Abdullah Ghanim Jaber
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Abdullah Ghanim Jaber has a total of 31 co-authors. Here are the top co-authors by number of shared publications:
- Ravie Chandren Muniyandi
Centre for Cyber Security, Faculty of Information Science and Technology (FTSM), Universiti Kebangsaan Malaysia (UKM), Bangi 43600, Selangor, Malaysia
3 shared publications - Khairul Akram Zainol Ariffin
Centre for Cyber Security, Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia (UKM), Bangi 43600, Selangor, Malaysia
2 shared publications Mohammed Jamal Salim
University of Information Technology and Communications, 10067, Baghdad, Iraq
2 shared publicationsAbdumutalliev Abdulakhad Abdusamadugli
Turan International University,Faculty of Business Adminstration,Namangan,Uzbekistan
1 shared publicationAbeer Ahmed Ali
Department of Computer Science, College of Science, University of Dijlah, Baghdad, Iraq
1 shared publication- Abeer Ahmed Ali
University of Dijlah
1 shared publication
Latest Publications
- Open Access
- 30 September 2026
- Published by Mustansiriyah University in Al-Mustansiriyah Journal of Science
- Vol. 37 (3) , 86-121
Lung Disease Detection and Classification Based on AI, Deep Learning and Machine Learning: A Comprehensive Survey
Background: Lung diseases significantly contribute to substantial global morbidity and mortality, which pose considerable diagnostic challenges. Manual analysis of medical images like chest X-rays and CT scans is often subject to human error, requires specialized expertise, and is time-consuming. To build fully automated systems that analyze the information contained in medical images, robust and efficient algorithms are required. In response, artificial intelligence (AI), especially deep learning (DL), has become an innovative approach that shows excellent results for the automation of lung disease detection and classification. Objective: Following a strict systematic literature review methodology, this study aims to provide an extensive survey of artificial intelligence, machine learning, and deep learning approaches for the detection and classification of lung diseases. Methods: The survey discusses over 30 reported approaches in the field. These approaches have been categorized and evaluated based on the methodology and reported results. We also discuss relevant datasets and benchmarking that have been used in state-of-the-art models and have undergone peer review. Results: The survey reveals a strong trend towards powerful ensemble and hybrid architectures like ResNet, VGG, RVCNet, Vision Transformers (ViTs), etc., and their variations. These models have achieved high accuracy for detecting and classifying various diseases. Conclusions: This work highlights the advancement and recent progress in using AI and deep learning to detect and classify lung diseases while addressing identified gaps and the limitations related to dataset availability, standardization, and imbalance, in addition to model transparency and the computational cost, providing a prospective roadmap for further research or implementation.
- 30 September 2026
- Published by Mustansiriyah University in Al-Mustansiriyah Journal of Science
- Vol. 37 (3) , 86-121
Open AccessLung Disease Detection and Classification Based on AI, Deep Learning and Machine Learning: A Comprehensive Survey
Background: Lung diseases significantly contribute to substantial global morbidity and mortality, which pose considerable diagnostic challenges. Manual analysis of medical images like chest X-rays and CT scans is often subject to human error, requires specialized expertise, and is time-consuming. To build fully automated systems that analyze the information contained in medical images, robust and efficient algorithms are required. In response, artificial intelligence (AI), especially deep learning (DL), has become an innovative approach that shows excellent results for the automation of lung disease detection and classification. Objective: Following a strict systematic literature review methodology, this study aims to provide an extensive survey of artificial intelligence, machine learning, and deep learning approaches for the detection and classification of lung diseases. Methods: The survey discusses over 30 reported approaches in the field. These approaches have been categorized and evaluated based on the methodology and reported results. We also discuss relevant datasets and benchmarking that have been used in state-of-the-art models and have undergone peer review. Results: The survey reveals a strong trend towards powerful ensemble and hybrid architectures like ResNet, VGG, RVCNet, Vision Transformers (ViTs), etc., and their variations. These models have achieved high accuracy for detecting and classifying various diseases. Conclusions: This work highlights the advancement and recent progress in using AI and deep learning to detect and classify lung diseases while addressing identified gaps and the limitations related to dataset availability, standardization, and imbalance, in addition to model transparency and the computational cost, providing a prospective roadmap for further research or implementation.
