albahlool mohamad ali abood


Permanent Lecturer

Qualification: Master

Academic rank: Lecturer

Specialization: هندسة تقنية المعلومات - الهندسة الكهربائية والحاسوب

Software Engineering - Faculty of Information Technology

Publications
When Preprocessing Changes the Winner: Sensitivity of Medical Prediction Model Rankings to Missing Data Handling
Journal Article

Missing data are common in clinical prediction studies, yet their handling may affect not only predictive performance but also which model is judged best. This study examined the stability of classifier selection when missing data handling was changed under controlled, paired evaluation conditions. Using SUPPORT2 data from 9,105 patients, Logistic Regression, Random Forest, and XGBoost were evaluated with median, K nearest neighbor, and iterative imputation. The analysis retained natural missingness, added nested missing completely at random (MCAR) perturbations of 5%, 10%, 20%, and 30%, and included a separate 20% missing at random (MAR) condition. Repeated stratified five fold cross validation used the same patient partitions, model seeds, and artificial missingness masks across corresponding comparisons. Ranking stability was assessed through condition level winner changes, paired rank reversals, and agreement across receiver operating characteristic area under the curve (ROC AUC), Average Precision, and Brier Score. The condition level winner remained stable under natural and mild additional missingness, but became dependent on imputation at higher missingness. Winner changes occurred in 6 of 12 imputation comparisons and 9 of 15 missingness comparisons, while pairwise rank reversals occurred in about 44% of matched repeat comparisons. All three metrics selected the same winner in 8 of 18 conditions. Because competing winners were separated by small ROC AUC margins, the results indicate sensitivity of model selection rather than large performance advantages. Reporting ranking stability alongside conventional performance estimates may therefore provide a more cautious basis for comparative clinical prediction studies.

albahlool mohamad ali abood, (09-2026), طرابلس: Libyan Journal of Contemporary Academic Studies, 4 (2), 77-94

Feature Reduction Sensitivity to Evaluation Protocol in Phishing URL Detection
Journal Article

Feature reduction is widely used in machine learning based phishing URL detection to lower model complexity while retaining detection performance. However, conclusions about how much reduction is acceptable may depend on how training and testing data are partitioned. This study examines whether conclusions about feature reduction remain stable when evaluation changes from random stratified to domain disjoint cross validation. Experiments were conducted on URL-Phish Version 2 using Mutual Information ranking within each training fold and four predefined feature budgets, from 22 to 5 features. Logistic Regression and Random Forest were evaluated under both protocols, with PR AUC as the primary metric. PR AUC decreased as the feature budget was reduced for both classifiers under both evaluation protocols, so the qualitative conclusion about feature reduction remained consistent within this experimental setting. However, the size of the protocol gap varied across classifiers and feature budgets: it was clearest for Random Forest under the smallest feature budget, whereas the Logistic Regression gaps were less clearly separated from fold-level variability. Domain disjoint evaluation also produced greater fold-level variability. The results show that claims about compact phishing URL representations should be interpreted together with the evaluation protocol used. Future work should examine whetherthis pattern persists across additional datasets, classifiers, and domain grouping rules.

albahlool mohamad ali abood, (09-2026), ليبيا: International Science and Technology Journal المجلة الدولية للعلوم والتقنية, 39 (1), 1-39

A Risk-Based Regulatory Framework for EMC and EMI Management in Internet of Things Applications
Journal Article

The rapid growth of Internet of Things (IoT) applications has increased the number of connected devices operating in shared wireless environments. IoT systems rely on sensors, actuators, embedded electronics, software, and internet connectivity to collect, exchange, and process data across sectors such as smart homes, healthcare, transportation, industrial systems, energy systems, and public infrastructure. However, the dense deployment of wireless IoT devices can create significant Electromagnetic Compatibility (EMC) challenges, especially when multiple transmitters and receivers operate in proximity or within the same or adjacent frequency bands. These conditions may lead to Electromagnetic Interference (EMI), which can degrade communication performance, reduce device reliability, and affect safety in critical environments. This study uses a regulatory review and conceptual framework development, drawing on literature synthesis, regulatory requirement extraction, analytical classification, regulatory mapping, and risk-based EMC categorisation. It identifies key EMC and EMI challenges in IoT applications, particularly in dense wireless and low-power communication environments. It analyses immunity requirements in critical sectors such as vehicular networks, healthcare, industry, and public infrastructure. It also develops a regulatory framework that defines stakeholder roles and classifies IoT connection methods, application areas, and device structures to support safer deployment and reduce interference risks.

albahlool mohamad ali abood, (09-2026), ليبيا: AlQalam Journal of Medical and Applied Sciences (AJMAS), 9 (9), 2727-2739

Leakage Aware Evaluation of Arabic Text Classification: Quantifying Document Level Leakage and the Sufficiency of Linear TF IDF Baselines
Journal Article

