Nayef Hmoud Alshammari
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Nayef Hmoud Alshammari has a total of 39 co-authors. Here are the top co-authors by number of shared publications:
- Sami Aziz Alshammari
Department of Information Technology, Faculty of Computing and Information Technology, Northern Border University, Rafha 76313, Saudi Arabia
15 shared publications - Ayoub Alsarhan
Department of Data Science and Artificial Intelligence, Faculty of Information Technology, Al-Ahliyya Amman University, Amman 19111, Jordan
13 shared publications - Khalid Hamad Alnafisah
Department of Computer Sciences, Faculty of Computing and Information Technology, Northern Border University, Rafha 73213, Saudi Arabia
8 shared publications - Mahmoud AlJamal
Department of Cybersecurity, Faculty of Science and Information Technology, Irbid National University, Irbid 21110, Jordan
5 shared publications - Mohammed Aleinzi
Department of Information Systems, Faculty of Computing and Information Technology, Northern Border University, Rafha 73213, Saudi Arabia
4 shared publications - Mohammad Aljaidi
Zarqa University
3 shared publications
Latest Publications
- Open Access
Leakage-Controlled Evaluation of CNN-LSTM Models for Process Temperature Forecasting and Soft Sensing in Machining: Evidence from the AI4I 2020 Benchmark
Convolutional recurrent networks are widely reported as being able to forecast process temperature in machining accurately. Many such evaluations, however, split overlapping sliding windows at random, which lets near-duplicate samples cross the train–test boundary. We re-examine process temperature forecasting and soft sensing on the AI4I 2020 benchmark under a leakage-controlled protocol: a chronological split with a purge gap, training-only scaling, five seeds, block-bootstrap confidence intervals and Diebold–Mariano tests with an autocorrelation-robust variance. LSTM, GRU, CNN-LSTM and an attention-augmented CNN-LSTM are compared with persistence, linear, random forest and multilayer-perceptron baselines that receive the same ten-record window. Under a random split the attention model reaches ; under the chronological split it falls to . Rolling-origin cross-validation, a purge-gap sweep, a factorial ablation and sensitivity analyses support this picture. In soft sensing, the error is dominated by a drifting process–air temperature offset that the machine signals in this benchmark do not observe, and refitting on recent data matters more than architecture. When lagged process temperature is available, persistence (MAE 0.054 K) is not beaten at horizons of 1–30 records, and convolutional and attention stages add no benefit while costing up to 2.4 times the training time of a plain LSTM. On this benchmark, the evaluation protocol changed the conclusions more than did the choice of architecture. Claimed gains of deep sequence models for machine monitoring should therefore be reported against persistence and information-matched baselines under a time-ordered split.Open AccessLeakage-Controlled Evaluation of CNN-LSTM Models for Process Temperature Forecasting and Soft Sensing in Machining: Evidence from the AI4I 2020 Benchmark
Convolutional recurrent networks are widely reported as being able to forecast process temperature in machining accurately. Many such evaluations, however, split overlapping sliding windows at random, which lets near-duplicate samples cross the train–test boundary. We re-examine process temperature forecasting and soft sensing on the AI4I 2020 benchmark under a leakage-controlled protocol: a chronological split with a purge gap, training-only scaling, five seeds, block-bootstrap confidence intervals and Diebold–Mariano tests with an autocorrelation-robust variance. LSTM, GRU, CNN-LSTM and an attention-augmented CNN-LSTM are compared with persistence, linear, random forest and multilayer-perceptron baselines that receive the same ten-record window. Under a random split the attention model reaches ; under the chronological split it falls to . Rolling-origin cross-validation, a purge-gap sweep, a factorial ablation and sensitivity analyses support this picture. In soft sensing, the error is dominated by a drifting process–air temperature offset that the machine signals in this benchmark do not observe, and refitting on recent data matters more than architecture. When lagged process temperature is available, persistence (MAE 0.054 K) is not beaten at horizons of 1–30 records, and convolutional and attention stages add no benefit while costing up to 2.4 times the training time of a plain LSTM. On this benchmark, the evaluation protocol changed the conclusions more than did the choice of architecture. Claimed gains of deep sequence models for machine monitoring should therefore be reported against persistence and information-matched baselines under a time-ordered split. - Open Access
- 3 November 2026
