SACM - United States of America
Permanent URI for this collectionhttps://drepo.sdl.edu.sa/handle/20.500.14154/9668
Browse
1900 results
Search Results
Item Restricted ADVANCES IN REAL-TIME AMERICAN SIGN LANGUAGE RECOGNITION SYSTEM USING DEEP LEARNING TECHNIQUES FOR ENHANCED ACCESSIBILITY(Saudi Digital Library, 2026) Alsharif, Bader; Ilyas, MohammadAdvancements in technology have significantly contributed to the development of innovative tools aimed at improving communication and accessibility for individuals with hearing impairments. This dissertation explores various machine learning and deep learning techniques for recognizing American Sign Language (ASL) gestures, focusing on enhancing accessibility and bridging the communication gap between hearing-impaired and hearing individuals. Traditional machine learning models, such as Random Forest, Support Vector Machines (SVM), and K-Nearest Neighbors (KNN), alongside deep learning architectures like AlexNet, ResNet-50, EfficientNet, ConvNeXt, and VisionTransformer, were investigated for their effectiveness. Experiments conducted on an extensive dataset of 87,000 ASL gesture images revealed exceptional recognition accuracy, with ResNet-50 achieving 99.98% and Random Forest reaching 99.55%, while other models performed within a range of 97% to 98%. Building on these findings, an innovative real-time recognition system was developed, integrating computer vision and deep learning techniques. The project initially utilized MediaPipe for precise hand movement tracking and YOLOv8, a state-of-the-art object detection model, to translate ASL gestures into text in real time. A comprehensive dataset of 29,820 annotated images was created to ensure strong generalization across diverse hand positions and lighting conditions. MediaPipe’s hand landmark annotations significantly enhanced input quality, improving the YOLOv8 models training accuracy. In addition, a more advanced framework was later designed that integrates YOLOv11 with MediaPipe for robust real-time ASL alphabet recognition. This system was trained on a large-scale dataset of 130,000 annotated images with custom keypoint-based annotations, enabling the model to capture subtle variations in hand and finger positions. Experimental evaluation demonstrated outstanding performance, achieving a mean Average Precision (mAP@0.5) of 98.2% with minimal latency, confirming its suitability for real-time applications in education, healthcare, and professional environments. Overall, the findings of this dissertation underscore the transformative potential of AI-driven solutions for ASL recognition. By bridging communication gaps through both traditional classification models and real-time deep learning frameworks, this work contributes to fostering inclusivity, accessibility, and independence for individuals with hearing impairments.6 0Item Restricted PATHWAYS TO FUNCTION VIA THE EMERGENCE OF A MECHANICAL SWITCH IN EVOLVABLE MATTER(Saudi Digital Library, 2025) Alqatari, Samar; Sidney, NagelThe underlying principles of how sharp switches occur in rugged fitness landscapes, while integral for understanding evolution of function and adaptation in biological systems, re- main elusive. Here I use elastic mechanical networks as a platform for probing the physical principles governing single-mutation transitions between two highly-fit, incompatible func- tions. The function used is an allosteric coupling of two pairs of source and target nodes that respond to an input strain in-phase or out-phase with each other. I study the complete fitness landscapes for ensembles of networks, and find that high-fitness pathways between these functions nearly always exist. At the largest fitness threshold for viable evolution, the functional transitions occur via a “jumper” mutation: a single bond addition or deletion that connects distinct fitness peaks with opposite functions. These mutations can be viewed as a mechanical switch, which I find can switch between incompatible functions with minimal perturbation to the system. In some cases, the mere presence of a bond, regardless of stiff- ness, constrains the deformation mode and determines function. However, bond formation or breaking is not always necessary: subtle geometric deformations that conserve connectivity can be sufficient to induce sharp functional transitions. The study of this physical system suggests that the single mutation function switches often found in biological systems may be fundamentally mechanical in origin.7 0Item Restricted EXAMINING PATIENT SAFETY CULTURE TRENDS IN U.S. HEALTHCARE THROUGH A MULTI-YEAR ANALYSIS(Saudi Digital Library, 2026) Alabdullah, Hassan; Karwowski, WaldemarPatient Safety Culture (PSC) is recognized as a cornerstone of healthcare quality and a key determinant of patient outcomes. Despite the Institute of Medicine’s early calls to establish safety-oriented systems, evidence on the long-term stability of