The volume of Arabic text online keeps growing, and with it the need for systems that sort it into meaningful categories. A quieter problem often passes unnoticed: when long documents are split into shorter segments and pieces of the same document fall on both sides of the boundary between training and testing, the reported scores can look far better than the model deserves. This study treats that document level leakage as its central subject. Using a purpose built multidomain Arabic corpus of 1,000 segments drawn from 183 source documents across seven categories, we first measure how much leakage distorts the numbers. Under a naive random split, an optimized Linear SVM appears to reach 0.9800 accuracy; under a grouped split keyed to the document identifier, the same model reaches 0.8528. The gap of about 12.7 accuracy points is attributable to leakage, and across models the inflation ranges from roughly 11.9 to 30.4 points. Leakage also flattens the ranking, so a weak Naive Bayes looks almost as strong as the best model. Under the honest protocol, an ablation shows that character level TF IDF alone matches the combined word and character representation and slightly exceeds it on Macro F1, 0.7801 against 0.7713, while word features mainly refine precision. McNemar tests and a document clustered bootstrap show that the strongest linear models are statistically indistinguishable. A fastText baseline reaches 0.6497 accuracy, and two pretrained Arabic transformers, AraBERT and MARBERT, perform comparably to the linear model rather than surpassing it. A class level analysis exposes the General category as a structural confound whose removal raises accuracy to 0.9349. Overall, leakage aware evaluation paired with subword rich TF IDF and a Linear SVM forms a strong, honest, and practical baseline for Arabic text classification.

albahlool mohamad ali abood, (07-2026), ليبيا: Libyan Open University Journal of Applied Sciences, 2 (2), 22-46

Task Scheduling in the Fog to Cloud Continuum for IoT Services: A Taxonomy and Structured Synthesis of Distributed Resource Management
Journal Article

Task scheduling has often been treated as a secondary concern in fog computing, something to address only after the architecture is defined. This review argues that it is instead the central runtime decision in the fog to cloud continuum, because it determines whether the promised gains in latency, energy efficiency, and reliability can actually be achieved. The study synthesizes 102 foundational, methodological, and technical sources on task scheduling in fog enabled IoT environments. The aim was not simply to catalogue algorithms, but to examine how the field has framed the scheduling problem and how that framing has changed over time. The evidence reveals a clear progression. Early studies commonly assumed stable resources, predictable workloads, and simplified network conditions, which made scheduling easier to model but less representative of real deployments. More recent work has relaxed these assumptions and introduced dynamic, multi objective, application aware, learning based, and deployment oriented approaches. Six research streams emerge from this evolution. The main finding is that algorithmic sophistication has advanced faster than evaluation practice. Reported improvements in latency, energy consumption, and other QoS metrics are often difficult to compare because studies use different workloads, simulators, baselines, and experimental assumptions. Scheduling and orchestration overhead is rarely measured, while physical testbed validation remains limited. These gaps directly affect confidence in whether a proposed scheduler would behave as expected in operational fog systems. The review therefore identifies several priorities for future work: standardized benchmark workloads, cloud native scheduling that accounts for container lifecycle and microservice dependencies, resilience aware scheduling that treats failures and migration as first class concerns, and carbon aware orchestration that extends beyond energy minimization. Beyond the taxonomy, the paper argues for a shift from proof of concept scheduling studies toward reproducible, transparent, and deployable fog systems.

albahlool mohamad ali abood, (07-2026), Asian Journal of Research in Computer Science: Asian Journal of Research in Computer Science, 19 (8), 34-64

An Explainable Deep Learning Framework for Plant Leaf Disease Detection Using a Custom CNN Model
Journal Article

Agricultural sustainability relies heavily on the early detection of plant pathologies. However, manual diagnosis remains challenging even for experts. This study proposes a lightweight Custom Convolutional Neural Network (CNN) architecture for automated leaf disease detection. The model was evaluated against state-of-the-art frameworks, MobileNetV2 and EfficientNetB0, using a dataset of 15,649 images that integrates global data with locally sourced samples from Libya. To ensure robustness, k-Fold Cross-Validation was implemented under standardized conditions. The proposed Custom CNN achieved a competitive accuracy of 97.6%, closely matching EfficientNetB0 (98.4%). Despite the slight accuracy advantage of transfer learning models, the Custom CNN demonstrated superior computational efficiency and a significantly smaller architectural footprint. These results position the proposed model as an ideal candidate for deployment in resource-constrained environments and mobile-based diagnostic systems.

albahlool mohamad ali abood, (06-2026), Academy Journal for Basic and Applied Sciences (AJBAS), Libya: Libyan Academy for Postgraduate Studies, 1 (8), 1-10