- Published by MDPI AG in Future Internet
- Vol. 18 (11) , 604
Certified Envelope Bounds and an Envelope-Informed Learning Surrogate for Road Network Resilience Under Stochastic Capacity Degradation
Road networks are routinely exposed to partial capacity losses caused by incidents, work zones, flooding and pavement failures, and planners need fast, trustworthy estimates of how such losses propagate through route choice. This paper develops a framework for user-equilibrium (UE) traffic networks with degradable link capacities that combines variational analysis with a learned surrogate. Writing the Beckmann potential in the coordinates makes it affine in u, so standard results (the concavity of a pointwise minimum of affine functions and Danskin’s theorem) show that the optimal potential is concave, non-decreasing and differentiable, with a gradient available from one equilibrium solution. The resulting criticality index equals times the congestion delay of each link; the theory adds to this classical indicator a derivative interpretation and certified bounds. We derive two-sided certificates on the potential change for any degradation, the identity , a solver-free certificate for the total system travel time (TSTT), and an additive certificate for restoring sets of links, whose per-link weight is the damaged-state delay of the link times a severity factor, and we use these quantities as features of an envelope-informed surrogate (EIGS), a gradient-boosted model on per-link envelope features diffused over the line graph. Experiments on the Sioux Falls and Anaheim benchmarks show where the results are useful and where they are not. The potential certificate is within a factor of 1.45 of the exact change at 25% capacity loss on Sioux Falls (1.03 on the 100 most critical Anaheim links) but loosens quickly with severity (factor 3.28 at 50% loss on Sioux Falls; 574 and 74 at 90% loss), and the solver-free TSTT bound exceeds the true change by a median factor of 3.8–12 in the multi-link Monte Carlo scenario sets. No single cheap indicator ranks link criticality best on both networks. On Sioux Falls, EIGS predicts the TSTT increase with (0.913–0.960 over ten splits) against 0.919 for ridge regression and 0.924 for gradient boosting on the diffused severities, and with against 0.862 on a spatially correlated test set generated after the model was fixed. Under shifts in demand () and nominal capacity, refreshing its envelope features from one equilibrium of the shifted network gives –; using the same equilibrium to rescale the predictions of raw-input baselines gives them –, so the gain from the per-link envelope features is modest. On Anaheim, whose losses are extremely heavy-tailed, EIGS ranks scenarios well (Spearman ) but does not predict their magnitude reliably, while ridge regression with a cross-validated penalty ranks them poorly (). For restoring three of about fifteen damaged links, the certified envelope rule, which needs a single equilibrium, recovers on average 93.6% of the loss recovered by the exact optimum over all three-link sets.- 3 November 2026
- Published by MDPI AG in Future Internet
- Vol. 18 (11) , 604
Open AccessCertified Envelope Bounds and an Envelope-Informed Learning Surrogate for Road Network Resilience Under Stochastic Capacity Degradation
Road networks are routinely exposed to partial capacity losses caused by incidents, work zones, flooding and pavement failures, and planners need fast, trustworthy estimates of how such losses propagate through route choice. This paper develops a framework for user-equilibrium (UE) traffic networks with degradable link capacities that combines variational analysis with a learned surrogate. Writing the Beckmann potential in the coordinates makes it affine in u, so standard results (the concavity of a pointwise minimum of affine functions and Danskin’s theorem) show that the optimal potential is concave, non-decreasing and differentiable, with a gradient available from one equilibrium solution. The resulting criticality index equals times the congestion delay of each link; the theory adds to this classical indicator a derivative interpretation and certified bounds. We derive two-sided certificates on the potential change for any degradation, the identity , a solver-free certificate for the total system travel time (TSTT), and an additive certificate for restoring sets of links, whose per-link weight is the damaged-state delay of the link times a severity factor, and we use these quantities as features of an envelope-informed surrogate (EIGS), a gradient-boosted model on per-link envelope features diffused over the line graph. Experiments on the Sioux Falls and Anaheim benchmarks show where the results are useful and where they are not. The potential certificate is within a factor of 1.45 of the exact change at 25% capacity loss on Sioux Falls (1.03 on the 100 