Saudi Cultural Missions Theses & Dissertations
Permanent URI for this communityhttps://drepo.sdl.edu.sa/handle/20.500.14154/10
Browse
54 results
Search Results
Item Restricted Deep Learning based Cancer Classification and Segmentation in Medical Images(Saudi Digital Library, 2025) Alharbi, Afaf; Zhang, QianniCancer has significantly threatened human life and health for many years. In the clinic, medical images analysis is the golden stand for evaluating the prediction of patient prog- nosis and treatment outcome. Generally, manually labelling tumour regions in hundreds of medical images is time- consuming and expensive for pathologists, radiologists and CT scans experts. Recently, the advancements in hardware and computer vision have allowed deep-learning-based methods to become main stream to segment tumours automatically, significantly reducing the workload of healthcare professionals. However, there still remain many challenging tasks towards medical images such as auto- mated cancer categorisation, tumour area segmentation, and relying on large-scale labeled images. Therefore, this research studies theses challenges tasks in medical images proposing novel deep-learning paradigms that can support healthcare professionals in cancer diagnosis and treatment plans. Chapter 3 proposes automated tissue classification framework called Multiple Instance Learning (MIL) in whole slide histology images. To overcome the limitations of weak super- vision in tissue classification, we incorporate the attention mechanism into the MIL frame- work. This integration allows us to effectively address the challenges associated with the inadequate labeling of training data and improve the accuracy and reliability of the tissue classification process. Chapter 4 proposes a novel approach for histopathology image classification with MIL model that combines an adaptive attention mechanism into an end-to-end deep CNN as well as transfer learning pre-trained models (Trans-AMIL). Well-known Transfer Learning architectures of VGGNet [14], DenseNet [15] and ResNet[16] are leverage in our framework implementation. Experiment and deep analysis have been conducted on public histopathol- ogy breast cancer dataset. The results show that our Trans-AMIL proposed approach with VGG pre- trained model demonstrates excellent improvement over the state-of-the-art. Chapter 5 proposes a self-supervised learning for Magnetic resonance imaging (MRI) tu- mour segmentation. A self-supervised cancer segmentation framework is proposed to re- duce label dependency. An innovative Barlow-Twins technique scheme combined with swin transformer is developed to perform this self supervised method in MRI brain medical im- ages. Additionally, data augmentation are applied to improve the discriminability of tumour features. Experimental results show that the proposed method achieves better tumour seg- mentation performance than other popular self- supervised methods. Chapter 6 proposes an innovative Barlow Twins self supervised technique combined with Regularised variational auto-encoder for MRI tumour images as well as CT scans images segmentation task. A self-supervised cancer segmentation framework is proposed to reduce label dependency. An innovative Barlow-Twins technique scheme is developed to represent tumour features based on unlabeled images. Additionally, data augmentation are applied to improve the discriminability of tumour features. Experimental results show that the pro- posed method achieves better tumour segmentation performance than other existing state of the art methods. The thesis presents four approaches for classifying and segmenting cancer images from his- tology images, MRI images and CT scans images: unsupervised, and weakly supervised methods. This research effectively classifies histopathology images tumour regions based on histopathological annotations and well-designed modules. The research additionally comprehensively segments MRI and CT images. Our studies comprehensively demonstrate label-effective automatic on various types of medical image classification and segmentation. Experimental results prove that our works achieve state-of-the-art performances on both classification and segmentation tasks on real world datasets9 0Item Restricted Breast Tumors AI-Based Early Identification using Screening Mammography for Adult Women(Saudi Digital Library, 2025) Almansour, Tareg Mohammed H; Abdelrazek, Elmetwally M; Elgarayhi, Ahmed; Medhet, TamerEarly detection of breast cancer (BrC) is one of the best strategies to prevent the disease's spread. This makes an autonomous diagnosis system based on deep learning (DL) attractive for improving the accuracy of detection and prediction. This study suggests employing transfer DL models to categorize BrC from mammograms. Furthermore, to identify BrC detection architectures, transfer DL models are applied to various well-known convolutional neural networks (CNNs). Three CNNs (NasNetMobile, EfficientNet-b0, and MobileNetV2) are adjusted in particular ways before being used. All systems use two types of optimizers: root mean square propagation (RMSP) and adaptive moment estimation (ADAM). The EfficientNet-b0 network attains 96.45% accuracy, 96.63% sensitivity, and 97.18% F1-score when using the ADAM optimizer. The experimental results demonstrate that EfficientNet-b0 outperforms other sophisticated CNN techniques and offers a number of advantages. Additionally, EfficientNet-b0 obtained an F1-score of 96.00%, a sensitivity of 96.55%, and an accuracy of 95.04% utilizing the RMSprop optimizer. To sum up, this work improves the identification of BrC for adult women by applying transfer DL models to digital mammography scans. The best-performing CNN among the three (NasNetMobile, EfficientNet-b0, and MobileNetV2) was EfficientNet-b0 optimized with ADAM and RMSprop. These results show how these structures could improve healthcare and increase the accuracy of BrC detection.15 0Item Restricted AI Impersonation on social media Analysing Human Characteristics and Ethical Implications(Saudi Digital Library, 2025) Almuammar, Eyad; Fahad, AhmadThis study explores the behavioural, ethical, social, and regulatory implications of AI bots that impersonate humans on social media platforms. As artificial intelligence becomes increasingly integrated into online communication, AI-driven bots are being deployed to mimic human users, influence opinions, and automate engagement. While these technologies offer efficiency, they also raise serious concerns about misinformation, manipulation, transparency, and digital trust. Using a structured online questionnaire distributed via platforms such as Twitter (X), LinkedIn, and WhatsApp, this research gathered responses from 57 participants. The survey examined user perceptions across multiple dimensions, including their confidence in identifying bots, behavioural changes due to bot exposure, ethical concerns, perceived political influence, and expectations for regulation and education. Findings indicate that while many users feel moderately confident in recognizing bots, they also express reduced trust and engagement when bots are suspected. Ethical concerns particularly around privacy and undisclosed AI interaction were prominent, and users widely supported stronger regulation, transparency tools, and public education initiatives. The study concludes that AI bots pose a significant challenge to online authenticity and democratic discourse and highlights the need for multi-stakeholder governance to ensure safe and ethical deployment of such technologies.4 0Item Restricted Artificial Intelligence Law in Saudi Arabia(ST.Thomas Uinversity, 2025) Alharbi, Ibrahim; Wiessner, SiegfriedThis dissertation examines the legal and regulatory frameworks governing artificial intelligence in Saudi Arabia, analyzing the intersection of modern technological advancement with traditional Islamic principles and international standards. Through the lens of the New Haven approach, this research investigates how Saudi Arabia balances innovation with cultural values while developing comprehensive AI regulations. The study focuses particularly on the kingdom's efforts to establish effective legal mechanisms for AI governance while maintaining alignment with Sharia principles and meeting global technological standards. The research employs a comparative methodology, analyzing Saudi Arabia's regulatory approach alongside the United States' frameworks, identifying potential areas for enhancement while recognizing the unique cultural and legal context of the Kingdom. This analysis reveals significant developments in Saudi Arabia's AI regulatory landscape, particularly through initiatives such as Vision 2030 and the establishment of the Saudi Data and Artificial Intelligence Authority (SDAIA), while also identifying areas requiring further development. Key findings demonstrate that Saudi Arabia's approach to AI regulation reflects a sophisticated understanding of the need to balance technological advancement with ethical considerations and cultural preservation. The research identifies crucial areas for regulatory development, including the need for specialized legal frameworks addressing AI-specific challenges, enhanced institutional capacity for implementation, and mechanisms for ensuring compliance with both international standards and Islamic principles. The study makes several original contributions to the field. First, it provides a comprehensive analysis of Saudi Arabia's emerging AI regulatory framework from both legal and ethical perspectives. Second, it demonstrates how Islamic legal principles can effectively guide modern technological regulation. Third, it offers practical recommendations for developing regulatory frameworks that serve both technological advancement and social welfare. This research has significant implications for policymakers, legal practitioners, and technology developers in Saudi Arabia and beyond. It suggests the need for a carefully balanced approach that promotes innovation while protecting social values and individual 8 rights, potentially serving as a model for other nations seeking to harmonize technological advancement with cultural preservation.27 0Item Restricted Artificial Intelligence for Automatic Attachment Assessment in School-Age Children: An Approach Based on Language and Paralanguage.