PSC in U.S. hospitals has remained limited. This dissertation addresses this gap through a multi-year evaluation of PSC using the Hospital Survey on Patient Safety Culture (HSOPSC v1.0) and advanced statistical methods. Drawing on one of the largest national datasets—comprising over 993,000 healthcare providers from 1,601 U.S. hospitals across three survey cycles (2013–2020)—the study employed a longitudinal repeated cross-sectional design. Analyses combined descriptive statistics, second-order factor modeling, and Partial Least Squares Structural Equation Modeling (PLS-SEM) with multi-group analysis to capture temporal trends, determinants, and outcomes of PSC. Findings showed that overall PSC scores averaged 65% across years, with strengths in “Supervisor/Manager Expectations” and “Teamwork within Units,” and persistent weaknesses in “Nonpunitive Response to Error” and “Handoffs and Transitions.” PSC declined slightly over time, with regional and institutional variations: smaller, non-teaching, and Southern/Central hospitals reported higher PSC. Hospital size and region exerted inconsistent effects, while workforce factors—such as staff role, tenure, and patient contact—were stronger and more stable predictors of PSC outcomes. Importantly, PSC demonstrated robust predictive power, explaining 56.7% of the variance in overall safety perceptions and 23.2% in error reporting frequency. The dissertation provides rare longitudinal evidence confirming PSC as a dynamic, multidimensional construct. While PSC’s influence on safety outcomes has strengthened over time, sustaining improvements remains challenging, particularly in fostering blame-free reporting, ensuring adequate staffing, and improving care transitions. Practical implications highlight leadership commitment, nonpunitive systems, and workforce-centered strategies, alongside interprofessional education to embed safety in daily practice. Collectively, the findings offer actionable insights for policy, leadership, and training, while advancing methodological rigor in PSC research.12 0Item Restricted Saudi and American Students’ Motivation and Anxiety in Online Collaborative Learning in The United States(Saudi Digital Library, 2024) Alqarni, Nawal; Boston, MelissaThis research study aims to explore motivation and anxiety Saudi and American students in online collaborative learning environments through online courses in U.S. universities and how they relate to their academic performance. The study utilized a quantitative approach for data collection through an online survey of 99 Saudi students and 39 American students who were enrolled in U.S. universities. The results showed that there was no significant difference in motivation scores between undergraduate Saudi students and their American counterparts. Nor was a significant difference observed in motivation scores between graduate Saudi students and graduate American students. The data also indicated no significant relationship between motivation scores and anticipated self-reported academic performance among undergraduate Saudi and American students. For graduate students, the correlation between motivation scores and anticipated academic performance was weak and non-significant for both Saudi and American students. Additionally, a significant difference in anxiety scores was found between Saudi and American students in both the undergraduate and graduate groups, with American students exhibiting higher anxiety levels than their Saudi counterparts. However, there was no significant relationship between anxiety scores and anticipated self-reported academic performance for either Saudi or American students across both undergraduate and graduate levels. The results also revealed that the relationship between motivation and anxiety among both Saudi and American students was weak and not statistically significant. Finally, the support structures in online courses survey results showed that both Saudi and American students identified interaction and collaborative learning as the most valuable support structures. Keywords: motivation, anxiety, academic performance, online collaborative learning, support structures, Saudi students, American students19 0Item Restricted The Influence of Artificial Intelligence on EAP Learners’ Oral Fluency(Saudi Digital Library, 2026) Alwadaeen, Norah Bakheet; Abbuhl, RebekhaThere is ongoing debate on how AI speaking tools can support the development of oral fluency in second language (L2) instruction. Despite the widespread usage of these tools, such as AI chatbots and Automated Speech Recognition (ASR), questions persist about how well they will work to improve oral fluency, reduce speaking anxiety, and foster learner autonomy. This study investigates how an AI-mediated speaking partner influences English for Academic Purposes (EAP) learners’ oral fluency, speaking anxiety, and autonomy over a short, intensive practice cycle. Five