
- Open Access
- 1 January 2024
- Published by Misurata University in The International Journal of Engineering & Information Technology (IJEIT)
- Vol. 11 (2) , 60-65
Investigated Signal-to-Noise Ratio for Terrestrial Free Space Optical based on Libya Cities Data
Free Space Optical (FSO) communication links offer high-speed data transmission but can be affected by weather conditions like rain, haze, fog, and snow. This study investigates the impact of rain on FSO link availability in the Libyan cities of Garian, Elkhoms, and Tripoli. An empirical model based on the ITU Carb. (France) Model is proposed to predict FSO link availability for ranges up to 5 km. Rain data shows that Garian has the highest rainfall, followed by Elkhoms and Tripoli. The study examines the effects of rainfall on FSO link performance for these three cities over a 5 km link distance. The results show that signal-to-noise ratio (SNR) and received power at the FSO link are influenced by both rainfall and path length. For a 2 km link distance, the SNR ranges from 16 dB in Tripoli to 10 dB in Garian. Under the influence of rain, the SNR varies from 45 dB to 5 dB over a link distance of 1 km to 5 km.
- 1 January 2024
- Published by Misurata University in The International Journal of Engineering & Information Technology (IJEIT)
- Vol. 11 (2) , 60-65
Open AccessInvestigated Signal-to-Noise Ratio for Terrestrial Free Space Optical based on Libya Cities Data
Free Space Optical (FSO) communication links offer high-speed data transmission but can be affected by weather conditions like rain, haze, fog, and snow. This study investigates the impact of rain on FSO link availability in the Libyan cities of Garian, Elkhoms, and Tripoli. An empirical model based on the ITU Carb. (France) Model is proposed to predict FSO link availability for ranges up to 5 km. Rain data shows that Garian has the highest rainfall, followed by Elkhoms and Tripoli. The study examines the effects of rainfall on FSO link performance for these three cities over a 5 km link distance. The results show that signal-to-noise ratio (SNR) and received power at the FSO link are influenced by both rainfall and path length. For a 2 km link distance, the SNR ranges from 16 dB in Tripoli to 10 dB in Garian. Under the influence of rain, the SNR varies from 45 dB to 5 dB over a link distance of 1 km to 5 km.
- Open Access
- 22 June 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 114172-114189
HEVC Watermarking Techniques for Authentication and Copyright Applications: Challenges and Opportunities
Recently, High-Efficiency Video Coding (HEVC/H.265) has been chosen to replace previous video coding standards, such as H.263 and H.264. Despite the efficiency of HEVC, it still lacks reliable and practical functionalities to support authentication and copyright applications. In order to provide this support, several watermarking techniques have been proposed by many researchers during the last few years. However, those techniques are still suffering from many issues that need to be considered for future designs. In this paper, a Systematic Literature Review (SLR) is introduced to identify HEVC challenges and potential research directions for interested researchers and developers. The time scope of this SLR covers all research articles published during the last six years starting from January 2014 up to the end of April 2020. Forty-two articles have met the criteria of selection out of 343 articles published in this area during the mentioned time scope. A new classification has been drawn followed by an identification of the challenges of implementing HEVC watermarking techniques based on the analysis and discussion of those chosen articles. Eventually, recommendations for HEVC watermarking techniques have been listed to help researchers to improve the existing techniques or to design new efficient ones.
- 22 June 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 114172-114189
Open AccessHEVC Watermarking Techniques for Authentication and Copyright Applications: Challenges and Opportunities
Recently, High-Efficiency Video Coding (HEVC/H.265) has been chosen to replace previous video coding standards, such as H.263 and H.264. Despite the efficiency of HEVC, it still lacks reliable and practical functionalities to support authentication and copyright applications. In order to provide this support, several watermarking techniques have been proposed by many researchers during the last few years. However, those techniques are still suffering from many issues that need to be considered for future designs. In this paper, a Systematic Literature Review (SLR) is introduced to identify HEVC challenges and potential research directions for interested researchers and developers. The time scope of this SLR covers all research articles published during the last six years starting from January 2014 up to the end of April 2020. Forty-two articles have met the criteria of selection out of 343 articles published in this area during the mentioned time scope. A new classification has been drawn followed by an identification of the challenges of implementing HEVC watermarking techniques based on the analysis and discussion of those chosen articles. Eventually, recommendations for HEVC watermarking techniques have been listed to help researchers to improve the existing techniques or to design new efficient ones.
- 1 November 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 174-179
Tampering detection of double-compression with the same quantization parameter in HEVC video streams
High-Efficiency Video Coding (HEVC) is a new video codec scheme, which has been published lately in 2013 by the ITU-T and ISO/IEC. The HEVC codec standards is a compressed video format; thus, its content cannot intentionally tamper unless decoding the video streams into to the spatial domain. In order for attackers to tamper any HEVC video content, the video stream should be initially decompressed into frames, then re-compressed. Recently, the video tampering detection has been used as a tool for supporting forensics and authentication process. By detecting the second compression, the integrity of video contents can be authenticated. In this paper, a novel method for distinguishing double-compression in HEVC is proposed, even if the same quantization parameter value is used in both compression processes. Our method is based on analyzing changes in the quantized residual DST coefficients and the values of intra-prediction modes. This approach increases the ability to discriminate the single and double compression in HEVC sequence streams, which can be utilized as an indication of double compression tampering. Several HEVC video classes are used to carry out the experiments, where the results show a high level of accuracy and efficiency for most quantization parameter values.
- 1 November 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 174-179
Tampering detection of double-compression with the same quantization parameter in HEVC video streams
High-Efficiency Video Coding (HEVC) is a new video codec scheme, which has been published lately in 2013 by the ITU-T and ISO/IEC. The HEVC codec standards is a compressed video format; thus, its content cannot intentionally tamper unless decoding the video streams into to the spatial domain. In order for attackers to tamper any HEVC video content, the video stream should be initially decompressed into frames, then re-compressed. Recently, the video tampering detection has been used as a tool for supporting forensics and authentication process. By detecting the second compression, the integrity of video contents can be authenticated. In this paper, a novel method for distinguishing double-compression in HEVC is proposed, even if the same quantization parameter value is used in both compression processes. Our method is based on analyzing changes in the quantized residual DST coefficients and the values of intra-prediction modes. This approach increases the ability to discriminate the single and double compression in HEVC sequence streams, which can be utilized as an indication of double compression tampering. Several HEVC video classes are used to carry out the experiments, where the results show a high level of accuracy and efficiency for most quantization parameter values.
- 31 May 2016
- Published by NADIA in International Journal of Security and Its Applications
- Vol. 10 (5) , 107-118
Digital Image Watermarking Based On Joint (DCT-DWT) and Arnold Transform
- 31 May 2016
- Published by NADIA in International Journal of Security and Its Applications
- Vol. 10 (5) , 107-118
Digital Image Watermarking Based On Joint (DCT-DWT) and Arnold Transform
- 31 January 2016
- Published by Global Vision Press in International Journal of Software Engineering and Its Applications
- Vol. 10 (1) , 263-270
Robust HEVC Video Watermarking Scheme Based on Repetition- BCH Syndrome Code
- 31 January 2016
- Published by Global Vision Press in International Journal of Software Engineering and Its Applications
- Vol. 10 (1) , 263-270
Robust HEVC Video Watermarking Scheme Based on Repetition- BCH Syndrome Code