most critical Anaheim links) but loosens quickly with severity (factor 3.28 at 50% loss on Sioux Falls; 574 and 74 at 90% loss), and the solver-free TSTT bound exceeds the true change by a median factor of 3.8–12 in the multi-link Monte Carlo scenario sets. No single cheap indicator ranks link criticality best on both networks. On Sioux Falls, EIGS predicts the TSTT increase with (0.913–0.960 over ten splits) against 0.919 for ridge regression and 0.924 for gradient boosting on the diffused severities, and with against 0.862 on a spatially correlated test set generated after the model was fixed. Under shifts in demand () and nominal capacity, refreshing its envelope features from one equilibrium of the shifted network gives –; using the same equilibrium to rescale the predictions of raw-input baselines gives them –, so the gain from the per-link envelope features is modest. On Anaheim, whose losses are extremely heavy-tailed, EIGS ranks scenarios well (Spearman ) but does not predict their magnitude reliably, while ridge regression with a cross-validated penalty ranks them poorly (). For restoring three of about fifteen damaged links, the certified envelope rule, which needs a single equilibrium, recovers on average 93.6% of the loss recovered by the exact optimum over all three-link sets. - Open Access
- 1 September 2026
- Published by MDPI AG in Mathematics
- Vol. 14 (17) , 3149
Mathematical Modeling and Simulation of Energy-Constrained Pavement Crack Maintenance Using XFEM-Based Crack Evolution and AI-Driven Repair Strategy Optimization
This study presents a mathematical modeling and simulation framework for pavement crack maintenance under limited work zone energy availability. The framework combines crack evolution, thermal repair, interface behavior, and maintenance decision-making within a unified structural–thermal–energy formulation. A three-dimensional multilayer flexible pavement model is developed with an XFEM-enriched region in the aged asphalt surface layer, a localized repair zone, cohesive interface behavior, and wheel-loading stages before and after maintenance. Rather than assuming constant heating, the repair heat flux is governed by a photovoltaic battery-dependent amplitude function, allowing the model to reflect practical variations in available energy. The simulation generated a dataset containing crack geometry, pavement properties, repair zone dimensions, loading conditions, heat flux intensity, heating duration, bonding quality, XFEM damage status, stress response, temperature distribution, interface damage, energy feasibility, durability, and service life gain. These variables were used to develop the Crack–Energy–Repair Interaction Graph Network (CERIG-Net), which represents each maintenance case as a physics-guided heterogeneous graph and ranks delayed repair, crack sealing, localized patching, thin overlay, and deep repair. The thin overlay strategy reduced final crack length from 94.7 mm to 53.8 mm, lowered maximum stress from 3.85 MPa to 2.22 MPa, achieved a durability index of 0.86, and extended service life by 6.7 years.
- 1 September 2026
- Published by MDPI AG in Mathematics
- Vol. 14 (17) , 3149
Open AccessMathematical Modeling and Simulation of Energy-Constrained Pavement Crack Maintenance Using XFEM-Based Crack Evolution and AI-Driven Repair Strategy Optimization
This study presents a mathematical modeling and simulation framework for pavement crack maintenance under limited work zone energy availability. The framework combines crack evolution, thermal repair, interface behavior, and maintenance decision-making within a unified structural–thermal–energy formulation. A three-dimensional multilayer flexible pavement model is developed with an XFEM-enriched region in the aged asphalt surface layer, a localized repair zone, cohesive interface behavior, and wheel-loading stages before and after maintenance. Rather than assuming constant heating, the repair heat flux is governed by a photovoltaic battery-dependent amplitude function, allowing the model to reflect practical variations in available energy. The simulation generated a dataset containing crack geometry, pavement properties, repair zone dimensions, loading conditions, heat flux intensity, heating duration, bonding quality, XFEM damage status, stress response, temperature distribution, interface damage, energy feasibility, durability, and service life gain. These variables were used to develop the Crack–Energy–Repair Interaction Graph Network (CERIG-Net), which represents each maintenance case as a physics-guided heterogeneous graph and ranks delayed repair, crack sealing, localized patching, thin overlay, and deep repair. The thin overlay strategy reduced final crack length from 94.7 mm to 53.8 mm, lowered maximum stress from 3.85 MPa to 2.22 MPa, achieved a durability index of 0.86, and extended service life by 6.7 years.