upper-intermediate ESL students at a California community college completed nine EAP Talk chatbot sessions across 3 weeks, framed by pre- and post-intervention IELTS-style monologic speaking tasks. Acoustic analyses of the pre/post tasks in PRAAT targeted three utterance-fluency indices (speaking ratio, repair phenomena, and pause placement). Session-by-session Likert questionnaires captured perceived fluency gains, anxiety, and autonomy, and post-intervention semi-structured interviews explored learners’ experiences with the AI-mediated practice. Oral fluency findings indicated that the speaking ratio increased, whereas pause and repair indices generally shifted in favorable directions. Anxiety, which was scaled so higher scores indicated less anxiety, exhibited clear gains. Autonomy trajectories were positive at the group level. Furthermore, the study highlights both the promise and limitations of AI chatbots for EAP speaking. It emphasizes the value of multi-indicator fluency assessment, explicit autonomy supports, and longer comparative designs in future work.22 0Item Restricted Resilience enhancement of post-disaster power distribution systems using Deep Reinforcement Learning(Saudi Digital Library, 2026) Alotaibi, Raed; Zohdy, Mohamed; Kaur, Amanpreet; Alghamdi, Ali; Edwards, William; Al-Salman, ZeinaWeather-driven extreme events are placing growing stress on aging distribution infrastructure and increasingly threaten continuity of service for critical loads during prolonged outages. Microgrids can enhance resilience by transitioning to islanded operations and supplying prioritized loads with local distributed energy resources (DERs); however, post-disaster restoration remains challenging because operators must make coupled discrete–continuous decisions under tight resource and operating constraints. This dissertation addressed this challenge by developing a parameterized deep reinforcement learning controller, PDQN-CLR, that targets priority-weighted restoration while enforcing operational feasibility under scarcity. The PDQN-CLR modeled restoration as a hybrid action in which a discrete operational category was selected and paired with a continuous parameter vector specifying the DER real and reactive power setpoints. The approach was evaluated in a closed-loop OpenDSS environment using the IEEE 123-node feeder configured as an islanded microgrid with five grid-forming battery energy storage systems and 17 prioritized critical loads over a 72-step (36-hour) horizon with a 30-minute decision interval. Snapshot power-flow evaluation was performed at each step. Uncertainty was represented through capacity-factor derating under sufficient and scarce regimes, and each episode randomized the fault scenario, derating level, and initial state of charge. This dissertation also introduced (i) an uncertainty-aware evaluation protocol based on capacity-factor derating; (ii) a three-tier priority-weighted reward to encode the critical-load hierarchy; and (iii) a DER-aware load service rule that reduced voltage-only overstatement in islanded operation. With sufficient resources, PDQN-CLR achieved a mean PCS of 0.94 versus 0.80 for a Greedy baseline, while maintaining a low constraint violation score (CVS) of approximately 0.009 in both sufficient and scarce regimes. The baseline produced substantially larger violation magnitudes (CVS ≈ 0.388–0.667), indicating more severe and/or more frequent exceedances of the constraints. These results indicate that parameterized deep reinforcement learning can improve priority-weighted restoration when capacity is available and preserve feasibility as a primary outcome when scarcity limits achievable restoration.20 0Item Restricted EXAMINING READING-RELATED TEACHER EDUCATION AMONG GENERAL EDUCATION TEACHERS OF PRIMARY SCHOOL STUDENTS WITH LEARNING DISABILITIES IN TAIF, SAUDI ARABIA(Saudi Digital Library, 2026) Alqrashi, Ahmad; Hosp, JohnThe education system of Saudi Arabia has made significant advances in expanding access to its general education through policies of inclusion, particularly through initiatives aligned with Vision 2030. In spite of these advances, the system still lacks an effective support structure for students with learning disabilities (LD) in general education classrooms, especially at the primary school level. Research on inclusive education indicates that teachers’ preparedness, encompassing their knowledge of evidence-based reading strategies, awareness of students’ needs, and capacity to implement appropriate strategies, directly enhances the academic outcomes of students with LD. In this study, the researcher investigated three central questions: 1. What professional development in reading do Saudi general education teachers of students with LD in primary schools report having undertaken? 