- Open Access
- 23 September 2026
- Published by MDPI AG in Electronics
- Vol. 15 (19) , 4382
FOX-SHIELD: A Secure Encrypted-Domain Remote Sensing Image Classification Framework Using Chebyshev-SHA and Fox-Optimized FRNNs
Remote sensing (RS) images transmitted through distributed satellite, UAV, and sensor networks are vulnerable to interception and misuse, while conventional encryption may reduce the effectiveness of downstream image classification. This paper proposes FOX-SHIELD, a secure encrypted-domain remote sensing image classification framework that integrates Chebyshev-SHA dynamic encryption with a Fox-Optimized Fast Recurrent Neural Network. The Chebyshev-SHA module generates image-specific dynamic keys and applies permutation–diffusion encryption to protect image confidentiality and integrity. The encrypted image representation is then classified using an FRNN optimized by the Fox Optimization Algorithm to improve convergence, classification accuracy, and computational efficiency. Experiments on the UC Merced Land Use and NWPU-RESISC45 datasets evaluate FOX-SHIELD across different scene-classification settings. On UC Merced, FOX-SHIELD achieves 97.14% accuracy, 96.87% recall, and 96.96% F1-score, outperforming selected privacy-preserving and lightweight remote sensing classification baselines. Empirical security analysis further indicates improved entropy, key sensitivity, and resistance to statistical attacks. The results suggest that FOX-SHIELD is a promising framework for secure remote sensing image classification in distributed, resource-aware environments.
- 23 September 2026
- Published by MDPI AG in Electronics
- Vol. 15 (19) , 4382
Open AccessFOX-SHIELD: A Secure Encrypted-Domain Remote Sensing Image Classification Framework Using Chebyshev-SHA and Fox-Optimized FRNNs
Remote sensing (RS) images transmitted through distributed satellite, UAV, and sensor networks are vulnerable to interception and misuse, while conventional encryption may reduce the effectiveness of downstream image classification. This paper proposes FOX-SHIELD, a secure encrypted-domain remote sensing image classification framework that integrates Chebyshev-SHA dynamic encryption with a Fox-Optimized Fast Recurrent Neural Network. The Chebyshev-SHA module generates image-specific dynamic keys and applies permutation–diffusion encryption to protect image confidentiality and integrity. The encrypted image representation is then classified using an FRNN optimized by the Fox Optimization Algorithm to improve convergence, classification accuracy, and computational efficiency. Experiments on the UC Merced Land Use and NWPU-RESISC45 datasets evaluate FOX-SHIELD across different scene-classification settings. On UC Merced, FOX-SHIELD achieves 97.14% accuracy, 96.87% recall, and 96.96% F1-score, outperforming selected privacy-preserving and lightweight remote sensing classification baselines. Empirical security analysis further indicates improved entropy, key sensitivity, and resistance to statistical attacks. The results suggest that FOX-SHIELD is a promising framework for secure remote sensing image classification in distributed, resource-aware environments.
- Open Access
- 26 August 2026
- Published by Dijlah University in Dijlah Journal of Engineering Sciences ISSN: 3078-9664, e-ISSN: 3078-9656
- Vol. 3 (3)
Real-Time Seizure Prediction Using Low-Power Spiking Neural Networks on Wearable Edge Devices
Epilepsy is a condition that is present in 50 million individuals all over the world, but predicting seizures in real-time on wearable devices is a challenging task because of stringent power and latency requirements. The current paper introduces a wearable edge devices-based low-power seizure prediction system based on Spiking Neural Networks (SNNs). In contrast to traditional deep learning models, SNNs compute EEG signals as a result of events, and spikes, which consumes much less energy by a factor of ten. We suggest a three-layer SNN, leaky integrate-and-fire neurons, adaptive thresholding and sparse connectivity, trained using a surrogate gradient descent. The system based on CHB-MIT scalp EEG database and patient-wise splitting, has a sensitivity of 88.4, specificity of 93.2 and a false alarm rate of 0.08/hour, predicting seizures 5-30 minutes before they occur. The system is implemented on an ARM Cortex-M4 microcontroller, using 3.4 - 13 times less energy than a CNN-LSTM baseline to make an inference, and has 45 ms latency. Ablation experiments validate the work of adaptive thresholding, population coding and 16 ms timestep resolution. This is the first SNN-based seizure prediction system to the best of knowledge that has been tested on a publicly available EEG dataset and with wearable-edge hardware simulation. The framework shows that neuromorphic computing has the capabilities to address clinical and engineering needs of real-time neurological monitoring.