- Open Access
A Simulation-Driven Cybersecurity Framework for Detecting Novel Multi-Stage Attacks in Cyber-Physical Smart Infrastructure
Cyber-physical smart infrastructures integrate sensing devices, communication networks, control components, and service platforms, which makes them vulnerable to malicious activities that may evolve gradually through several attack stages. The objective of this study is to develop and evaluate a simulation-based cybersecurity framework capable of detecting a proposed novel multi-stage cyber attack and identifying its internal progression within a realistic smart infrastructure environment. To achieve this objective, a NetSim-based cyber-physical smart infrastructure was modeled to generate both normal operational traffic and staged malicious traffic. The generated traffic was captured, processed, labeled, and transformed into a stage-aware cybersecurity dataset. An artificial neural network (ANN) model was then trained and evaluated for two detection tasks: binary classification of normal versus attack traffic and multi-class classification of compromise, coordination, and execution attack stages. Twenty experimental configurations were designed to examine the model under progressively broader infrastructure contexts, including sensing, service, gateway, control, backbone, and full-span operational scenarios. The best binary testing performance was achieved in the eighteenth experimental configuration, representing a broad full-span infrastructure scenario, with 97.96% accuracy, 97.80% precision, 97.65% recall, 97.72% F1-score, and 1.06% false positive rate. For stage-aware multi-class detection, the ANN model achieved 96.97% accuracy, 96.36% macro-averaged precision, 96.20% macro-averaged recall, 96.28% macro-averaged F1-score, and 96.55% weighted F1-score. Macro-averaged metrics report the unweighted average performance across classes, while weighted F1-score accounts for class support. These results show that the proposed simulation-based framework can generate realistic attack-aware traffic data and support reliable ANN-based detection of both attack presence and attack-stage progression.
Open AccessA Simulation-Driven Cybersecurity Framework for Detecting Novel Multi-Stage Attacks in Cyber-Physical Smart Infrastructure
Cyber-physical smart infrastructures integrate sensing devices, communication networks, control components, and service platforms, which makes them vulnerable to malicious activities that may evolve gradually through several attack stages. The objective of this study is to develop and evaluate a simulation-based cybersecurity framework capable of detecting a proposed novel multi-stage cyber attack and identifying its internal progression within a realistic smart infrastructure environment. To achieve this objective, a NetSim-based cyber-physical smart infrastructure was modeled to generate both normal operational traffic and staged malicious traffic. The generated traffic was captured, processed, labeled, and transformed into a stage-aware cybersecurity dataset. An artificial neural network (ANN) model was then trained and evaluated for two detection tasks: binary classification of normal versus attack traffic and multi-class classification of compromise, coordination, and execution attack stages. Twenty experimental configurations were designed to examine the model under progressively broader infrastructure contexts, including sensing, service, gateway, control, backbone, and full-span operational scenarios. The best binary testing performance was achieved in the eighteenth experimental configuration, representing a broad full-span infrastructure scenario, with 97.96% accuracy, 97.80% precision, 97.65% recall, 97.72% F1-score, and 1.06% false positive rate. For stage-aware multi-class detection, the ANN model achieved 96.97% accuracy, 96.36% macro-averaged precision, 96.20% macro-averaged recall, 96.28% macro-averaged F1-score, and 96.55% weighted F1-score. Macro-averaged metrics report the unweighted average performance across classes, while weighted F1-score accounts for class support. These results show that the proposed simulation-based framework can generate realistic attack-aware traffic data and support reliable ANN-based detection of both attack presence and attack-stage progression.