2.) To what extent do Saudi general education teachers' university training and professional development in reading instruction relate to their implementation of evidence-based practices for students with LD in inclusive primary classrooms? and 3.) What are the perceptions of Saudi general education teachers toward evidence-based reading instruction for students with LD? To address these questions, a mixed-methods approach was employed, including a survey of 98 general education teachers in Taif and semi-structured interviews with six teachers from the same region. Quantitative analysis indicated that teachers received significantly more training in general reading than in LD-specific instruction, and that formal training did not predict the use of evidence-based strategies. Qualitative findings revealed that while teachers held positive perceptions of evidence-based reading strategies, structural barriers such as large class sizes, limited instructional time, and insufficient collaboration with special education professionals severely constrained implementation. The study concludes that there are both knowledge and application gaps between the Saudi inclusive education policy and classroom practice. To realise the goals of Vision 2030, urgent reforms are needed in teacher preparation, mandatory professional development, and classroom resource allocation.25 0Item Embargo Optimizing Aerosol Therapy During Noninvasive Ventilation in Pediatric Patients: A Narrative Review(Saudi Digital Library, 2025) AlKhiry, Ali; Goodfellow, Lynda TTitle: Optimizing Aerosol Therapy During Noninvasive Ventilation in Pediatric Patients: A Narrative Review Background: Noninvasive ventilation (NIV) is widely used in pediatric respiratory care, often in conjunction with aerosolized medications. However, the effectiveness of aerosol delivery in children remains uncertain due to anatomical, physiological, and behavioral complexities unique to this population. Objective: To systematically evaluate the influence of interface type, circuit configuration, and nebulizer placement on the effectiveness of aerosol therapy in pediatric patients receiving NIV. Methods: A comprehensive literature search was conducted in PubMed, Embase, and CINAHL using standardized indexing terms. A total of 328 records were screened, with 11 studies meeting inclusion criteria for qualitative synthesis. Studies were selected based on relevance to pediatric populations using NIV and reporting measurable clinical outcomes such as lung deposition, symptom improvement, adverse events, and hospital length of stay. Results: Oronasal masks were found to yield significantly higher pulmonary drug deposition (up to 30%) compared to nasal cannulas (1–6%). Dual-limb ventilator circuits outperformed single-limb setups in minimizing aerosol loss. Optimal nebulizer placement between the exhalation valve and patient was critical for maximizing drug delivery. Clinical outcomes associated with optimized aerosol therapy included reduced respiratory distress, shortened duration of respiratory support, lower intubation rates, and decreased hospital stays. Adverse events were rare but included skin and eye irritation when masks were poorly fitted. Conclusion: The effectiveness of aerosol therapy during pediatric NIV is closely linked to the selection of interface, ventilator circuit design, and nebulizer positioning. Evidence consistently supports the use of oronasal masks and dual-limb circuits, when tolerated by the patient, as these configurations maximize pulmonary drug deposition and clinical efficacy. Proper placement of the nebulizer, ideally between the exhalation valve and the patient, further enhances drug delivery. These adjustments not only improve therapeutic outcomes such as reduced respiratory distress and shorter hospital stays but also minimize the need for invasive ventilation and associated complications. Importantly, optimizing aerosol therapy in this context demands a patient-centered approach that balances drug delivery efficiency with comfort and tolerance. These findings offer a practical and evidence-based framework for clinicians seeking to refine aerosol administration strategies in pediatric NIV, ultimately contributing to safer, more effective, and personalized respiratory care. Keywords: Pediatric, NIV, aerosol delivery, nebulizer interface, lung deposition, respiratory therapy, noninvasive ventilation35 0Item Restricted USING MACHINE LEARNING TO PREDICT OPTICAL PROPERTIES OF MOLECULES(Saudi Digital Library, 2026) Alotaibi, Maha; Clayborne, AndreUnderstanding and predicting optical properties at the molecular scale is essential for the development of functional materials in fields such as photovoltaics, sensing, and molecular electronics. Several approaches have been developed to model these properties, ranging from traditional quantum mechanical simulations to emerging datadriven techniques. Traditional quantum chemical methods, such as time-dependent density functional theory (TD-DFT), are known for their high computational