Saudi Cultural Missions Theses & Dissertations
Permanent URI for this communityhttps://drepo.sdl.edu.sa/handle/20.500.14154/10
Browse
39 results
Search Results
Item Restricted Development of Creative AI for Subconscious Actions(Saudi Digital Library, 2026) Almuhaydib, Mohammed; Hongying, MengThis dissertation involves the technical development of the Ascended Intelligence project, an AI-driven installation. The project explores real-time voicebased emotional interaction using AI, blending sound, storytelling, and symbolic feedback. The system is designed to analyze a participant’s voice tone in real time, classify their emotional frequency, and display dynamic visuals. The overall goal is to offer an emotionally intelligent experience. Human-computer interaction and artificial intelligence bring emotion recognition into the spotlight with increasing importance in developing emotions systems. Voice is a high carrier of affect information and an implicit and non-intrusive method for detecting emotions. This dissertation discusses designing and implementing an emotional state recognition system from speech in real time with openSMILE for feature extraction and classification based on machine learning30 0Item Restricted Leveraging Digital Technology Determinants to Enhance Operational Efficiency: Insights from the Saudi Transport Sector(Saudi Digital Library, 2026) ALSUBAIE, Sultan Bader A; AlHamad, SalahSaudi Arabia’s transportation sector is undergoing rapid transformation under Vision 2030 as the country aims to become a global logistics hub. Despite major investments in transport infrastructure, many organizations continue to face operational inefficiencies such as delayed deliveries, fleet underutilization, high maintenance costs, and fragmented operational systems. Digital technologies have emerged as critical tools for addressing these challenges; however, limited research has examined their collective impact within Saudi Arabia’s transportation sector. This study investigates how artificial intelligence, Internet of Things (IoT), big data analytics, cloud computing, blockchain, cybersecurity readiness, and workforce digital readiness influence operational efficiency in Saudi transport organizations. A quantitative research design was adopted using a structured survey distributed to transportation professionals across Riyadh, Jeddah, Dammam, and NEOM. A total of 287 valid responses were analyzed using descriptive statistics, regression analysis, ANOVA, and simulation modeling. The findings revealed that IoT recorded the highest adoption level, while blockchain remained the least adopted technology. Artificial intelligence, IoT, workforce readiness, and cybersecurity readiness were identified as the strongest predictors of operational efficiency. The study concludes that digital transformation significantly improves transportation efficiency, but success depends on effective implementation, employee readiness, and cybersecurity capabilities.3 0Item Restricted Deepfake Technology: A Multi-Disciplinary Analysis of Technical, Social, Legal, and Ethical Issues(Saudi Digital Library, 2026) Alanazi, Sami; Asif, SeemalAdvances in deep learning have enabled the creation of highly realistic synthetic media capable of manipulating faces, voices, and actions with increasing fidelity. These techniques support legitimate uses in entertainment, education, and digital content production. At the same time, misuse has raised concerns linked to misinformation, privacy infringement, identity fraud, and ethical accountability. This thesis examines deepfake technology as a socio-technical problem, integrating technical analysis with social, legal, and ethical perspectives to inform effective mitigation. Three strands structure the investigation. A critical review of the literature establishes the state of generative and forensic research. Fourteen expert interviews across artificial intelligence, law, ethics, and cybersecurity provide institutional and professional context. Alongside this, empirical experimentation evaluates deep learning approaches to deepfake detection under realistic conditions. Initial technical work focused on image-based forensics, leading to the development of AI-Guard, a convolutional detection system designed for practical deployment. Evaluation results indicate that AI-Guard achieved 98% validation accuracy and 93.2% test accuracy on a dataset exceeding 450,000 images, while supporting real-time inference on mobile platforms. Video forensics forms the second technical contribution. Building on insights from earlier experiments, the thesis introduces VIDS-Guard, a forensics-aware detection framework that combines frequency-domain features, YCbCr colour decomposition, and temporal Transformer-based attention. Trained on 26,975 videos, the system achieved an accuracy of 0.91, a Macro-F1 score of 0.90, and an AUC of 