- 26 August 2026
- Published by Dijlah University in Dijlah Journal of Engineering Sciences ISSN: 3078-9664, e-ISSN: 3078-9656
- Vol. 3 (3)
Open AccessReal-Time Seizure Prediction Using Low-Power Spiking Neural Networks on Wearable Edge Devices
Epilepsy is a condition that is present in 50 million individuals all over the world, but predicting seizures in real-time on wearable devices is a challenging task because of stringent power and latency requirements. The current paper introduces a wearable edge devices-based low-power seizure prediction system based on Spiking Neural Networks (SNNs). In contrast to traditional deep learning models, SNNs compute EEG signals as a result of events, and spikes, which consumes much less energy by a factor of ten. We suggest a three-layer SNN, leaky integrate-and-fire neurons, adaptive thresholding and sparse connectivity, trained using a surrogate gradient descent. The system based on CHB-MIT scalp EEG database and patient-wise splitting, has a sensitivity of 88.4, specificity of 93.2 and a false alarm rate of 0.08/hour, predicting seizures 5-30 minutes before they occur. The system is implemented on an ARM Cortex-M4 microcontroller, using 3.4 - 13 times less energy than a CNN-LSTM baseline to make an inference, and has 45 ms latency. Ablation experiments validate the work of adaptive thresholding, population coding and 16 ms timestep resolution. This is the first SNN-based seizure prediction system to the best of knowledge that has been tested on a publicly available EEG dataset and with wearable-edge hardware simulation. The framework shows that neuromorphic computing has the capabilities to address clinical and engineering needs of real-time neurological monitoring.
- Open Access
- 22 March 2026
- Published by Dijlah University in Dijlah Journal of Engineering Sciences ISSN: 3078-9664, e-ISSN: 3078-9656
- Vol. 3 (1)
Anatomical Pretext Tasks with Hybrid CNN-ViT Backbone for Enhanced SVM-Based Mammogram Analysis
We suggest a new method of enhancing the feature discriminability of mammogram analysis through integrating anatomical pretext tasks in a hybrid CNN-ViT backbone followed by improved classification using SVM. Traditional self-supervised approaches usually use generic image transforms, which does not necessarily reflect the subtle clinical reasoning regarding radiologists. To tackle this, we formulate domain-specific pretext tasks, which directly model anatomical priors, such as spatial context reconstruction, orientation prediction conditional on ductal tree alignment and lesion-context consistency using contrastive learning. The hybrid backbone is a hybrid of ResNet-50 and ViT, which extracts local and global context patterns, respectively, to produce an integrated feature representation that links hierarchical and long-range dependencies. These characteristics are then trimmed down using PCA, so that they can be compatible with SVM kernels whilst retaining anatomical significance. In comparison to the current approaches, our framework is the only one to use the pretraining goals with clinical workflows, thus enhancing the interpretability of features and minimizing the need of large labeled datasets. Experiments indicate that the suggested approach performs better than the conventional deep feature extractors in mammogram classification tasks. Integrating domain-sensitive medical image analysis with self-directed learning through incorporating anatomical reasoning provides new opportunities to analyze medical images, especially in cases when few annotations are available. The contribution of the paper is the progression of the synergy between radiologist-inspired feature learning and up-to-date deep architectures, which gives a scalable algorithm that enhances the accuracy of diagnostic outcomes.