demands. This dissertation focuses on using machine learning (ML) to predict optical spectra for molecular systems and potentially reduce the computational cost for calculations. Two sets of molecules were used as testbeds for the machine learning workflow: 1) Organic Molecules from the QM8 database and 2) Metalloporphyrins. Initially, a dataset of small organic molecules was used to train and evaluate machine learning models for the prediction of UV-Vis profile. Two regression algorithms, Kernel Ridge Regression (KRR) and Random Forest (RF), were applied using molecular descriptors generated xv with RDKit. These models were trained and validated on optical property data obtained from quantum chemical calculations using TD-DFT. To further validate the ML models, additional DFT-data was collected for metalloporphyrins. This included information about the geometry, electronic properties, and optical spectra of metalloporphyrins that included first and second row transition metals with varying anchoring groups. The relatively small dataset for the optical properties of metalloporphyrins introduced challenges to the ML model. This research highlights importance of structure and composition on optical properties and how machine learning can provide insight into the optical properties and ultimately molecular design principles for specific applications.5 0Item Restricted Essays on Audit Committee Chair Characteristics, Cybersecurity Risk Disclosure, and ESG Disclosure Scores(Saudi Digital Library, 2025) Alanazi, Musharraf; Thiruvadi, SheelaIn recent years, environmental, social, and governance (ESG) considerations have shifted from peripheral concerns to central pillars of corporate governance and reporting. Growing attention to climate risks, sustainability practices, and corporate responsibility has led regulators, investors, and civil society to demand high-quality and comparable ESG information. Audit committees are emerging as key players in this process because their oversight of financial reporting, risk management, and internal controls increasingly intersects with ESG responsibilities. This role has been reinforced by evolving regulatory frameworks such as the EU Corporate Sustainability Reporting Directive and the SEC's climate and cybersecurity disclosure rules. However, despite the rising importance of disclosure, limited evidence exists on how the personal and professional traits of audit committee chairs influence transparency in ESG and cybersecurity reporting. The first essay examines the relationship between audit committee chair characteristics, namely, gender, age, CPA qualification, and prior auditor experience, and ESG disclosure scores, utilizing panel data from S&P 500 firms between 2015 and 2023. Results from ordinary least squares (OLS) regressions show that female chairs are strongly associated with higher ESG disclosure scores, particularly in environmental and social dimensions, while chair age is negatively related to ESG outcomes. CPA credentials have no consistent effect, and prior auditor experience is modestly associated with the level of governance disclosure. Interaction results reveal that younger female chairs drive the strongest ESG disclosure score and that combining gender diversity with prior audit experience further enhances transparency. The second essay examines cybersecurity risk disclosure, employing logistic regression on the same dataset. Findings indicate that demographic traits such as gender, age, and CPA credentials are not significant predictors, while prior auditor experience improves disclosure quality, highlighting the value of technical expertise in addressing IT risks. Firm-level factors also matter: profitability (ROA) is negatively associated with disclosure, while larger firms are more likely to report, reflecting heightened regulatory and investor pressures. This study makes significant contributions to the accounting, auditing, and sustainability literature in several ways. First, it fills an important gap, as no prior research has jointly examined how audit committee chair characteristics influence both ESG disclosure score and cybersecurity risk disclosure. Second, the findings provide new evidence that demographic and professional traits, such as gender, age, and prior audit experience, affect disclosure outcomes, with notable effects on ESG transparency. Third, the study applies Upper Echelons Theory to explain how leadership diversity and experience shape ESG reporting, while highlighting the role of evolving regulatory frameworks in driving cybersecurity disclosure. Together, these insights offer practical implications for boards, regulators, policymakers, and investors seeking to strengthen corporate transparency and accountability. Keywords: Corporate Governance; Audit Committee Chair; ESG disclosure score; Cybersecurity Risk Disclosure; Gender Diversity; CPA Qualification; Prior Auditor Experience33 0