0.97, outperforming established benchmark models across multiple evaluation settings. The results suggest that architectural diversity and temporal modelling improve generalisation under dataset variation. Technical findings do not stand alone. Analysis of expert perspectives and regulatory gaps indicates that detection systems, if unreliable or poorly governed, may themselves contribute to harm. Effective responses therefore appear to require coordination between deployable forensic tools, legal clarity, and ethical safeguards. By aligning system design with institutional and societal considerations, this thesis advances both practical detection capability and regulatory understanding, contributing to transparency, accountability, and resilience within the digital media ecosystem.10 0Item Restricted Data Protection in Online Banking in the United Kingdom(Saudi Digital Library, 2025) Albalawi, Reham; Warburton, JoshuaThe rise of online banking has fundamentally transformed financial services by increasing accessibility and operational efficiency. However, this transformation has introduced significant challenges concerning the protection of personal data. In light of escalating cyber threats and data breaches, this dissertation critically evaluates the efficacy of existing legal and regulatory frameworks governing data protection in online banking. It begins by outlining the core legal principles underpinning data privacy, including the General Data Protection Regulation (GDPR), the Data Protection Act 2018, and key provisions of the UK's Financial Services legislation. The analysis proceeds to examine how financial institutions implement data protection standards, with particular attention to data minimisation, consent mechanisms, encryption practices, and third-party access. Case studies are employed to highlight persistent vulnerabilities in both regulatory enforcement and corporate compliance, revealing a gap between theoretical protection and practical implementation. It is argued that while the legal framework provides a robust foundation, its fragmented application and reactive enforcement often permit systemic weaknesses to persist. Accordingly, this dissertation asserts the need for enhanced accountability mechanisms, greater regulatory harmonisation, and mandatory cybersecurity certifications for financial technology systems. Through a doctrinal and comparative methodology, it is submitted that reform must strike a balance between technological innovation and safeguarding individual privacy rights. The study concludes that a proactive and unified approach to data governance is essential for maintaining public trust and resilience in the digital banking sector.14 0Item Restricted AI Systems for Understanding and Grounding Radiology Reports(Saudi Digital Library, 2026) Baharoon, Mohammed; Pranav, RajpurkarRadiology reports are the primary medium through which radiologists communicate, conveying critical clinical information in natural language. AI holds the potential to both generate and analyze these reports, yet two key challenges persist. First, as AI systems increasingly generate radiology reports, evaluating their accuracy remains an open problem. Second, a fundamental disconnect exists between the findings described in radiology reports and their corresponding locations in the imaging studies, limiting referring physicians, patients, and trainees who must interpret findings without explicit visual guidance. This thesis addresses these challenges through three interconnected contributions spanning report evaluation, report visualization, and clinical application. First, we introduce CRIMSON, a clinically grounded evaluation metric for radiology report generation, along with two new benchmarks: RadJudge, a 30-case clinical judgment test suite, and RadPref, a 100-case radiologist preference benchmark. CRIMSON incorporates patient context and weights errors by clinical significance when comparing generated against reference reports. Validated against radiologist error counts from the ReXVal dataset, RadJudge, and RadPref, CRIMSON achieves stronger alignment with expert judgment than prior metrics. Second, we introduce ReXGroundingCT, the first publicly available dataset linking free-text radiology findings to manually annotated 3D segmentation masks in chest CT scans. Designed through a multi-stage annotation pipeline, the dataset comprises 3,142 scans and 8,028 segmented findings. We benchmark state-of-the-art text-prompted segmentation models, demonstrating that current approaches fall substantially short of clinical utility, even after fine-tuning. Subsequently, we release the dataset, along with a public leaderboard to drive continued progress on this task. Third, we present RadGame, an AI-powered platform for radiology education that brings together both report evaluation and grounding as a concrete downstream