Mahmoud Moshref

Prof. Mahmoud Moshref


Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 May 2022 in Indonesian Journal of Electrical Engineering and Computer Science
Verified
Journal Article
Open access
PDF file
MMMahmoud Moshref
Mahmoud Moshref
RARizik M. H. Al-Sayyed
Rizik M. H. Al-Sayyed
SASaleh Al-Sharaeh
Saleh Al-Sharaeh
Multi-objective algorithms are used to achieve high performance for quality of service (QoS) in wireless sensor networks (WSNs) is an important field for researchers because these algorithms improve two or more conflicting objectives and present the best trade-off between the conflicting objectives to solve multi-objective problems (MOPs). Previous research proposed an algorithm that relies on non-dominated sorting genetic algorithm 3 (NSGA-III), namely enhanced non-dominated sorting genetic routing algorithm (ENSGRA). This algorithm is used to optimise three objectives, which include number of worked sensors, energy consuming and node covering area. The fourth objective, which is node load balancing, is added in the current research. Such an addition aims to improve node distribution around cluster heads and decrease network congestion, thus decreasing energy consumption and increasing network lifetime. The ENSGRA algorithm is compared with multi-objective multi-step particle swarm optimisation (MOMSPSO), non-dominated sorting genetic algorithm 2 (NSGA-II), and NSGA-III. The proposed algorithm ENSGRA exceed to MOMSPSO, NSGA-II, and NSGA-III in the proposed QoS model in the final outcomes, as the proposed approach achieved (38%) average combination (optimisation) percentage. Which is the highest percentage over other methods.

6 May 2026 in Electronics
Verified
Journal Article
Open access
PDF file
EAEsra'a Alkafaween
Esra'a Alkafaween
MMMahmoud Moshref
Mahmoud Moshref
MAMAMOUN ALDMOUR
MAMOUN ALDMOUR
Artificial intelligence applications in mental health diagnosis face persistent challenges related to interpretability, trust, and the integrity of results. This study presents a trust-aware explainable deep learning framework that combines systematic benchmarking, SHAP-based interpretability, and permissioned blockchain verification to achieve secure mental health classification. The Depression & Mental Health Classification Dataset was used, which contains 1999 records, 21 features, and 12 classes. Data preprocessing included categorical encoding and Z-score normalization for continuous variables. To ensure robust evaluation, a stratified train–test split was applied, and class imbalance was addressed using the Synthetic Minority Over-sampling Technique (SMOTE). Eight machine learning and deep learning models were assessed under identical preprocessing and validation settings. In addition, two models were proposed: Feature Attention XGBoost (FA-XGBoost) and Feature Attention Feedforward Neural Network (FA-FNN). The FA-FNN model achieved the best performance, attaining an accuracy of 96.00%, precision of 98.31%, recall of 97.31%, and F1-score of 98.04%. To address deep learning’s black-box limitation, SHapley Additive ExPlanations (SHAPs) were used to provide both global feature importance and instance-level explanations, enabling transparent identification of the most influential mental health markers. Beyond interpretability, a permissioned blockchain layer was added to provide tamper-proof logging and traceable verification of AI results. The framework securely stores cryptographic hashes of model versions, prediction results, and generated SHAP artifacts, including visualization images, without exposing sensitive medical data. By integrating explainable decision-making, high-performance classification, and blockchain-based trust enforcement, the proposed framework creates a transparent and secure pipeline suitable for real-world mental healthcare systems. Controlled experiments on a permissioned Ethereum-InterPlanetary File System (IPFS) network demonstrated predictable latency, stable throughput (≈28–30 transactions/s), and lower operational costs, proving the framework’s suitability for enterprise and healthcare deployments.

22 September 2026 in Information
Verified
Journal Article
Open access
PDF file
RARand Ibrahim Al-Suhimat
Rand Ibrahim Al-Suhimat
EAEsra'a Alkafaween
Esra'a Alkafaween
MMMahmoud Moshref
Mahmoud Moshref
SASamar Al-Saqqa
Samar Al-Saqqa
MAMAMOUN ALDMOUR
MAMOUN ALDMOUR
Electrocardiographic (ECG) biometric verification can lose reliability over time because ECG morphology changes across longitudinal sessions, which makes enrolled templates increasingly likely to reject genuine users. Most existing methods focus on maximizing recognition accuracy or updating templates only after new data arrive, and they do not try to forecast how reliable a future verification will be before it happens. This work investigates whether information available before a verification attempt can be used to predict the reliability of future genuine verifications, thereby enabling uncertainty-aware decisions and adaptive re-enrollment. Experiments used the longitudinal Heartprint dataset, with earlier sessions reserved for model development and later sessions (S3R and S3L) held out for prospective evaluation. A one-dimensional ResNet produced 128-dimensional ECG embeddings that were compared via cosine similarity. Logistic Regression and XGBoost then predicted future reliability from temporal features, historical similarity measures, and signal-quality indicators. The framework also examined feature ablation, probability calibration, abstention, and adaptive re-enrollment. Under a fixed development threshold, AUROC fell from 0.971 in S2 to 0.936 in S3R and 0.916 in S3L, while the false-rejection rate rose from 9.27% to 16.99% and 20.94%, respectively. Logistic Regression showed stronger discrimination, whereas XGBoost yielded lower Brier scores and negative log-likelihood. Calibration lowered ECE from 34.18% to 11.64% on S3R and from 32.05% to 15.52% on S3L. Adaptive re-enrollment needed 88 and 84 updates on S3R and S3L, respectively—fewer than the fixed policies—although it did not achieve the lowest residual error. Overall, the results support managing ECG biometric systems with explicit attention to reliability, balancing risk, coverage, and update frequency.