- 22 March 2026
- Published by Dijlah University in Dijlah Journal of Engineering Sciences ISSN: 3078-9664, e-ISSN: 3078-9656
- Vol. 3 (1)
Open AccessAnatomical Pretext Tasks with Hybrid CNN-ViT Backbone for Enhanced SVM-Based Mammogram Analysis
We suggest a new method of enhancing the feature discriminability of mammogram analysis through integrating anatomical pretext tasks in a hybrid CNN-ViT backbone followed by improved classification using SVM. Traditional self-supervised approaches usually use generic image transforms, which does not necessarily reflect the subtle clinical reasoning regarding radiologists. To tackle this, we formulate domain-specific pretext tasks, which directly model anatomical priors, such as spatial context reconstruction, orientation prediction conditional on ductal tree alignment and lesion-context consistency using contrastive learning. The hybrid backbone is a hybrid of ResNet-50 and ViT, which extracts local and global context patterns, respectively, to produce an integrated feature representation that links hierarchical and long-range dependencies. These characteristics are then trimmed down using PCA, so that they can be compatible with SVM kernels whilst retaining anatomical significance. In comparison to the current approaches, our framework is the only one to use the pretraining goals with clinical workflows, thus enhancing the interpretability of features and minimizing the need of large labeled datasets. Experiments indicate that the suggested approach performs better than the conventional deep feature extractors in mammogram classification tasks. Integrating domain-sensitive medical image analysis with self-directed learning through incorporating anatomical reasoning provides new opportunities to analyze medical images, especially in cases when few annotations are available. The contribution of the paper is the progression of the synergy between radiologist-inspired feature learning and up-to-date deep architectures, which gives a scalable algorithm that enhances the accuracy of diagnostic outcomes.
- Open Access
- 12 March 2026
- Published by RSIS International in International Journal of Research and Innovation in Applied Science
- Vol. 11 (2) , 924-938
Privacy-Preserving and Secure AI-based Stress Monitoring Federated Learning on Wearable Edge Devices Using Homomorphic Encryption
The paper presents a new framework, HE-FedStress, with which it is feasible to monitor stress and preserve privacy in an AI-based approach to stress detection through federated learning and homomorphic encryption on wearable edge devices. The proposed system handles the essential privacy issues that come with decentralized health surveillance because the proposed system allows joint model training without exposing uncoded biometric information. The Edge wearable devices are local physiological signal temporal attention models that inference latency can process five-second windows with a latency of just 47 ms, implemented on photoplethysmography, electrodermal activity and accelerator data. The updates of the model are coded using the Pailier cryptosystem and sent to the central server where they could be aggregated securely without decrypting each individual contribution. The WESAD and SWELL-KW datasets have been empirically assessed to verify that HE-FedStress can give F1-scores of 89.7% and 85.2% respectively and retain centralized model performance with 92 and 94 % of this performance under full cryptographic protection against model-inversion attacks (compared to 34.7 % centralization in the standard federated learning case). The structure uses gradient quantization, which cuts down the communication load to 63KB/ round, and uses adaptive batch size to support heterogeneous device capacity. The computational optimizations (depthwise separable convolutions, selective attention pruning, and eight-bit quantization) allow incessant 24 hour execution of commercial wearables with only a 19% power consumption impact over plaintext federated learning. The design of the modular architecture is to meet GDPR and HIPAA data-localization standards and provide the ability to extend it to other healthcare applications. Therefore, this contribution can provide a practical, scalable stress monitoring solution to secure and personalized performance with a robust guarantee on cryptography, and can also indicate that the requirements of resource-constrained edge environments can be satisfied with a robust guarantee alongside real-time performance.
- 12 March 2026
- Published by RSIS International in International Journal of Research and Innovation in Applied Science
- Vol. 11 (2) , 924-938
Open AccessPrivacy-Preserving and Secure AI-based Stress Monitoring Federated Learning on Wearable Edge Devices Using Homomorphic Encryption
The paper presents a new framework, HE-FedStress, with which it is feasible to monitor stress and preserve privacy in an AI-based approach to stress detection through federated learning and homomorphic encryption on wearable edge devices. The proposed system handles the essential privacy issues that come with decentralized health surveillance because the proposed system allows joint model training without exposing uncoded biometric information. The Edge wearable devices are local physiological signal temporal attention models that inference latency can process five-second windows with a latency of just 47 ms, implemented on photoplethysmography, electrodermal activity and accelerator data. The updates of the model are coded using the Pailier cryptosystem and sent to the central server where they could be aggregated securely without decrypting each individual contribution. The WESAD and SWELL-KW datasets have been empirically assessed to verify that HE-FedStress can give F1-scores of 89.7% and 85.2% respectively and retain centralized model performance with 92 and 94 % of this performance under full cryptographic protection against model-inversion attacks (compared to 34.7 % centralization in the standard federated learning case). The structure uses gradient quantization, which cuts down the communication load to 63KB/ round, and uses adaptive batch size to support heterogeneous device capacity. The computational optimizations (depthwise separable convolutions, selective attention pruning, and eight-bit quantization) allow incessant 24 hour execution of commercial wearables with only a 19% power consumption impact over plaintext federated learning. The design of the modular architecture is to meet GDPR and HIPAA data-localization standards and provide the ability to extend it to other healthcare applications. Therefore, this contribution can provide a practical, scalable stress monitoring solution to secure and personalized performance with a robust guarantee on cryptography, and can also indicate that the requirements of resource-constrained edge environments can be satisfied with a robust guarantee alongside real-time performance.