application. The platform teaches two core skills: localizing findings through interactive bounding-box annotation, and writing radiology reports with automated structured feedback. In a prospective multi-institutional study with 18 medical students, participants using RadGame achieved a 68\% improvement in localization accuracy and a 31\% improvement in report-writing scores, outperforming traditional passive learning methods. Together, these contributions address the radiology AI pipeline from multiple angles: evaluating generated reports against clinical standards, spatial grounding of reports in imaging, and applying both to advance radiology education.29 0Item Restricted Adversarial Robustness of Intrusion Detection Systems for the In-Vehicle Networks of Connected and Autonomous Vehicles(Saudi Digital Library, 2026) ALORAINI, FATIMAH SULAIMAN; Javed, AmirConnected and autonomous vehicles (CAVs) rely on machine learning (ML)-based intrusion detection systems (IDSs) to secure in-vehicle network (IVN) communications. However, ML models are inherently vulnerable to adversarial attacks. While prior adversarial research in CAVs has predominantly focused on perception models, particularly object detection, the robustness of IVN-based IDSs remains largely underexplored. This thesis addresses this gap by investigating the adversarial robustness of IVN-based IDSs, introducing an IVN-specific threat taxonomy, and developing an attack method capable of generating adversarial IVN frames under varying levels of attacker knowledge of the deployed IDS model. Experimental results demonstrate that adversarial manipulation poses a severe threat to IVN-based IDSs. Under complete attacker knowledge of the deployed IDS model, detection performance drops from an F1-score of 99%toaslowas19%, withattacksuccess rates reaching up to 89%. Even under limited knowledge, detection performance decreases from 95% to 38%, with success rates of up to 60%. To mitigate these vulnerabilities, this thesis proposes Explainability guided Counterfactual Adversarial Training (EXCAT), a novel defense mechanism that leverages model explainability to generate more representative adversarial training examples. EXCAT restores detection performance to up to 94% and reduces attack success rates to as low as 7.55%, demonstrating that explainability-guided training offers a promising direction for strengthening IVN-based IDS robustness and improving the safety of deployed CAV systems.21 0Item Restricted Evaluation of Modified AI-Enhanced Radiographic Images of Artificial Teeth for Caries Removal Decision-Making in Predoctoral Dental Students(Saudi Digital Library, 2026) Aldandan, Sukaina; Fontana, Margherita; Neiva, GiseleBackground: Accurate radiographic interpretation is essential for caries removal decision-making but remains challenging for early dental learners. Artificial intelligence (AI) has demonstrated promise in improving caries detection; however, its role in supporting operative decision-making during preclinical training remains unclear. Objective: To evaluate the effect of modified AI-enhanced radiographic images on the quality of caries removal performed by first-year dental students and to determine whether the effect of modified AI-enhanced images differs between shallow and deeper lesions. Methods: A two-period crossover study was conducted involving first-year dental students in a preclinical operative dentistry course. Participants performed caries removal on standardized 3D-printed teeth containing either shallow or deeper carious lesions. Students completed procedures using either standard bitewing radiographs or modified AI-enhanced radiographic images. Caries removal quality was assessed using the Composite Caries Removal Quality Score (CRQS), which incorporated convenience form, caries removal at the dentinoenamel junction (DEJ), caries removal at the pulpal floor. Completion time was also recorded. Results: Modified AI-enhanced radiographic images significantly improved overall CRQS compared with standard radiographs (p = 0.002). This improvement was primarily observed in shallow lesions, which demonstrated significantly higher CRQS scores under the modified AI-enhanced condition (p = 0.001), whereas no significant difference was found for deeper lesions (p = 0.727). The greatest improvement was observed in convenience form for shallow lesions (p < 0.001). No significant differences were detected for caries removal at the DEJ or pulpal floor. Lesion depth significantly influenced several outcomes, with deeper lesions demonstrating lower DEJ scores and requiring longer completion times. Modified AI-enhanced images did not significantly affect completion time. Conclusions: Modified AI-enhanced radiographic images improved the quality of caries removal performed by first-year dental students, particularly for shallow lesions where radiographic interpretation