AUS Repository (American University of Sharjah)
Not a member yet
2669 research outputs found
Sort by
Pavement Crack Assessment Using Satellite Remote Sensing and Deep Learning Model
No full textA Master of Science thesis in Civil Engineering by Maryam Al Adab entitled, “Pavement Crack Assessment Using Satellite Remote Sensing and Deep Learning Model”, submitted in July 2025. Thesis advisor is Dr. Tarig Ali. Soft copy is available (Thesis, Completion Certificate, Approval Signatures, and AUS Archives Consent Form).Cracking is one of the common forms of surface distress found in asphalt pavement. It can affect riding quality, structural integrity, and decreases the design life of the pavement. Accurate and timely detection of pavement cracks is crucial for maintenance planning. There are several methods used for assessing pavement condition, and the most common methods include the traditional visual inspection or vehicle-mounted system. However, these methods remain to be time consuming and challenging for large urban networks. Recent advancement is high-resolution satellite imagery and deep learning provide new opportunities for efficient and large-scale pavement condition assessment. This research investigates the feasibility of using high-resolution satellite imagery, combined with deep learning model to detect and classify asphalt pavement crack in the urban context of Los Angeles (LA). LA was selected due to extensive road networks and visible surface distresses pattern that can be captured by satellite. This study uses high-resolution satellite imagery obtained through Google Earth Pro. To achieve this goal, the YOLOv8s-seg model, an advanced variant of the YOLO (You Only Look Once) family, was fine-tuned on a manually labeled crack dataset for realtime object detection and segmentation. The training dataset includes three main types of cracks: alligator cracks, Longitudinal and transverse cracks, and sealed cracks. Images were carefully annotated using the Roboflow platform and augmented to increase data diversity and improve model generalization.The results obtained demonstrate the potential of this approach for automatically detecting and classifying different cracks types from satellite imagery, despite the challenges posed by satellite resolution limits and background noise. The study is among the first to explore pavement crack type classification at a city scale using accessible satellite data and contributes a practical workflow for integrating AI-based surface distress assessment into pavement management strategies. The finding highlights how remote sensing and DL support cost-effective, scalable assessment of asphalt pavement conditions in major cities like Los Angeles.College of EngineeringDepartment of Civil EngineeringMaster of Science in Civil Engineering (MSCE
Explainable Supervised and Semi-Supervised Learning for Breast Cancer Risk Prediction from Questionnaires: A Study on BCSC and UAE Datasets
No full textA Master of Science thesis in Computer Engineering by Omar Ahmad Alsarookh entitled, “Explainable Supervised and Semi-Supervised Learning for Breast Cancer Risk Prediction from Questionnaires: A Study on BCSC and UAE Datasets”, submitted in June 2025. Thesis advisor is Dr. Salam Dhou. Soft copy is available (Thesis, Completion Certificate, Approval Signatures, and AUS Archives Consent Form).Breast cancer is one of the most prevalent cancers globally and remains a leading cause of death among women. While mammography helps detect existing abnormalities, it offers limited insight into the future risk of developing cancer. This highlights the need for proactive risk assessment which enables early intervention before symptoms appear. This thesis explores supervised and semi-supervised machine learning methods to classify women into low and high-risk groups using environmental and lifestyle features. Three datasets were utilized: the labeled Breast Cancer Surveillance Consortium (BCSC) Risk Estimation dataset, the unlabeled BCSC Risk Factors dataset, and a labeled private region-specific dataset from University Hospital Sharjah (UHS) in the UAE. In the supervised approach, multiple models were evaluated on the BCSC Risk Estimation dataset including XGBoost, TabNet, Random Forest, and Logistic Regression. XGBoost achieved the best performance with an F1-score of 0.93. A separate region-specific supervised model was also developed using the UHS dataset, with XGBoost again performing best (F1-score: 0.85). Since labeled medical data is often scarce and expensive to obtain, semi-supervised learning allows us to leverage large volumes of unlabeled data to improve model performance and generalization. In the semi-supervised approach, two techniques were used on the unlabeled BCSC Risk Factors dataset: Label Spreading, a graph-based method, and Self-Training, where the classifier iteratively labels data based on confidence thresholds. Pseudo-labeled samples from both methods were combined with labeled data to retrain classifiers. The best semi-supervised model (Self-Training with XGBoost) achieved an F1-score of 0.91. Generalizability was evaluated by testing the BCSC-trained models on the UHS dataset. The supervised BCSC model achieved an F1-score of 0.92, while the semi-supervised model’s F1-score dropped to 0.81 when tested on UHS data, which highlights domain shift and pseudo-label noise. SHAP and LIME were used for explainability, confirming the influence of key risk factors such as breast density, family history, and BMI. These results validate the feasibility of integrating supervised and semi-supervised approaches for proactive, population-specific breast cancer risk assessment.College of EngineeringDepartment of Computer Science and EngineeringMaster of Science in Computer Engineering (MSCoE