- Open Access
- 16 June 2026
- Published by MDPI AG in Cryptography
- Vol. 10 (3) , 39
An Energy-Aware Post-Quantum Ascon–ML-KEM Cryptographic Framework for Low-Latency UAV Remote Sensing Communications
UAV-based remote sensing systems are increasingly deployed in smart surveillance, disaster response, environmental monitoring, and critical infrastructure inspection. In these applications, aerial sensing platforms must transmit telemetry, control commands, and observation data securely and reliably under strict latency, energy, and computational constraints. However, existing security approaches often fail to jointly provide lightweight payload confidentiality, quantum-resilient key establishment, and adaptive communication protection suitable for dynamic and resource-constrained aerial sensing environments. To address this challenge, this paper proposes an energy-aware post-quantum hybrid cryptographic framework for secure and low-latency UAV remote sensing communications in UAV–IoT mission networks. The proposed framework integrates Ascon-based authenticated encryption for low-overhead protection of remote sensing payloads and mission telemetry, ML-KEM-based post-quantum session-key establishment for long-term resilience against quantum-era threats, and an AI-driven adaptive rekeying mechanism that dynamically adjusts key-refresh decisions according to threat level, residual energy, mobility state, channel stability, anomaly density, traffic sensitivity, link type, and mission progression. Accordingly, rekeying is treated not as a static maintenance process but as an intelligent and context-aware cryptographic control function that adapts communication security to evolving mission and sensing conditions. The framework is evaluated across twenty progressively demanding scenarios involving different UAV counts, sensor densities, payload sizes, communication modes, and adversarial settings relevant to real-time remote sensing operations. Experimental results demonstrate a secure delivery rate of 99.2%, attack detection and mitigation effectiveness of 98.9%, end-to-end encryption latency of 8.7 ms, throughput of 5.03 Mbps, energy overhead of 11.6 mJ/session, rekeying overhead of 2.9 mJ/event, session resilience of 96.4%, and integrity verification success of 99.1%. These findings show that the proposed framework provides a practical and scalable contribution to post-quantum secure UAV remote sensing by unifying lightweight authenticated encryption, ML-KEM-based quantum-resilient key establishment, and AI-driven adaptive rekeying within a resilient aerial–terrestrial communication architecture.
- 16 June 2026
- Published by MDPI AG in Cryptography
- Vol. 10 (3) , 39
Open AccessAn Energy-Aware Post-Quantum Ascon–ML-KEM Cryptographic Framework for Low-Latency UAV Remote Sensing Communications
UAV-based remote sensing systems are increasingly deployed in smart surveillance, disaster response, environmental monitoring, and critical infrastructure inspection. In these applications, aerial sensing platforms must transmit telemetry, control commands, and observation data securely and reliably under strict latency, energy, and computational constraints. However, existing security approaches often fail to jointly provide lightweight payload confidentiality, quantum-resilient key establishment, and adaptive communication protection suitable for dynamic and resource-constrained aerial sensing environments. To address this challenge, this paper proposes an energy-aware post-quantum hybrid cryptographic framework for secure and low-latency UAV remote sensing communications in UAV–IoT mission networks. The proposed framework integrates Ascon-based authenticated encryption for low-overhead protection of remote sensing payloads and mission telemetry, ML-KEM-based post-quantum session-key establishment for long-term resilience against quantum-era threats, and an AI-driven adaptive rekeying mechanism that dynamically adjusts key-refresh decisions according to threat level, residual energy, mobility state, channel stability, anomaly density, traffic sensitivity, link type, and mission progression. Accordingly, rekeying is treated not as a static maintenance process but as an intelligent and context-aware cryptographic control function that adapts communication security to evolving mission and sensing conditions. The framework is evaluated across twenty progressively demanding scenarios involving different UAV counts, sensor densities, payload sizes, communication modes, and adversarial settings relevant to real-time remote sensing operations. Experimental results demonstrate a secure delivery rate of 99.2%, attack detection and mitigation effectiveness of 98.9%, end-to-end encryption latency of 8.7 ms, throughput of 5.03 Mbps, energy overhead of 11.6 mJ/session, rekeying overhead of 2.9 mJ/event, session resilience of 96.4%, and integrity verification success of 99.1%. These findings show that the proposed framework provides a practical and scalable contribution to post-quantum secure UAV remote sensing by unifying lightweight authenticated encryption, ML-KEM-based quantum-resilient key establishment, and AI-driven adaptive rekeying within a resilient aerial–terrestrial communication architecture.