is more challenging. The benefits were primarily related to improved convenience form rather than caries removal at the DEJ or pulpal floor. These findings suggest that modified AI-enhanced radiographic images may be a valuable adjunct in preclinical dental education and may support the development of diagnostic and operative decision-making skills in early learners.10 0Item Restricted Toward Robust Mental Health Classification Systems Across Genres and Languages(Saudi Digital Library, 2026) Alqahtani, Amal Abdullah; Diab, Mona; Hwa, RebeccaMental health conditions are a major global public health challenge, yet many individuals do not receive appropriate care because of stigma, limited access to services, and the difficulty of accurate assessment. Natural Language Processing (NLP) has shown growing promise for identifying mental health conditions through language, but existing systems often struggle to generalize across modalities, domains, conditions, and languages. Existing approaches leave critical gaps in condition specificity, cross-genre robustness, and multilingual coverage. Prior work often studies isolated features or a single modality, leaving open how language markers behave across both writing and speech for the same condition. Condition-specific continual pretraining remains underexplored relative to generic mental health adaptation. Cross-condition transfer from clinically comorbid disorders has been proposed but rarely validated. And the field remains overwhelmingly English-centric, with Arabic among the most underserved languages despite its more than 400 million speakers. This dissertation addresses these gaps through a progression from interpretable linguistic analysis to multilingual evaluation, using schizophrenia as a core case study. We first present an integrated analysis of cohesion features, pragmatic cues, and language model-based measures across clinical speech and writing, showing that patients exhibit heightened fear, higher neuroticism, reduced specificity, and lower cohesion, with effects generally stronger in writing. We then evaluate these signals through supervised classification, finding that cohesion is the strongest standalone structured feature view in writing, while a TF-IDF lexical baseline dominates in speech. Moving to neural modeling, we show that progressive multi-stage continual training of BERT on patient-generated social media achieves an 11.7% relative F1 improvement over base BERT and outperforms MentalBERT and ClinicalBERT for schizophrenia detection. We then demonstrate that focused cross-condition transfer outperforms broad mental health pretraining, with StressRoBERTa achieving 82% F1 on the SMM4H 2022 stress detection benchmark. To extend mental health NLP beyond English, we introduce ArMHC, a large-scale Arabic mental health corpus from X (formerly Twitter) constructed through a dialect-aware extraction pipeline with LLM-based validation, covering 18 conditions across 1,911 users. Using the ArMHC schizophrenia subset, we evaluate cross-lingual and cross-genre transfer from English clinical data to Arabic social media, finding that both language and genre mismatch contribute substantially to transfer degradation, with genre mismatch being qualitatively more destructive: cross-lingual same-genre transfer still permits partial detection, while cross-genre transfer falls below chance. Overall, this dissertation demonstrates that robust mental health NLP benefits from combining interpretable linguistic analysis with domain-adaptive and transfer-based modeling, while expanding into low-resource multilingual settings. The findings contribute new linguistic evidence, modeling strategies, and dataset resources for building more inclusive and clinically relevant computational approaches to mental health assessment.22 0Item Restricted Artificial Intelligence through Machine Learning techniques to enhance the application of 3D body scanning in apparel shape and sizing(Saudi Digital Library, 2026) Alhassawi, Ruqey Ali; Simeon, Gill; Steve, Hayes; Kristina, BrubacherSignificant challenges persist in realising the full potential of technology related to accurate and inclusive body dimension variation and garment sizing and fit. Traditional methods often fail to capture the complexity of human body morphology, highlighting the value of more detailed approaches to analysing body dimension variation. This doctoral research aims to support the visual analysis of anthropometric population data through the integration of artificial intelligence (AI) and machine learning (ML) techniques, addressing limitations in traditional anthropometric methods used for apparel sizing and body–to–pattern mapping. A mixed–methods approach was employed across five interconnected phases, leveraging 3D body scanning (3DBS) technology to analyse and compare real–world body dimensions, classical garment