(Saudi Digital Library, 2025-06-17) Buker, Areej; Vinciarelli, AlessandroAttachment is a psychological construct that provides a framework for understanding how individuals perceive and interpret social interactions, navigate relational dynamics, and experience and regulate their emotional states, particularly under conditions of stress. An attachment style begins to develop within the first few months of life, shaped by a child’s interactions with their primary caregivers. Consistent and nurturing care promotes the development of a secure attachment style, whereas inconsistent or inadequate caregiving often gives rise to insecure attachment patterns. Insecure attachment is linked to a range of challenges, including behavioural issues such as antisocial tendencies; mental health difficulties like anxiety, emotional dysregulation, and body image concerns; and heightened risks of physical health problems, including sleep disturbances. Early recognition and intervention for insecure attachment increases the likelihood of reshaping maladaptive patterns into secure ones, potentially reducing attachment-related challenges. Automated approaches for attachment recognition offer significant benefits, including consistent delivery of assessments, such as the MCAST, and broader accessibility to a wider population. While there are a few available systems for delivering attachment tests (e.g., CMCAST and SAM), the limited studies focused on developing automated classifiers to analyse the collected data have shown a suboptimal performance. These classifiers often struggle to recognise insecure attachment, achieving a maximum Accuracy of only 62.7%. Furthermore, these studies fail to offer insights into the reasoning behind their classifications, missing an opportunity to advance the understanding of attachment in early to middle childhood. This developmental stage—characterised by significant changes that include the expansion of social circles and the internalisation of emotional representations—has historically received less attention in a field predominantly focused on studying attachment markers in infants and adults. This thesis focuses on two primary objectives: enhancing the automated classification of attachment styles in children, particularly insecure attachment, and identifying markers associated with these styles. The study employs two modalities—language and paralanguage— along with emotions derived from both modalities. These modalities are utilised within a unimodal and a multimodal framework. Among all classifiers developed using the same dataset, the language-based unimodal approach demonstrated the highest effectiveness, achieving exceptional performance in recognising insecure attachment with an Accuracy of 82.2%, all while relying on relatively simple methodologies. Furthermore, this research identified linguistic, acoustic, and emotional markers of attachment, offering valuable insights into attachment representations in children.41 0Item Restricted DOES AI INTEGRATION MODERATE THE RELATIONSHIP BETWEEN FIRM GROWTH AND PERFORMANCE IN SMES: THE INFLUENCE OF DECISION-MAKING AND OPERATIONAL PERFORMANCE(University of South Alabama, 2025-05) AlQahtani, Dalal T; Butler, Frank C; Gillis, William E; Hair Jr, Joe F; Scott, Justin TToday’s dynamic business environment requires small and medium-sized enterprises (SMEs) to keep up with technological advancements in order to remain competitive. Business growth creates more challenges for SMEs since they possess fewer available resources than big organizations. Since the introduction of artificial intelligence (AI), several SMEs have been able to compete more effectively and deliver better performance. As part of this research, I examine the possibility that AI integration (AII) will moderate the relationship between firm growth and both decision-making and operational performance, ultimately affecting the performance of SMEs. The aim of this research is to provide practical implications for AI as a strategic resource for improving decision-making capabilities, performance and growth by utilizing the resource-based view (RBV) and information processing theory (IPT). A partial least squares structural equation model (PLS-SEM) was used to analyze data from 338 SME business strategy decision-makers in the United States. In order to verify the measurement model’s reliability and validity, a Confirmatory Composite Analysis (CCA) was performed, followed by the evaluation of the structural model in order to test the hypotheses. In contrast to initial hypotheses, this study found that firm growth is positively related to both decision-making and operational performance. Nevertheless, the study results support the original hypothesis that both decision-making performance (DMP) and operational performance (OPP) positively affect a firm’s performance. Furthermore, AII significantly moderated the relationship between FG and OPP, while it did not significantly moderate the relationship between FG and DMP. This indicates the complexity of the role AI integration plays in SMEs. The paper concludes with recommendations for future research, as well as guidance for practitioners regarding how SMEs can improve their decision-making capabilities and performance using AI.29 0Item Restricted Assessing the Regulation of Medical Artificial Intelligence in Clinical Settings: Considerations for Form, Process, Authority, and Timing(University of Pittsburgh, 2025) Alotaibi, Hazim; Crossley, MaryThe rapid integration of artificial intelligence (AI) into healthcare has introduced a transformative category of technologies known as Medical Artificial Intelligence (MAI). These tools, often approved by the U.S. Food and Drug Administration (FDA), are now used to assist in diagnosis, treatment planning, patient monitoring, and clinical decision-making. However, MAI poses novel regulatory challenges due to its dynamic, adaptive, and sometimes opaque nature. This dissertation critically examines the current regulatory frameworks governing MAI in the United States, focusing on tools used by health professionals in clinical settings. Drawing on legal theory, empirical data, and interdisciplinary analysis, the study explores how MAI fits—or fails to fit—within existing regulatory categories designed for conventional medical devices. It analyzes FDA approval trends, clearance pathways, medical specialties, and manufacturer profiles for over 1,000 FDA-approved AI/ML-enabled devices. The study also investigates gaps in post-market surveillance, algorithmic transparency, and the role of third-party evaluators. Chapters in this dissertation evaluate the scope and limits of current regulatory mechanisms, such as the FDA’s 510(k), De Novo, and PMA pathways, and discuss the involvement of other regulatory bodies including the Federal Trade Commission and Department of Health and Human Services. Particular attention is given to unresolved legal questions, such as liability in AI-induced errors, the classification of MAI as a “system” versus a “device,” and the role of evolving real-world performance in determining regulatory adequacy. Ultimately, this work proposes a tailored regulatory framework that is adaptive, risk-based, and harmonized across international borders. It advocates for collaborative governance involving public agencies, private innovators, and global partners to ensure that regulation keeps pace with technological advancement while protecting patients, supporting clinicians, and promoting innovation.29 0Item Restricted The Integration of Artificial Intelligence (AI) In Business Operations(La Trobe University, 2022) Alqahtani, Raed Ayidh; Soh, BenThis research investigates the integration of Artificial Intelligence (AI) in business operations. AI has become increasingly prevalent in various industries due to its potential to enhance efficiency, improve decision-making, and drive innovation. However, there is a lack of comprehensive understanding of how AI integration has been implemented in the business context. Therefore, this study utilizes a systematic review approach, following the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) methodology, to examine and synthesize existing literature on AI integration in business operations. The primary outcomes of this research will provide insights into the current state of AI integration in businesses, identify common challenges and benefits, and highlight potential areas for future research. This research contributes to the understanding of the impact of AI on business operations, paving the way for the effective and successful implementation of AI in organizations.32 0Item Restricted The ethical implications of using Multimodal Learning Analytics: a framework for research and practice(University College London (UCL), 2025) Alwahaby, Hifa; Cukurova, MutluA growing number of multimodal data (MMD) streams and complex artificial intelligence (AI) models are being used in learning analytics research to allow us to better understand, model and support learning, together with teaching processes. Considering MMDs’ potentially more invasive, extremely granular and temporal nature compared to log files, they may present additional ethical challenges in comparison to more traditional learning activity data. The systematic review undertaken during this study revealed a