- Open Access
DeepLayer-ID: A Lightweight Multi-Domain Forensic Framework for Real-Time Deepfake Detection in Resource-Constrained UAV Sensor Platforms
Unmanned aerial vehicle (UAV) imaging systems are increasingly deployed in surveillance, infrastructure monitoring, and smart-city applications, where the integrity of captured visual data is critical. Recent advances in generative models enable highly realistic deepfake manipulations that can compromise aerial sensor streams, particularly under real-world degradations such as motion blur, sensor noise, and compression artifacts. This paper introduces DeepLayer-ID, a degradation-aware multi-domain forensic framework specifically designed for UAV sensing environments. The proposed architecture decomposes forensic evidence into complementary spatial, frequency, and residual domains. A discrete wavelet transform module captures sub-band energy inconsistencies, while high-pass residual filtering isolates sensor pattern anomalies. A lightweight transformer-based fusion mechanism adaptively integrates cross-domain representations to enhance robustness under heterogeneous acquisition conditions. To emulate operational UAV pipelines, we construct a balanced dataset of 1096 aerial frames derived from the VisDrone2019-DET validation subset, incorporating synthetic manipulations and physics-consistent degradations. The experimental results show that DeepLayer-ID achieves 97.8% accuracy and 0.991 AUC, outperforming ResNet-50 (90.9%, 0.942 AUC), XceptionNet (92.4%, 0.957 AUC), and Noiseprint CNN (93.1%, 0.964 AUC). Notably, the model maintains real-time feasibility, with only 5.4 M parameters and 9.8 ms inference latency. These findings demonstrate that structured multi-domain signal decomposition combined with attention-guided fusion provides a robust and computationally efficient solution for deepfake detection in degraded UAV sensing systems.
Open AccessDeepLayer-ID: A Lightweight Multi-Domain Forensic Framework for Real-Time Deepfake Detection in Resource-Constrained UAV Sensor Platforms
Unmanned aerial vehicle (UAV) imaging systems are increasingly deployed in surveillance, infrastructure monitoring, and smart-city applications, where the integrity of captured visual data is critical. Recent advances in generative models enable highly realistic deepfake manipulations that can compromise aerial sensor streams, particularly under real-world degradations such as motion blur, sensor noise, and compression artifacts. This paper introduces DeepLayer-ID, a degradation-aware multi-domain forensic framework specifically designed for UAV sensing environments. The proposed architecture decomposes forensic evidence into complementary spatial, frequency, and residual domains. A discrete wavelet transform module captures sub-band energy inconsistencies, while high-pass residual filtering isolates sensor pattern anomalies. A lightweight transformer-based fusion mechanism adaptively integrates cross-domain representations to enhance robustness under heterogeneous acquisition conditions. To emulate operational UAV pipelines, we construct a balanced dataset of 1096 aerial frames derived from the VisDrone2019-DET validation subset, incorporating synthetic manipulations and physics-consistent degradations. The experimental results show that DeepLayer-ID achieves 97.8% accuracy and 0.991 AUC, outperforming ResNet-50 (90.9%, 0.942 AUC), XceptionNet (92.4%, 0.957 AUC), and Noiseprint CNN (93.1%, 0.964 AUC). Notably, the model maintains real-time feasibility, with only 5.4 M parameters and 9.8 ms inference latency. These findings demonstrate that structured multi-domain signal decomposition combined with attention-guided fusion provides a robust and computationally efficient solution for deepfake detection in degraded UAV sensing systems.
- Open Access
- 24 February 2026
- Published by BON VIEW PUBLISHING PTE in Journal of Computational and Cognitive Engineering
- Vol. 5 (3) , 399-409
Embedded Sparsity and Ensemble Learning for Real-Time Textual Anomaly Detection: A SCADA-Inspired Benchmark on Lecture Transcript Data
This study presents a comprehensive benchmark of feature selection methods for real-time text classification, evaluating the computational trade-offs between embedded sparsity techniques (Lasso regularization), filter methods (ANOVA, mutual information), and wrapper approaches (recursive feature elimination). Using a dataset of 15,746 educational comments with TF-IDF representations, we systematically compare five feature selection methods paired with both classical machine learning and shallow neural network classifiers. Our experimental model evaluates both classification performance and computational latency in the context of binary and multiclass sentiment classification. Results show that the Lasso-based feature selection, combined with XGBoost, achieves F1-scores of 0.859 for binary classification and 0.699 for multiclass classification, with inference times of less than 1 s. Recursive feature elimination takes 284 s to do similar performance. Shallow neural networks achieve higher accuracy (F1 = 0.910 for binary, 0.841 for multiclass) at the cost of 8-s training times. In contrast, convolutional neural networks (CNNs) applied directly to TF-IDF vectors perform poorly (F1 = 0.646) with excessive training overhead (126 s), indicating that standard CNN architectures are unsuitable for sparse text representations. Our findings offer practical guidance for selecting feature reduction and classification methods based on latency requirements: Lasso with ensemble methods for real-time applications that require sub-second response and shallow neural networks for batch processing, where higher accuracy justifies the additional computational cost. Although this work uses educational text data as a testbed, the methodology and findings are applicable to any high-dimensional text classification scenario requiring efficient feature selection. Received: 10 September 2025 | Revised: 3 December 2025 | Accepted: 6 January 2026 Conflicts of Interest The authors declare that they have no conflicts of interest to this work. Data Availability Statement The data that support the findings of this study are openly available in GitHub at https://github.com/rosewang2008/sight. Author Contribution Statement Ayoub Alsarhan: Conceptualization, Resources, Writing – original draft, Visualization. Saja Jaradat: Conceptualization, Resources, Writing – original draft, Visualization. Suhaila Abuowaida: Validation, Writing – review & editing, Funding acquisition. Sami Aziz Alshammari: Methodology, Investigation, Data curation, Supervision. Nayef Hmoud Alshammari: Software, Project administration. Khalid Hamad Alnafisah: Software, Formal analysis, Project administration.