sizing classifications and garment patterns. The research involved: (1) a comprehensive analysis of 3DBS data to establish body dimension diversity, (2) a critical reassessment of the traditional 8–head figure ratio, (3) clustering algorithms (Hierarchical, self–organizing map (SOM), k–means) to classify body types, (4) application of support vector machine (SVM) and principal component analysis–SVM (PCA–SVM) models for accurate size prediction, and (5) enhanced regression analysis to develop a data–driven approach for garment pattern adjustment. A dataset of 677 female participants from a range of ethnic backgrounds was utilised. Significant dimensional variations within conventional size groups were identified, revealing limitations in traditional measurement-based sizing systems within the study sample. Key findings demonstrate frequent deviations from the classical 8–head figure proportion model, emphasising the need for a more comprehensive approach. Clustering algorithms successfully delineated distinct morphological categories, while SVM modelling exposed trade–offs between predictive accuracy and computational complexity. Regression analysis established quantitative relationships between body measurements and pattern block parameters, offering a means of examining how body dimension variation relates to patternmaking practice. This research makes several theoretical, methodological and practical contributions. Theoretically, it provides data-based evidence of body proportion variability within standard size categories, challenges the classical 8-head figure proportion model using measured data, and identifies distinct body shape clusters within the study sample. Methodologically, it applies an integrated analytical framework – combining 3D body scan data, statistical analysis, ML clustering and classification, and regression analysis – to examine body dimension variation and body-to-pattern relationships. Practically, it provides how data-driven analysis of anthropometric variation may inform patternmaking considerations, subject to further applied investigation. This research examines the integration of 3D body scanning and computational techniques within anthropometric analysis. The use of data-based derived visual tools provides a means of representing and exploring body variation within the study sample. The findings highlight the potential relevance of data-driven approaches to sizing and may inform further investigation into how body diversity is represented within garment sizing systems.19 0Item Restricted Assessing the Accuracy of Artificial Intelligence Synthetic CT Generation for Liver and Brain MRI-Only Radiotherapy(Saudi Digital Library, 2025) Aljaafari, Lamyaa; SPEIGHT, Richard; BIRD, David; Buckley, David; ALQAISIEH, BasharBackground: Magnetic resonance imaging (MRI) is increasingly integrated into radiotherapy because of its superior soft-tissue contrast compared with computed tomography (CT). This has prompted interest in four-dimensional (4D) MRI for motion management and MRI-only radiotherapy using synthetic CT (sCT) for dose calculation and patient positioning verification. This thesis aimed to provide clinical evidence for the technical feasibility and clinical implementation of MRI-only radiotherapy for liver and brain cancer. Methods: (i) A PRISMA-guided systematic review of the 4D MRI literature for abdominal radiotherapy was conducted. (ii) A deep-learning sCT model was developed using clinical MRI and CT data to generate liver MRI-only radiotherapy. (iii) The performance of a commercial sCT solution (Philips MRCAT) was assessed for brain MRI-only radiotherapy. For both liver and brain, dosimetric accuracy was evaluated using dose volume histogram (DVH) analysis. In addition, image-guided patient positioning was verified using the clinical XVI system. Results: (i) The systematic review, encompassing 39 studies, indicated that 4D MRI had the potential to improve abdominal radiotherapy by enabling accurate tumour definition and motion characterisation compared to 4D CT. (ii) For the liver sCT model, relative mean dose differences between CT and sCT were 0.0% for the planning target volume (PTV) and <0.5% for all organs at risk (OARs). Positioning verification revealed mean translational and rotational differences of <0.5 mm and <0.5°, respectively. (iii) For the brain MRCAT, relative mean dose differences were <0.4% for the PTV and <0.3% for OARs, with positioning accuracy maintained within ±1 mm and ±1°. Conclusion: 4D MRI shows considerable promise for motion management, but its clinical implementation remains limited, by lack of robust clinical validation or standardisation. Both liver and brain sCT models demonstrated dosimetric and positioning accuracy comparable to CT, confirming the technical feasibility of MRI-only radiotherapy for the liver and its clinical applicability for the brain.10 0