- Open Access
- 1 March 2026
- Published by Al-Iraqia University in Al-Iraqia Journal for Scientific Engineering Research
- Vol. 5 (1) , 34-48
Dynamic Quantization-Aware Neural Architecture Search for Real-Time Encrypted Traffic Classification in 5G Networks
This paper presents a dynamic quantization-aware neural architecture search (NAS) framework for real-time encrypted traffic classification in 5G networks. The framework jointly optimizes model architecture and quantization policies using reinforcement learning with hardware-in-the-loop feedback, addressing both accuracy and efficiency on edge devices. Unlike conventional static methods, the proposed system supports runtime bitwidth switching to adapt precision levels based on fluctuating traffic loads and hardware conditions. Extensive experiments were conducted on ISCX-VPN, USTC-TFC2016, and QUIC-5G datasets. The results show that the proposed approach achieves 94.2% accuracy on ISCX-VPN, 92.7% on USTC, and 89.4% on QUIC-5G, outperforming baseline methods while reducing inference latency by 28–42% and lowering energy consumption by up to 26%. The framework maintains robustness under low-precision constraints, with a mean Quantization Stability Score (QSS) of 0.91, compared to 0.82–0.87 for existing approaches. Hardware-specific optimizations provide additional gains, such as a 2.1 × speedup on Raspberry Pi 4, reduced latency on Jetson Xavier and lower energy consumption on Intel NCS2. The results of Ablation studies affirm that dynamic quantization, hardware feedback, and stability and mechanisms are an absolute necessity, improving accuracy by up to 3.1% and decreasing latency by 31% over sequential optimization. These results prove the efficiency of dynamic quantization-aware NAS to classify encrypted traffic and emphasize its prospects in broader 5G edge AI applications.
- 1 March 2026
- Published by Al-Iraqia University in Al-Iraqia Journal for Scientific Engineering Research
- Vol. 5 (1) , 34-48
Open AccessDynamic Quantization-Aware Neural Architecture Search for Real-Time Encrypted Traffic Classification in 5G Networks
This paper presents a dynamic quantization-aware neural architecture search (NAS) framework for real-time encrypted traffic classification in 5G networks. The framework jointly optimizes model architecture and quantization policies using reinforcement learning with hardware-in-the-loop feedback, addressing both accuracy and efficiency on edge devices. Unlike conventional static methods, the proposed system supports runtime bitwidth switching to adapt precision levels based on fluctuating traffic loads and hardware conditions. Extensive experiments were conducted on ISCX-VPN, USTC-TFC2016, and QUIC-5G datasets. The results show that the proposed approach achieves 94.2% accuracy on ISCX-VPN, 92.7% on USTC, and 89.4% on QUIC-5G, outperforming baseline methods while reducing inference latency by 28–42% and lowering energy consumption by up to 26%. The framework maintains robustness under low-precision constraints, with a mean Quantization Stability Score (QSS) of 0.91, compared to 0.82–0.87 for existing approaches. Hardware-specific optimizations provide additional gains, such as a 2.1 × speedup on Raspberry Pi 4, reduced latency on Jetson Xavier and lower energy consumption on Intel NCS2. The results of Ablation studies affirm that dynamic quantization, hardware feedback, and stability and mechanisms are an absolute necessity, improving accuracy by up to 3.1% and decreasing latency by 31% over sequential optimization. These results prove the efficiency of dynamic quantization-aware NAS to classify encrypted traffic and emphasize its prospects in broader 5G edge AI applications.