- 24 February 2026
- Published by BON VIEW PUBLISHING PTE in Journal of Computational and Cognitive Engineering
- Vol. 5 (3) , 399-409
Open AccessEmbedded Sparsity and Ensemble Learning for Real-Time Textual Anomaly Detection: A SCADA-Inspired Benchmark on Lecture Transcript Data
This study presents a comprehensive benchmark of feature selection methods for real-time text classification, evaluating the computational trade-offs between embedded sparsity techniques (Lasso regularization), filter methods (ANOVA, mutual information), and wrapper approaches (recursive feature elimination). Using a dataset of 15,746 educational comments with TF-IDF representations, we systematically compare five feature selection methods paired with both classical machine learning and shallow neural network classifiers. Our experimental model evaluates both classification performance and computational latency in the context of binary and multiclass sentiment classification. Results show that the Lasso-based feature selection, combined with XGBoost, achieves F1-scores of 0.859 for binary classification and 0.699 for multiclass classification, with inference times of less than 1 s. Recursive feature elimination takes 284 s to do similar performance. Shallow neural networks achieve higher accuracy (F1 = 0.910 for binary, 0.841 for multiclass) at the cost of 8-s training times. In contrast, convolutional neural networks (CNNs) applied directly to TF-IDF vectors perform poorly (F1 = 0.646) with excessive training overhead (126 s), indicating that standard CNN architectures are unsuitable for sparse text representations. Our findings offer practical guidance for selecting feature reduction and classification methods based on latency requirements: Lasso with ensemble methods for real-time applications that require sub-second response and shallow neural networks for batch processing, where higher accuracy justifies the additional computational cost. Although this work uses educational text data as a testbed, the methodology and findings are applicable to any high-dimensional text classification scenario requiring efficient feature selection. Received: 10 September 2025 | Revised: 3 December 2025 | Accepted: 6 January 2026 Conflicts of Interest The authors declare that they have no conflicts of interest to this work. Data Availability Statement The data that support the findings of this study are openly available in GitHub at https://github.com/rosewang2008/sight. Author Contribution Statement Ayoub Alsarhan: Conceptualization, Resources, Writing – original draft, Visualization. Saja Jaradat: Conceptualization, Resources, Writing – original draft, Visualization. Suhaila Abuowaida: Validation, Writing – review & editing, Funding acquisition. Sami Aziz Alshammari: Methodology, Investigation, Data curation, Supervision. Nayef Hmoud Alshammari: Software, Project administration. Khalid Hamad Alnafisah: Software, Formal analysis, Project administration.
- Open Access
- 20 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 34769-34789
Adaptive and Secure Three-Level Steganography Scheme With Random Distribution and Parity Coding
Data hiding has become crucial for ensuring information confidentiality in response to the increasing capabilities of modern decryption tools. This paper presents a novel steganographic approach based on Least Significant Bit manipulation to counter visual and statistical attacks. The proposed approach introduces a three-level steganography scheme that employs binary cover generation, Quick Response codes, and data embedding into Red, Green, and Blue image channels using parity coding and smoothing functions. Its key features include random data distribution across levels, adaptive pixel capacity, and the elimination of repetitive encryption processes. The approach achieves a maximum data hiding capacity of 9 bits per pixel while maintaining flexibility for varying secret message sizes. Experimental results examining standard test images demonstrate high robustness and imperceptibility, assessed through Peak Signal-to-Noise Ratio, Structural Similarity Index Measure, and Mean Squared Error metrics. These findings emphasize the efficacy of the proposed approach for secure data hiding in digital images.