Numerical Modeling of Time-Fractional Phase-Change Problems
No full textA Master of Science thesis in Mathematics by Sura Azrak entitled, “Numerical Modeling of Time-Fractional Phase-Change Problems”, submitted in July 2025. Thesis advisor is Dr. Youssef Belhamadia. Soft copy is available (Thesis, Completion Certificate, Approval Signatures, and AUS Archives Consent Form).Phase-change problems, such as melting and solidification, are central to numerous natural and industrial applications. Mathematically, phase-change problems involve heat-diffusion equations in the solid and liquid regions, coupled with an interfacial condition that balances latent heat release with the motion of the solid-liquid interface, together with prescribed initial and boundary conditions. However, classical models often fail to capture the memory-dependent behavior observed in complex materials. This thesis proposes a time-fractional extension of the phase-change problem using Caputo derivatives to incorporate memory effects into the modeling of phase-change processes. A one-domain enthalpy-based formulation is derived, allowing for smooth phase transitions without explicit interface tracking. The resulting model is solved numerically using a finite difference scheme and the L1 approximation for the Caputo derivative. Several simulations are presented, demonstrating the impact of fractional order on thermal behavior and validating the model’s consistency with classical results as the order approaches one.College of Arts and SciencesDepartment of Mathematics and StatisticsMaster of Science in Mathematics (MSMTH
Determinants of Off-Balance Sheet Business in the Case of GCC Banking Sectors during Covid-19
No full textA Master of Science thesis in Accounting (MSA) by Mohamad Jomaa entitled, “Determinants of Off-Balance Sheet Business in the Case of GCC Banking Sectors during Covid-19”, submitted in August 2025. Thesis advisor is Dr. Abed Al-Nasser Abdallah. Soft copy is available (Thesis, Approval Signatures, Completion Certificate, and AUS Archives Consent Form).This study investigates the factors driving the use of off-balance sheet instruments’ usage among banks in the Gulf Cooperation Council during the Coronavirus Disease 2019. It aims to determine how macroeconomic conditions and growing credit risk influenced these banks' reliance on off-balance sheet instruments. Additionally, it explores how variations in off-balance sheet usage varied across banks based on institutional characteristics, such as bank size and profitability before, during, and after the pandemic. Lastly, the study aims to highlight the implications of increased off-balance sheet activity for financial stability and regulatory oversight during crisis periods, as indicated by the capital adequacy and loan ratios. The study used a sample of 79 banks from the Gulf Cooperation Council and employed a multiple regression model to identify the significant drivers of off-balance sheet activity. A Wilcoxon test finds no significant change in off-balance sheet activity over the three periods. However, regression models for the respective periods find bank size as the most significant determinant of off-balance sheet usage across all years, while loan ratio negatively impacted off-balance sheet activity. Profitability and liquidity exhibited weaker and largely insignificant effects. These findings underscore the role of institutional characteristics in shaping off-balance sheet activity, presenting valuable insights for policymakers and bank management in times of crisis.School of Business AdministrationDepartment of Accounting and Information SystemsMaster of Science in Accounting (MSA
Well-AI Platform: A SMART Blockchain Solution for Eliminating Bad Medical Debt
No full textA Doctor of Philosophy Dissertation in Engineering Systems Management by Inas Al Khatib entitled, “Well-AI Platform: A SMART Blockchain Solution for Eliminating Bad Medical Debt”, submitted in October 2025. Dissertation advisor is Dr. Malick Ndiaye. Soft copy is available (Dissertation, Completion Certificate, Approval Signatures, and AUS Archives Consent Form).College of EngineeringDepartment of Industrial EngineeringPhD in Engineering - Engineering Systems Management (PhD-ESM
Strengthening of Pre-Damaged Columns exposed to Fire using FRCM