6LoWPAN - Technical Features and Challenges in IoT: A Review
Conference paper

The phrase "Internet of Things" (IoT) has been considered the next great prospect and a test for the Internet engineering community, technology users, society, and enterprises. The billions of physical devices are currently online, collecting and exchanging data globally. Anything as little as a pill or as large as an airliner can be made into a component of the IoT because of the development of affordable computer chips and the expansion of wireless networks. Devices that would otherwise be dumb are given a level of digital intelligence by connecting all these various components and attaching sensors to them, allowing them to communicate data in real time without human interaction. The difficulty of choosing the best wireless low-power area networks for IoT applications arises from the exponential expansion of wireless technologies connecting to the IoT. Therefore, this review investigates the importance of 6LoWPAN as a foundation for the IoT's future and reviews the history that led to IoT and the advantages of using 6LoWPAN-based IP networks. We also discuss the popular implementation and challenges of 6LoWPAN.

albahlool mohamad ali abood, (05-2024), IEEE: 2024 IEEE 4th International Maghreb Meeting of the Conference on Sciences and Techniques of Automatic Control and Computer Engineering (MI-STA),Tripoli, Libya, 19-21 May 2024.,

Educational Data Mininig During the COVID-19 Pandemic
Journal Article

Educational data mining studies have employed various techniques and tools in supporting decision-making based on students’ online presence, academic performances, and personal profiling. However, the unexpected advent of COVID-19 and imposed containment measures around the world necessitate academic institutions to haphazardly transfer academic activities to the eLearning environments. This rapid transfer might have posed peculiar challenges to the usual decision-making approaches. Fortunately, data mining techniques have proven their merit in supporting quick and complex decision-making. Accordingly, in the present study we assessed eLearning studies that employed data mining techniques in making educational decisions in the period of COVID-19 pandemic. Based on the common research approaches, data mining solutions employed in addressing the peculiar educational challenges were explored and analyzed to inform future decisions. The study findings revealed that several studies have utilized data mining in ascertaining the effectiveness of various eLearning modalities including social media in teaching and learning during the pandemic. Moreover, studies have utilized both machine learning and statistical data mining approaches in supporting educational decisions during the pandemic. However, none of the current studies reported the application of the popular educational data mining platforms during the pandemic. Thus, future studies require to employ the expertise in educational data mining techniques toward demonstrating the efficacy of the common educational data mining platforms in supporting various academic activities and academic decision-making processes. However, this current study's purpose is to analyze eLearning studies that utilized data mining approaches in endowing educational activities or in making educational decisions during the period of COVID-19 pandemic.

albahlool mohamad ali abood, (12-2022), Journal of Electronic Systems and Programming (JESP), Tripoli, Libya: Journal of Electronic Systems and Programming, Libya, 6 (6), 3-22

A Review of Blockchain-based on IoT applications (challenges and future research directions)
Conference paper

Internet of Things is defined as the framework of interconnected computing systems, mechanical and digital appliances, objects, animals, or people that are equipped with specific identifiers as well as the ability to transfer data over networks. Such devices will not require human-to-human or human-to-computer interaction. This technology has emerged with a Blockchain, which has been used in cryptocurrency, to enhance the performance of security and decrease costs. Although emerging Blockchain with IoT has improved the entire system design. It still faces a number of issues relevant to time latency, anonymity, power efficiency, and big data. Blockchain has been used in various applications such as Healthcare, smart homes, and smart cities. In this paper, we will briefly define the idea of Blockchain including the definition of Blockchain, its types, advantages, and disadvantages, and then present some challenges of Blockchain-based applications on the Internet of things where we focus on Healthcare, smart homes, and smart cities. Finally, some future work direction will be introduced.

albahlool mohamad ali abood, (03-2021), 2020 5th International Conference on Innovative Technologies in Intelligent Systems and Industrial Applications (CITISIA), Sydney, Australia: IEEE (Institute of Electrical and Electronics Engineers), 1-7

Design & Simulation of Voice QoS Performance in Data Network Congestion for M/D/1 Queuing Model
Journal Article

Voice in IP networks is transmitted as packets over IP (VoIP), the voice signals are converted to IP packets after being digitized and compressed for transmission. However, some packets can be missed in their way to the receiving side, due to network congestion. The loss of these packets degrades the speech quality in the listener side at VoIP system transmission. Since voice is transmitted is real time, the receiver cannot request a retransmission for any lost packets. Voice and data multiplexing in VoIP network always face problems when huge TCP traffic is transmitted resulting the voice packet to be stuck in the network during congestion. Therefore, VoIP packets will be delayed. Since delay and loss are the main parameters that affect the quality of a voice signal in a VoIP network.

This paper presents a design and a simulation study of voice and data integration in a VoIP network and analyses which scenario will suite the best performance for voice packets in traffic congestion to have a high voice quality rating when using a single data TCP source and a multiple TCP sources when multiplexed with a UDP voice source. This is accomplished by using NS-2 network simulator (version 2), and M/D/1 queue type with various queuing systems such as First in First out (FIFO), Fair queue (FQ) and Deficit Round Robin (DRR), which represent the technique mechanism to serve voice and data packets in a queueing system. Then loss and delay are measured for each scenario to determine the quality of voice.

albahlool mohamad ali abood, (01-2021), Albahit Journal of Applied Sciences: (Albahit Journal of Applied Sciences), 1 (2), 37-45

© All rights reserved to University of Gharyan