- 20 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 34769-34789
Open AccessAdaptive and Secure Three-Level Steganography Scheme With Random Distribution and Parity Coding
Data hiding has become crucial for ensuring information confidentiality in response to the increasing capabilities of modern decryption tools. This paper presents a novel steganographic approach based on Least Significant Bit manipulation to counter visual and statistical attacks. The proposed approach introduces a three-level steganography scheme that employs binary cover generation, Quick Response codes, and data embedding into Red, Green, and Blue image channels using parity coding and smoothing functions. Its key features include random data distribution across levels, adaptive pixel capacity, and the elimination of repetitive encryption processes. The approach achieves a maximum data hiding capacity of 9 bits per pixel while maintaining flexibility for varying secret message sizes. Experimental results examining standard test images demonstrate high robustness and imperceptibility, assessed through Peak Signal-to-Noise Ratio, Structural Similarity Index Measure, and Mean Squared Error metrics. These findings emphasize the efficacy of the proposed approach for secure data hiding in digital images.
- Top Cited PapersOpen Access
- 18 February 2026
- Published by MDPI AG in Electronics
- Vol. 15 (4) , 861
GISLC: Gated-Inception Model for Skin Lesion Classification
Skin-lesion recognition from clinical photographs is clinically valuable yet computationally challenging due to large intra-class variation, subtle inter-class boundaries, class imbalance, and heterogeneous acquisition conditions. To address these constraints under realistic compute budgets, we investigate Inception-family convolutional baselines and propose GISLC—a Gated-Inception model that augments a GoogLeNet/Inception-V1 backbone with a lightweight, spatial gating head inspired by ConvLSTM. Unlike static fusion (concatenation/summation) of multi-branch features, the proposed gated head performs per-location, learnable regulation of feature flow across branches, prioritizing diagnostically salient patterns while suppressing redundant activations. Experiments were conducted on the clinical-images subset of the Multimodal Augmented Skin Lesion Dataset (MASLD), an augmented derivative of HAM10000, using stratified train/validation/test splits, clinically motivated augmentation, and class-weighted optimization to mitigate skewed label frequencies. A controlled ablation study evaluates backbone choices and optimization settings and isolates the contribution of gated fusion relative to standard Inception heads. Across runs, the gated fusion strategy improves discriminative performance while remaining parameter-efficient, supporting the view that spatially adaptive regulation can enhance robustness on non-dermatoscopic clinical imagery. We further outline practical steps for calibration analysis and compression-aware deployment in clinical and edge settings.
- 18 February 2026
- Published by MDPI AG in Electronics
- Vol. 15 (4) , 861
Top Cited PapersOpen AccessGISLC: Gated-Inception Model for Skin Lesion Classification
Skin-lesion recognition from clinical photographs is clinically valuable yet computationally challenging due to large intra-class variation, subtle inter-class boundaries, class imbalance, and heterogeneous acquisition conditions. To address these constraints under realistic compute budgets, we investigate Inception-family convolutional baselines and propose GISLC—a Gated-Inception model that augments a GoogLeNet/Inception-V1 backbone with a lightweight, spatial gating head inspired by ConvLSTM. Unlike static fusion (concatenation/summation) of multi-branch features, the proposed gated head performs per-location, learnable regulation of feature flow across branches, prioritizing diagnostically salient patterns while suppressing redundant activations. Experiments were conducted on the clinical-images subset of the Multimodal Augmented Skin Lesion Dataset (MASLD), an augmented derivative of HAM10000, using stratified train/validation/test splits, clinically motivated augmentation, and class-weighted optimization to mitigate skewed label frequencies. A controlled ablation study evaluates backbone choices and optimization settings and isolates the contribution of gated fusion relative to standard Inception heads. Across runs, the gated fusion strategy improves discriminative performance while remaining parameter-efficient, supporting the view that spatially adaptive regulation can enhance robustness on non-dermatoscopic clinical imagery. We further outline practical steps for calibration analysis and compression-aware deployment in clinical and edge settings.