- Open Access
- 23 February 2026
- Published by RSIS International in International Journal of Latest Technology in Engineering Management & Applied Science
- Vol. 15 (2) , 840-858
Fedstress: A Privacy-Preserving Federated Learning Framework for Efficient and Accurate Stress Detection Using Wearable Sensors
The proposed privacy-sensitive federated learning method is FedStress, which is aimed at identifying wearable stressors with high accuracy and efficiency. The growing use of wearables in health monitoring poses serious issues regarding data privacy and computational limitations especially in a situation where sensitive physiological data is to be used. The approaches in existence have inherent trade-offs: federated learning opens model parameters to gradient inversion attacks and differential privacy errors the accuracy by injecting noise and homomorphic encryption is prohibitive due to resource-constrained devices. To solve these issues, FedStress combines federated learning with an optimized homomorphic encryption and allows collaborative model training without having access to raw user data. Every device trains locally a lightweight stress detector using a variant of MobileNetV3 using depthwise separable convolutions and a hybrid attention mechanism in order to trade off accuracy and efficiency. The encrypted transmission of model updates is done through partially homomorphic encryption, sensor-aware ciphertext packing which minimises overhead on encrypted model updates, and allows secure aggregation in the encrypted space. An additional defense mechanism is on-device differential privacy with adaptive noise scaling, which prevents inference attacks and hierarchical key management which implements strict access control. Experimental confirmation of the WESAD dataset shows that FedStress can have 87.6% accuracy in detecting stress as centralized methods (89.1) with a much lower level of privacy risk, a gradient inversion attack success rate of 11% and a score of 0.09 on information leakage (0.45 with standard federated learning). This framework is practical, with 23ms inference time and 0.45J of energy used to make a classification on commercial smartwatch systems due to efficient parameter synchronization and model compression. We also provide a viable solution to the current trend of privacy-conscious health monitoring systems, which offers a reasonable compromise between algorithmic performance and practical functionality of wearable applications. The modular structure also enables it to increase the physiological sensing tasks, which makes it a flexible instrument in studying edge-based federated learning.
- 23 February 2026
- Published by RSIS International in International Journal of Latest Technology in Engineering Management & Applied Science
- Vol. 15 (2) , 840-858
Open AccessFedstress: A Privacy-Preserving Federated Learning Framework for Efficient and Accurate Stress Detection Using Wearable Sensors
The proposed privacy-sensitive federated learning method is FedStress, which is aimed at identifying wearable stressors with high accuracy and efficiency. The growing use of wearables in health monitoring poses serious issues regarding data privacy and computational limitations especially in a situation where sensitive physiological data is to be used. The approaches in existence have inherent trade-offs: federated learning opens model parameters to gradient inversion attacks and differential privacy errors the accuracy by injecting noise and homomorphic encryption is prohibitive due to resource-constrained devices. To solve these issues, FedStress combines federated learning with an optimized homomorphic encryption and allows collaborative model training without having access to raw user data. Every device trains locally a lightweight stress detector using a variant of MobileNetV3 using depthwise separable convolutions and a hybrid attention mechanism in order to trade off accuracy and efficiency. The encrypted transmission of model updates is done through partially homomorphic encryption, sensor-aware ciphertext packing which minimises overhead on encrypted model updates, and allows secure aggregation in the encrypted space. An additional defense mechanism is on-device differential privacy with adaptive noise scaling, which prevents inference attacks and hierarchical key management which implements strict access control. Experimental confirmation of the WESAD dataset shows that FedStress can have 87.6% accuracy in detecting stress as centralized methods (89.1) with a much lower level of privacy risk, a gradient inversion attack success rate of 11% and a score of 0.09 on information leakage (0.45 with standard federated learning). This framework is practical, with 23ms inference time and 0.45J of energy used to make a classification on commercial smartwatch systems due to efficient parameter synchronization and model compression. We also provide a viable solution to the current trend of privacy-conscious health monitoring systems, which offers a reasonable compromise between algorithmic performance and practical functionality of wearable applications. The modular structure also enables it to increase the physiological sensing tasks, which makes it a flexible instrument in studying edge-based federated learning.