dearth of ethical considerations in previous multimodal learning analytics (MMLA) literature. Consequently, this study aims to identify the ethical issues associated with the use of MMLA and propose a practical framework to assist end-users to become more aware of these issues and potentially mitigate them. To gain a better understanding of the ethical issues and how they may be mitigated, the study aims to investigate the ethical concerns associated with the use of MMLA in higher education by collecting the opinions and experiences of appropriate stakeholders. Accordingly, structured individual interviews were conducted via Microsoft Teams, a video conferencing software, due to COVID-19 restrictions. In total, 60 interviews were conducted with educational stakeholders (39 higher education students, 12 researchers, eight educators and one representative of an educational technology company). Based on the thematic coding of verbatim transcriptions, nine distinct themes were identified. In response to the themes and accompanying probing questions presented to the MMLA stakeholders, and based on the ethical guidance and recommendations identified from previous literature, a first draft of the MMLA ethical framework was prepared. Subsequently, the draft was evaluated by 27 evaluators (seven higher-education students, 13 researchers–practitioners, four teachers, one ethics expert and two policymakers) by means of structured interviews. Additionally, a group of researchers adopted the framework in their research and provided constructive feedback. Based on the thematic analysis of the interviews, the framework was continually improved for three rounds until data saturation was achieved. This resulted in the presentation of the first MMLA ethical framework, which was the principal goal of this study. This thesis delivers three key contributions: (1) a systematic review of previous MMLA literature that confirms the lack of ethical considerations in the literature; (2) an examination of the ethical issues connected with MMLA from the perspective of different stakeholders; and (3) an ethical MMLA framework for higher education. By developing the framework, this thesis aims to increase awareness of the potential ethical issues and therefore, alleviate them by promoting a more ethical design, along with the development and use of MMLA in a higher education setting.24 0Item Restricted Design, analysis, and evaluation of highly secure smart city infrastructures and services(University of Arizona, 2025) Almazyad, Ibrahim; Hariri, SalimCritical infrastructure resources and services, such as energy networks, water treatment facilities, and 5G telecommunications, form the backbone of national security and public welfare. However, many of these infrastructures rely on outdated technologies, rendering them increasingly vulnerable to evolving cyber threats. As these infrastructures become increasingly digitized and integrated under Industry 4.0 - integrating cloud computing, Artificial Intelligence (AI), and the Industrial Internet of Things (IIoT) - they simultaneously introduce a broader attack surface susceptible to threats such as sensor spoofing, Denial-of-Service (DoS), and man-in-the-middle attacks. Existing critical infrastructure testbeds are isolated and limited in their ability to replicate cross-domain dependencies and security vulnerabilities inherent in modern smart cities. To address this gap, this dissertation developed a Federated Cybersecurity Testbed as a Service (FCTaaS) environment, an innovative approach that integrates geographically dispersed critical infrastructure testbeds to enable the development and experimentation of effective algorithms to secure the normal operations of critical infrastructures against a wide range of cyberattacks. The research specifically focused on two critical infrastructures: The Water Treatment Facility Testbed (WTFT) and the 5G Telecommunication Testbed (5GTT). It begins with a comprehensive threat modeling across Industrial Control Systems (ICS) and 5G architecture to identify vulnerabilities, followed by designing and implementing security detection and mitigation algorithms. Specifically, we have developed an edge-deployed anomaly detection algorithm that is based on an autoencoder that achieved 98.3% accuracy in detecting cyberattacks against water treatment infrastructure. We have also demonstrated the effectiveness of our security defense algorithms in detecting cyberattacks against 5G networks with an accuracy of 98.9% against various cellular network attacks. This dissertation developed a unified and scalable cybersecurity research environment that significantly facilitates the development of realistic critical infrastructure experimentations and AI-driven security algorithms to secure and protect their normal operations against any type of cyberattacks known or unknown, regardless of their origins, insider or outsider.28 0