Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Ali M. Abdulshahed has a total of 21 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • An AHP Framework for Evaluating Large Language Models in Software Vulnerability Assessment

    by Mohamed Abugharsa, Ali M. Abdulshahed

    Large language models (LLMs) can assist software security review, but detecting more weaknesses may increase false alarms, unreliable patches, or higher costs. This methodological paper specifies a reproducible Analytic Hierarchy Process (AHP) framework for evaluating LLM-assisted vulnerability assessment in a synthetic banking-information application. Applying the framework to a local operational banking system was not feasible because obtaining the required security approvals was difficult; no production banking infrastructure was tested. Six objectives are linked to measurable indicators covering ground-truth completeness, detection, classification and severity assessment, secure remediation, reliability and resource use, and decision sensitivity. The protocol specifies 12 vulnerable and 12 corrected variants, four scenarios, repeated runs, blinded adjudication, CVSS v4.0 assessment, regression tests, and paired analysis. A comparison with SecurityEval, CyberSecEval, CyberSecEval 2, and BountyBench positions the proposed contribution as linking verified outcomes to stakeholder priorities rather than demonstrating superior benchmark performance. An exact reciprocal AHP example uses weights of 0.40, 0.30, 0.20, and 0.10. A separate simulation yields group weights of 0.3565, 0.2920, 0.2187, and 0.1328, with a consistency ratio of 0.0008. These are constructed examples, not elicited expert judgments. No LLM benchmarking was performed, and no model ranking is claimed. Empirical validation requires archived runs, independently assessed outcomes, and human stakeholder judgments; production transfer additionally requires institutional authorization and service-specific validation.

  • Open Access

    A Deep Reinforcement Learning Framework for the Dynamic Berth Allocation Problem: A Case Study of the Misurata Free Zone Port

    by Inass Husien, Ali M Abdulshahed

    Maritime terminal efficiency is critical for global supply chains, yet many ports continue to rely on manual heuristics for the Berth Allocation Problem (BAP). This research proposes an application-oriented Deep Reinforcement Learning (DRL) framework to optimize berth assignment at the Misurata Free Zone (MFZ) Port. The problem is modeled as a Markov Decision Process (MDP) and validated using a customized discrete-event simulation environment ("PortEnv") trained on 2024 historical logs. The framework incorporates complex industrial constraints, including functional berth heterogeneity and adjacent berthing logic for continuous quays. A Deep Q-Network (DQN) agent was trained using a sparse reward structure to prioritize global throughput over immediate gains.Benchmarking against the First-Come-First-Served (FCFS) heuristic using a 2023 industrial stress-test dataset revealed a transformative 99.31% reduction in average vessel waiting time, decreasing from 42.5 days to 7.2 hours. Furthermore, the agent reduced the maximum wait time by 94.27% and demonstrated sophisticated operational intelligence by executing strategic trade-offs between specialized cargo sectors. Specifically, the agent learned to sacrifice immediate tanker occupancy to resolve critical bottlenecks in the high-volume Iron and Steel sector. These results indicate that DRL-based decision support systems can significantly enhance port reliability and environmental sustainability by minimizing vessel idling emissions. This study provides a scalable ICT solution for transitioning port management from reactive heuristics to proactive, globally optimized operational models.

  • Surface Roughness Prediction in Additive Manufacturing: Presenting the Power of Neural Networks Compared to Linear Regression

    by A. M. Abdulshahed, Fatma Wafa

    This paper investigates surface roughness prediction in additive manufacturing through a comprehensive comparative analysis of linear regression (LR) and neural network (NN) models. Employing [ ]-means clustering, we identify four distinct clusters within the experimental data, each closely associated with specific 3D printing parameters. Within each cluster, we explore the optimal combination of factors that contribute to surface roughness and power efficiency. The main objective focuses on predicting a target variable, with an emphasis on evaluating model performance via key metrics such as [ ]-squared ([ ]2), adjusted [ ]-squared, predicted [ ]-squared, mean squared error (MSE), and correlation coefficient ([ ]). Our study’s results illuminate the robust predictive capabilities of both LR and NN models. However, it becomes evident that the Neural Network model outperforms Linear Regression. It exhibits excellent performance metrics, characterized by higher [ ]2 and correlation values, reduced MSE, and greater resilience to outliers. This pronounced disparity underscores the Neural Network model’s exceptional suitability for tasks requiring precise predictions and the identification of nonlinear patterns, particularly in the field of surface roughness prediction in additive manufacturing. These findings emphasize the key role of advanced machine learning techniques, illustrated by neural networks, in achieving precision within similar domains.