- Open Access
- 8 January 2026
- Published by University of Information Technology and Communications in Iraqi Journal for Computers and Informatics
- Vol. 52 (1) , 113-126
Adaptive Multi-Layer Security for UAV Video Streaming: A Chaotic Blockchain Key Scheduler with MDP-Driven Reinforcement Learning
Our adaptive multi-layer security lets UAVs communicate live video. This technique improves key scheduling over time by using MDP, chaotic maps, and blockchain technology. The bulk of essential management frameworks use legislation or centralized trust systems. In UAV networks, safe and fast video transmission is in demand, thus we must match encryption strength with operation speed. Reinforcement learning can optimize key generation and distribution. Monitor network trust scores, chaotic entropy, and blockchain update timestamps in MDP state space, and automatically remembered action refresh times in state space. The system may evolve with the network since the reward function handles unpredictability, timeliness, and trustworthiness. The system's adaptability allows this. Non-linear chaotic map framework parameter modifications can be made by using blockchain-based trust signals and entropy measurements. Removal of repeating patterns does not weaken the cryptography technique. A transformer-encoded deep Q-network produces optimal policies in the presented manner. An Old Fault Through Tolerant blockchain consensus, important blockchain modifications may be checked. The experiment shows that GPU-powered chaotic generators can use Hyperledger Fabric to reach refresh rates below one second. In practice, UAV network dynamics prove this. This work evaluates our defenses against replay and key compromise and advances high-throughput video streaming systems.
- 8 January 2026
- Published by University of Information Technology and Communications in Iraqi Journal for Computers and Informatics
- Vol. 52 (1) , 113-126
Open AccessAdaptive Multi-Layer Security for UAV Video Streaming: A Chaotic Blockchain Key Scheduler with MDP-Driven Reinforcement Learning
Our adaptive multi-layer security lets UAVs communicate live video. This technique improves key scheduling over time by using MDP, chaotic maps, and blockchain technology. The bulk of essential management frameworks use legislation or centralized trust systems. In UAV networks, safe and fast video transmission is in demand, thus we must match encryption strength with operation speed. Reinforcement learning can optimize key generation and distribution. Monitor network trust scores, chaotic entropy, and blockchain update timestamps in MDP state space, and automatically remembered action refresh times in state space. The system may evolve with the network since the reward function handles unpredictability, timeliness, and trustworthiness. The system's adaptability allows this. Non-linear chaotic map framework parameter modifications can be made by using blockchain-based trust signals and entropy measurements. Removal of repeating patterns does not weaken the cryptography technique. A transformer-encoded deep Q-network produces optimal policies in the presented manner. An Old Fault Through Tolerant blockchain consensus, important blockchain modifications may be checked. The experiment shows that GPU-powered chaotic generators can use Hyperledger Fabric to reach refresh rates below one second. In practice, UAV network dynamics prove this. This work evaluates our defenses against replay and key compromise and advances high-throughput video streaming systems.
- 1 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-7
Smart Evaluation of Stylistic Elements in Student Writing Using AI Tools
The integration of artificial intelligence in educational assessment has opened new pathways for evaluating nuanced aspects of student writing, such as stylistic and tonal features. This study proposes a novel AI-driven framework for analyzing stylistic elements in student literary compositions to enhance interpretive feedback and writing development. Existing methods for assessing literary essays often rely on rubric-based or manual evaluations, which are time-consuming, subjective, and limited in capturing subtle stylistic variations. To address these limitations, we introduce the Analyzing Tone using Explainable AI (AT-XAI) framework, which incorporates Stylometric Feature Extraction to analyze student essays automatically. This system evaluates tone, style, and linguistic patterns using interpretable AI models, offering transparent insights for educators and learners. The proposed method facilitates automated, consistent, and pedagogically relevant feedback, helping students refine their literary voice and critical writing. Findings show that AT-XAI achieves high accuracy in tone classification and stylistic feature detection, aligning closely with expert human evaluations while significantly reducing assessment time. The study demonstrates the potential of explainable AI to foster more equitable and scalable writing instruction across literature classrooms.
