GRGhaith Rabadi

Ghaith Rabadi

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Ghaith Rabadi has a total of 86 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    AI-Enabled Decision Support for Volunteer Allocation in Disaster Management: A Three-Stage Optimization Framework

    by Emrah Köksalmış, Ghaith Rabadi, Bulent Soykan, Gulsah Hancerliogullari Koksalmis

    Recent advances in artificial intelligence (AI) are transforming disaster management through intelligent decision support, predictive resource allocation, and adaptive operational planning. Volunteer management — a critical yet underexplored challenge in humanitarian logistics — represents a domain where AI-driven optimization can deliver substantial operational gains. This chapter presents a three-stage AI-enabled decision support framework for volunteer allocation in large-scale disaster response. At its core is a mixed-integer linear programming (MILP) model that constitutes the optimization layer of a broader AI-assisted humanitarian logistics ecosystem. The model assigns volunteers to disaster management centers while maximizing demand satisfaction, respecting capacity and travel-time constraints, incorporating individual preferences, enforcing group cohesion to improve long-term retention, and preventing scheduling conflicts. Computational experiments using a synthetic scenario with 100 volunteers, six volunteer types, four disaster management centers, and a seven-day response horizon confirm the model’s feasibility: the MILP solver reaches a solution in under 8 seconds and generates schedules that substantially reduce unmet demand. Sensitivity analysis on the preference–demand trade-off reveals important operational dynamics. The chapter concludes with a roadmap for extending the framework with machine learning demand forecasting, reinforcement learning-based dynamic reassignment, digital twin simulation, and predictive retention modeling — positioning the system as a foundation for next-generation AI tools in disaster humanitarian logistics.

  • Open Access

    iHELP: Intelligent Holistic Emergency Logistics Platform. A Cloud-Based Simulation-Optimization Platform for Disaster Logistics and Real-Time Situational Awareness

    by Ghaith Rabadi

    Natural disasters increasingly cause severe casualties, displacement, and economic destruction, yet emergency response operations are routinely hindered by fragmented inter-agency coordination, resource planning bottlenecks, and information limited to overwhelmed traditional communication channels. To address these operational challenges, this chapter presents the Intelligent Holistic Emergency Logistics Platform (iHELP), a cloud-based simulation-optimization system designed to coordinate multi-modal supply chains and provide real-time situational awareness during emergencies. Abstracting the challenge as a multi-commodity, multi-mode transportation problem, iHELP models the assignment, routing, and scheduling of heterogeneous vehicle fleets across ground, air, and maritime networks under dynamic operational constraints. To overcome data scarcity during emergencies, iHELP incorporates a dedicated Social Media Analytics Module that uses natural language processing, computer vision, and spatial clustering to ingest user posts, filter misinformation, compute confidence metrics, and infer urgent humanitarian needs. Additional integrated modules manage weather disruptions, service prioritization, and infrastructure availability. Decision-makers interact with the system via a web dashboard that visualizes animated operations, transporter utilization, and inventory trends. Developed and validated in collaboration with NATO’s Crisis Management and Disaster Response Center of Excellence through simulated flood response scenarios, iHELP demonstrates strong capability in delivering robust, high-quality emergency logistics plans under stress and uncertainty.

  • Top Cited Papers
    Open Access

    Usefulness of Large Language Models (LLMs) for Student Feedback on H&P during Clerkship: Artificial Intelligence for Personalized Learning

    by Ahmad A Bany Abdelnabi, Bulent Soykan, Danish Bhatti, Ghaith Rabadi

    Large Language Models (LLMs), notably GPT-4, demonstrate exceptional language generation and comprehension abilities, and they have potential uses in clinical practice, learning, and medical research. In this study, we explore practical use of LLMs in enhancing case-based learning in medical education. The study employs a designed mixed-methods approach, combining quantitative metrics with qualitative feedback from 100 medical students, providing comprehensive insights into both the technical performance and the educational value of LLM-based feedback systems. Our results indicate that LLMs can enhance medical students’ History and Physical (H&P) skills by providing personalized insights, fostering critical thinking, and improving their abilities to analyze, diagnose, and present clinical cases. This study has surfaced significant insights into the potential benefits and limitations of integrating LLMs into medical education. Our findings show the positive impact of LLMs on enhancing personalized learning experiences, critical thinking, and the effectiveness of case-based learning aids and highlighting its limitations.