No full textA Master of Science thesis in Civil Engineering by Bashar Al-Momani entitled, “Strengthening of Pre-Damaged Columns exposed to Fire using FRCM”, submitted in November 2025. Thesis advisor is Dr. Farid Abed. Soft copy is available (Thesis, Completion Certificate, Approval Signatures, and AUS Archives Consent Form).Fabric-Reinforced Cementitious Matrix (FRCM) systems have recently emerged as an effective method for strengthening and repairing concrete structures. This technology embeds textile reinforcement within an inorganic cementitious mortar, creating a durable composite. Unlike traditional epoxy-based Fiber-Reinforced Polymers (FRP), FRCM maintains structural integrity at significantly higher temperatures, offering notable advantages for fire-prone applications. This study evaluates the performance of poly-paraphenylene-benzobisoxazole (PBO)-FRCM as a retrofitting solution for fire damaged reinforced concrete (RC) short columns. Seven circular RC columns, each 1.2 meters tall and 200 mm in diameter with a 1.5% reinforcement ratio, were tested under axial compression. Two columns served as control samples and were not exposed to fire, while five columns were exposed to fire for 133 minutes in accordance with ASTM E119, then repaired with two layers of PBO-FRCM. Variables included concrete type as normal (NSC) or Ultra-high performance concrete (UHPC), pre-fire wrapping with FRCM or FRP, and the presence of a cement-based insulation system prior to fire exposure. The findings demonstrated that post-fire strengthening plays a significant role in restoring the original capacity of the tested normal concrete specimens. Repairing the fire-exposed column, which lacked both insulation and wrapping, recovered 68% of its axial capacity. Pre-fire FRCM strengthening combined with insulation improved the post-fire axial behavior to similar levels to that of the unwrapped control specimens, but the axial capacity remained about 17% lower than that of the unheated FRCM-wrapped control column. PBO-FRCM effectively
improved the axial performance of the UHPC column, where its axial capacity was 183% higher than that of the unrepaired counterpart. However, relative to the nominal
capacity predicted by ACI ITG-4.3R, the repaired column retained only 36.5% of the original capacity. Analytical predictions based on international codes closely aligned
with experimental findings, yielding experimental-to-predicted capacity ratios of 1.13–1.30 for control columns and 1.17–1.50 for fire-exposed columns, reflecting uncertainties associated with modeling post-fire material degradation.College of EngineeringDepartment of Civil EngineeringMaster of Science in Civil Engineering (MSCE
Exploring Sustainable Healthcare Waste Management Practices Date of Defense
No full textA Master of Science thesis in Engineering Systems Management by Haneen Alrabiah entitled, “Exploring Sustainable Healthcare Waste Management Practices Date of Defense”, submitted in November 2025. Thesis advisor is Dr. Vian Ahmed and thesis co-advisor is Dr. Zied Bahroun. Soft copy is available (Thesis, Completion Certificate, Approval Signatures, and AUS Archives Consent Form).College of EngineeringDepartment of Industrial EngineeringMaster of Science in Engineering Systems Management (MSESM
SWIPT-Enabled Relaying Networks for Next-Generation Wireless Systems: A Review of Achievable Rates and Future Challenges
No full textEfficiently powering the billions of mobile devices currently in use is a growing challenge, as most of these devices are battery-operated and require substantial energy for reliable signal transmission. To address this, harvesting energy from radio frequency (RF) signals has emerged as a promising solution. This approach, known as Simultaneous Wireless Information and Power Transfer (SWIPT), has garnered increasing attention from both researchers and industry due to its potential to extend battery life. Among its various applications, relaying networks represent a key area in which SWIPT can make a significant impact. These networks offer improved coverage, higher data rates, lower latency, and better energy and spectral efficiency, which are critical attributes for meeting the demands of next-generation (5G/6G) ultra-dense wireless networks. In this paper, we provide a comprehensive review of SWIPT in relaying networks, exploring its principles, structures, protocols, and technical aspects. We also examine the achievable rates in SWIPT-enabled relaying networks and discuss how machine learning could enhance these systems, presenting it as a promising direction for future research. Finally, we highlight several key challenges that remain to be addressed, emphasizing the need for continued exploration in the rapidly evolving landscape of wireless technology.American University of SharjahTelekom Research and Development Sdn Bh
INScription: Department of International Studies (INS) Issue #29 (March 27, 2025, Issue 7)
No full textCollege of Arts and SciencesDepartment of International Studie