  • Open Access

    Prediction of Surface Roughness in Additive Manufacturing Using Artificial Neural Networks

    by Fatma Wafa, A.M. Abdulshahed

    In this work, we applied an Artificial Neural Networks (ANN) approach for prediction of the part surface roughness for 3D printing technology. A small number of neurons was used for building ANN model with the help of MATLAB environment. The predicted values are found to be in excellent agreement with the experimental data with average error value of 8%.In addition, we compared the proposed ANN model to another regression-based approach. Results show that the proposed model has high accuracy in comparison to statistical approach. Therefore, we can use ANN model to predict the part surface roughness for 3D printing technology.

  • Open Access

    Offline Recognition System for Arabic Handwritten Words Using Artificial Neural Networks

    by M.M. Makhlou Makhlou, A.M. Abdulshahed Abdulshahed

    Arabic handwritten recognition is playing an important role in communicating and documenting information in everyday life. Handwriting has functional importance considering its ubiquity in human activities, as in reading handwritten notes in a PDA (Personal Digital Assistant), in postal addresses on envelopes, in amounts in bank accounts, etc. In this work, an offline recognition system for Arabic handwritten names is proposed using Artificial Neural Network (ANN). As part of the feature extraction, region props were used, it extracts array with fields: Area, Centroid and Bounding Box. A feed-forward neural network with three different topologies was trained using backpropagation algorithm. The number of nodes in the hidden layer was varied; the lower the number of hidden layers, the higher the recognition rate. Moreover, we found that the first topology (with two hidden layers) produced a higher recognition rate 92% from the trained data compared to the second and third topologies that produced a smaller recognition rate.

  • A grey-based assessment approach to the site selection of a desalination plant in Libya

    by Ibrahim A. Badi, Ali M. Abdulshahed, Ali Shetwan, Mohamed Ali Ballem

    Purpose: The purpose of this paper is to propose a site selection method using grey system theory for a desalination plant in Libya. Design/methodology/approach: In order to tackle incompleteness and imprecision of human’s judgments, grey numbers were used. This work uses a grey-based approach to represent decision makers’ comparison judgments and extent analysis method to select the best site. Therefore, a real case study of a selection problem of a site selection of desalination plant in Libya was used to illustrate the proposed approach. Findings: Site selection in a desalination plant can be one of the most important decisions in planning a desalination project. The decision affects both the project cost and potentially the project schedule. Based on the results of grey model, a clear order of these sites and the degree of preference are obtained. This paper presents a way to improve a site selection by using a grey model, especially in a complex environment like Libya. Originality/value: To the best knowledge of the authors, there is no literature for site selection using grey system theory in a desalination plant in Libya. This attempt may well enhance and facilitate the decision-making process of the best site in the country involved in this research.


  • A grey-based decision-making approach to the supplier selection problem in a steelmaking company

    by Ali M. Abdulshahed, Ibrahim A. Badi, Mohamed Mehemed Blaow

    Purpose: The purpose of this paper is to propose a supplier selection method using grey system theory for a steelmaking company in Libya. Design/methodology/approach: In order to tackle incompleteness and imprecision of human’s judgments, grey numbers were used. This work uses a grey-based approach to represent decision makers’ comparison judgments and extent analysis method to select the best supplier. Therefore, an example of a selection problem of a steelmaking company in Libya was used to illustrate the proposed approach. Findings: Supplier selection in a supply chain is a critical strategic decision for company’s success and has attracted much attention of both academic scholars and decision makers. The authors have found that the Grey model can play an important role in improving supplier selection strategy, especially when it is in a situation where complex sustainability environments (i.e. Libya) exist. Originality/value: No literature has been found till date for selection of supplier using grey system theory in a steelmaking company in Libya. An attempt in this regard could enhance a decision-making technique for selecting the best suppliers for the selected case company.


  • Assessment of airport performance using the grey theory method

    by Mohamed Ibrahim Eshtaiwi, Ibrahim A. Badi, Ali M. Abdulshahed, Turan Erman Erkan

    Purpose: Performance evaluation of airports or any other organisation is paramount for improving performance. The purpose of this paper is to evaluate and compare the performance of the three international airports in Libya (MJI, MRA, and LAQ airports) by considering five aspects of performance. Design/methodology/approach: The considered aspects are airport service quality, airport operations, airport economy, safety and security, and environmental. The paper uses the grey system theory to assess these airports by summarizing the opinions of experts. Findings: The finding of this study provides directions of the evaluated airports to take the correct actions to improve overall performance. Originality/value: No literature has been found till date is to evaluate and compare the performance of the international airports in Libya.