  • Open Access

    A mathematical model and heuristic approaches for runway rescheduling

    by G. Hancerliogullari Koksalmis, G. Rabadi, M. Kharbeche, M. Al-Salem

    This study addresses the Aircraft Reactive Scheduling Problem (ARSP) on multiple parallel runways in response to operational disruptions. We specifically consider three disruptive event types; flight cancelations, delays and unexpected arrivals. Interruptions to aircraft schedules due to various reasons (e.g. bad weather conditions) may render the initial schedule not optimal or infeasible. In this paper, the ARSP is conceptualised as a multi-objective optimisation problem wherein considerations encompass not only the quality of the schedule but also its stability, defined as its conformity to an initial schedule, are of interest. A mixed-integer linear programming (MILP) model is introduced to obtain optimal solutions under different policies. Repair and regeneration heuristic approaches are developed for larger instances for which optimal solutions are time-consuming to obtain. While prevailing literature tends to concentrate on individual disruption types, our investigation diverges by concurrently addressing diverse disruption types through multiple disruptive events. We introduce alternative reactive scheduling methodologies wherein the model autonomously adapts by dynamically choosing from a range of candidate solution methods, considering conflicting objectives related to both quality and stability. A computational study is conducted, and we compare the solutions of heuristics to optimal solutions or the best solution found within a time limit, and their performances are assessed in terms of schedule stability, solution quality and computational time. We compare the solutions of heuristics and optimal solutions (i.e. the best solution found so far), and their performances are assessed in terms of schedule stability, solution quality and computational time.


  • Open Access

    Human Detection From Unmanned Aerial Vehicles’ Images for Search and Rescue Missions: A State-of-the-Art Review

    by Ahmad A. Bany Abdelnabi, Ghaith Rabadi

    Natural disasters continue to occur at an alarming rate impacting communities worldwide and requiring greater preparedness and response efforts. In the aftermath of disasters such as hurricanes and earthquakes, search and rescue (SAR) usually takes the highest priority on the response list. Utilizing recent advancements in technology, especially Unmanned Aerial Vehicles (UAVs) and Computer Vision in SAR operations has become more common due to their ability to quickly scan large disaster areas, identify and locate victims, and deliver first aid supplies especially in challenging environments. Researchers have leveraged machine learning (ML), particularly Convolutional Neural Networks, to enhance human detection accuracy. However, despite achieving excellent recall rates, the efficiency of these algorithms during actual SAR missions remains a critical consideration. The aim of this paper is to thoroughly examine the literature on human detection from UAV aerial images in SAR scenarios. This paper reviews the existing literature comprehensively and categorizes methods based on disaster type, environment, case study availability, and UAV system capabilities. It also reviews in detail the ML approaches used in the literature and compares them based on factors like image types, training datasets, model details, processing hardware, and evaluation methods. Moreover, it reviews and compares the available datasets according to their types, quantities, applications, and relevance to SAR operations. It also briefly covers state-of-the-art hardware for real-time onboard processing. Finally, we discuss the main challenges and recommendations for achieving fully autonomous UAV systems for human detection in SAR missions and offer recommendations for future research directions.


  • Optimizing Multi Commodity Flow Problem Under Uncertainty: A Deep Reinforcement Learning Approach

    by Bulent Soykan, Ghaith Rabadi

    We propose a deep reinforcement learning (DRL) approach to optimize the multi commodity flow problem under uncertainty. We frame the problem as a Markov decision problem (MDP) and develop a DRL agent that implements a Deep Q-Network (DQN) algorithm. The agent is trained via Q-Iearning iterations, and the Q-value function is modeled by a graph neural network (GNN) for value function approximation. The DRL agent is trained within a simulated environment to optimize the policy by minimizing costs, satisfying capacity constraints, and considering uncertain demands. We present the details of the environment and the DRL agent, the methodology, and a comparison of our approach with the traditional branch & bound algorithm. Our experimental results highlight the effectiveness and efficiency of the DRL approach in solving instances of the problem.


  • Open Access

    CHANCES AND CHALLENGES OF CHATGPT AND SIMILAR MODELS FOR EDUCATION IN M&S

    by William Scherer, Andreas Tolk Tolk, Margaret Loper, Phillip Barry, Ghaith Rabadi, Levent Yilmaz

    The position paper summarizes the inputs of a set of experts from academia and industry presenting their view on chances and challenges of using ChatGPT within the Modelling and Simulation education. They also address the need to evaluate continuous education as well as education of faculty members to address scholastic challenges and opportunities while meeting the expectation of industry.