- 1 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-7
Smart Evaluation of Stylistic Elements in Student Writing Using AI Tools
The integration of artificial intelligence in educational assessment has opened new pathways for evaluating nuanced aspects of student writing, such as stylistic and tonal features. This study proposes a novel AI-driven framework for analyzing stylistic elements in student literary compositions to enhance interpretive feedback and writing development. Existing methods for assessing literary essays often rely on rubric-based or manual evaluations, which are time-consuming, subjective, and limited in capturing subtle stylistic variations. To address these limitations, we introduce the Analyzing Tone using Explainable AI (AT-XAI) framework, which incorporates Stylometric Feature Extraction to analyze student essays automatically. This system evaluates tone, style, and linguistic patterns using interpretable AI models, offering transparent insights for educators and learners. The proposed method facilitates automated, consistent, and pedagogically relevant feedback, helping students refine their literary voice and critical writing. Findings show that AT-XAI achieves high accuracy in tone classification and stylistic feature detection, aligning closely with expert human evaluations while significantly reducing assessment time. The study demonstrates the potential of explainable AI to foster more equitable and scalable writing instruction across literature classrooms.
- Open Access
- 18 November 2025
- Published by MDPI AG in Preprints.org
A Secure and Efficient Remote Sensing Image Classification Framework Using Chebyshev-SHA Encryption and Fox-Optimized Fast Recurrent Neural Networks
The exponential rise of remote sensing and sensor network technologies has generated massive amounts of visual data, posing challenges in safe transmission, data integrity, and categorization. In real-time applications, existing approaches fail to reconcile strong encryption, classification accuracy, and computing economy. This study aims to develop a safe and effective remote sensing image classification system that addresses both data security and intelligent analysis, enabling automated, context-aware insights in dispersed, real-time settings. The proposed work introduces the Fox-Optimized Secure Hybrid Image Encryption and Learning-based Detection (FOX-SHIELD) framework, which effectively integrates advanced encryption techniques with deep learning-based image classification, ensuring both data security and high classification accuracy for remote sensing images in real-time, distributed environments. An upgraded Chebyshev chaotic map and the Secure Hash Algorithm (SHA-256) provide dynamic, stable encryption keys in the first phase, ensuring data secrecy and integrity throughout transmission and storage. A Fast Recurrent Neural Network (FRNN) coupled with the Fox Optimization Algorithm improves convergence rate, stability, and classification accuracy even for encrypted input in the second phase. This integration enables powerful object detection while ensuring anonymity, an essential feature for sensitive remote sensing tasks. The FOX-SHIELD framework outperforms traditional models, including Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and other hybrid encryption-learning models, in terms of classification accuracy, training convergence, and computational efficiency when applied to standard remote sensing datasets. This work addresses the fundamental issue of data security in remote sensing image classification by integrating lightweight cryptographic methods with metaheuristic deep learning optimization to enhance model accuracy, convergence, and computational efficiency in real-time applications.
- 18 November 2025
- Published by MDPI AG in Preprints.org
Open AccessA Secure and Efficient Remote Sensing Image Classification Framework Using Chebyshev-SHA Encryption and Fox-Optimized Fast Recurrent Neural Networks
The exponential rise of remote sensing and sensor network technologies has generated massive amounts of visual data, posing challenges in safe transmission, data integrity, and categorization. In real-time applications, existing approaches fail to reconcile strong encryption, classification accuracy, and computing economy. This study aims to develop a safe and effective remote sensing image classification system that addresses both data security and intelligent analysis, enabling automated, context-aware insights in dispersed, real-time settings. The proposed work introduces the Fox-Optimized Secure Hybrid Image Encryption and Learning-based Detection (FOX-SHIELD) framework, which effectively integrates advanced encryption techniques with deep learning-based image classification, ensuring both data security and high classification accuracy for remote sensing images in real-time, distributed environments. An upgraded Chebyshev chaotic map and the Secure Hash Algorithm (SHA-256) provide dynamic, stable encryption keys in the first phase, ensuring data secrecy and integrity throughout transmission and storage. A Fast Recurrent Neural Network (FRNN) coupled with the Fox Optimization Algorithm improves convergence rate, stability, and classification accuracy even for encrypted input in the second phase. This integration enables powerful object detection while ensuring anonymity, an essential feature for sensitive remote sensing tasks. The FOX-SHIELD framework outperforms traditional models, including Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and other hybrid encryption-learning models, in terms of classification accuracy, training convergence, and computational efficiency when applied to standard remote sensing datasets. This work addresses the fundamental issue of data security in remote sensing image classification by integrating lightweight cryptographic methods with metaheuristic deep learning optimization to enhance model accuracy, convergence, and computational efficiency in real-time applications.