Saudi Cultural Missions Theses & Dissertations
Permanent URI for this communityhttps://drepo.sdl.edu.sa/handle/20.500.14154/10
Browse
41 results
Search Results
Item Restricted Intelligent Diabetes Screening with Advanced Analytics(University of Birmingham, 2024) Aldossary, Soha; Smith, PhillipDiabetes mellitus is a prevalent chronic disease with significant health implications worldwide. This project aimed to mitigate this pressing public health concern by using machine learning techniques and deep learning algorithms. I also established an online platform at which patients can enter their test results and health information and receive real-time diabetes detection and dietary recommendations based on their health profiles. Research has illustrated that models such as Gradient Boosting, Random Forest and Decision Trees perform well in diabetes prediction due to their ability to capture complex nonlinear relationships and handle diverse input features. Therefore, this project incorporated these models with others, such as the Support Vector Classifier and AdaBoost. Additionally, deep learning models, including Neural Networks, were utilised to explore intricate relationships within diabetes-related indicators. Notably, the Gradient Boosting model achieved an impressive accuracy of 99%, with 99% precision, 97% recall and 97% F1-score. To implement these solutions, I used Python as the programming language, employing libraries such as scikit-learn, NumPy, Pandas and Matplotlib, while Streamlit served as the app’s framework.12 0Item Restricted Automating the Resolutions for Software Merge Conflicts(Virginia Polytechnic Institute and State University, 2024-11-22) Aldndni, Waad; Meng, Na; Servant, FranciscoDuring collaborative software development, developers engage in parallel work on separate branches, which are eventually merged at regular intervals. However, conflicts can arise when edits from different branches overlap in the text. Resolving such conflicts involves three strategies: keeping the local version only (KL), keeping the remote version only (KR), or manually editing them (ME). Nonetheless, manually resolving merge conflicts can be a laborious and error-prone process. Thus, researchers proposed tools to aid in conflict resolution by combining edits from both branches as many as possible, although these tools often fail to consider the preferences of the developers involved adequately. Recent studies show that developers predominantly resolve textual conflicts via KL or KR. This suggests that existing tools do not fully consider the resolution preferences of developers but only focus on the technical feasibility of merging branch edits. Our research focuses on predicting developers’ resolutions automatically for software merge conflicts and suggesting resolution edits to developers. We designed and implemented three tools to automatically predict resolution strategies for merge conflicts and to automatically apply some of the strategies by producing merged versions. The tool evaluation shows promising results. Our research will help developers resolve conflicts effectively and efficiently; it will also shed light on future research for software merge and automatic conflict resolution.21 0Item Restricted Behavior and Design of Composite Rebars Interfaced with Concrete(university of colorado Denver, 2024) Alatify, Ali; Kim, JimmyAbstract This dissertation studies different aspects of the interfacial behavior of composite reinforcement embedded in concrete. GFRP rebars are known for its none-corrosiveness, light weight, and high strength compared to conventional steel rebars, and became predominantly employed in different structural applications such as bridge construction. Thus, the serviceability and interfacial behavior of GFRP bars in different structural applications is investigated in four phases in this research. Chapter three presents an experimental study on the residual bond of glass fiber reinforced polymer (GFRP) rebars embedded in ultra-high performance concrete (UHPC) subjected to elevated temperatures, including a comparison with ordinary concrete. Based on the range of thermal loading from 25oC (77oF) to 300oC (572oF), material and push-out tests are conducted to examine the temperature-dependent properties of the constituents and the behavior of the interface. Also performed are chemical and radiometric analyses. The average specific heat and thermal conductivity of UHPC are 12.1% and 6.1% higher than those of the ordinary concrete, respectively. The temperature-induced reduction of density in these mixtures ranges between 5.4% and 6.2% at 300oC (572oF). Thermal damage to GFRP, in the context of microcracking, is observed after exposure to 150°C (302°F). Fourier transform infrared spectroscopy reveals prominent wavenumbers at 668 cm-1 (263 in.-1) and 2,360 cm-1 (929 in.-1), related to the bond between the fibers and resin in the rebars, while spectroradiometry characterizes the thermal degradation of GFRP through diminished reflectivity in conjunction with the peak wavelength positions of 584 nm (2,299×10-8 in.) and 1,871 nm (7,366×10-8 in.). The linearly ascending bond-slip response of the interface alters after reaching the maximum shear stresses, leading to gradual and abrupt declines for the ordinary concrete and UHPC, respectively. The failure mode of the ordinary concrete interface is temperature-sensitive; however, spalling in the bonded region is consistently noticed in the UHPC interface. The fracture energy of the interface with UHPC exceeds that of the interface with the ordinary concrete beyond 150oC (302oF). Design recommendations are provided for estimating reductions in the residual bond of the GFRP system exposed to elevated temperatures. The interface shear between ordinary concrete and ultra-high-performance concrete (UHPC) connected with glass fiber reinforced polymer (GFRP) rebars is presented in chapter four. Following ancillary tests on the fracture of the rebars under in-plane shear loading, concrete-rebar assemblies are loaded to examine capacities and failure modes that are dependent upon the size, spacing, and number of the rebars. While the transition of load-resisting axes in the glass fibers and their quantity dominates the shear behavior of the bare rebars, the size and spacing of the reinforcement control the capacities of the interface by altering load-transfer mechanisms from the rebar to the concrete. The degree of stress distribution affects the load-displacement response of the interface, which is characterized in terms of quasi-steady, kinetic, and failure regions. The primary failure modes of the interface comprise rebar rupture and concrete splitting. The formation of cracks between ordinary concrete and UHPC results from interfacial deformations, leading to spalling damage when applied loads exceed service levels. An analytical model is formulated alongside an optimization technique. The capacities of the interface in relation to the rebar rupture and concrete splitting failure modes are predicted. Furthermore, a machine learning algorithm is utilized to define a failure envelope and propose practice guidelines through parametric investigations. The serviceability of concrete beams with continuous and spliced glass fiber reinforced polymer (GFRP) rebars is investigated and detailed in chapter five. An experimental program is undertaken using 18 beams incorporating various reinforcing schemes to examine the effects of rebar distribution and spacing on flexural and cracking responses. The cracking load of the beams with the continuous rebars (Category C) is 24.2% higher than that of the beams with the spliced rebars (Category S) experiencing stress concentrations. The distributed configuration of the rebars enhances interactions between the concrete and reinforcement, thereby increasing bond transfer in the beams. Contrary to the linear load-displacement behavior of the C-category beams after cracking, parabolic trends are observed in the S-category beams owing to the slip of the spliced rebars, which degrades composite action at the rebar-concrete interface and reduces the flexural rigidity of the beams. The crack opening of the C-category beams under service loading is within the tolerable limits of published guidelines, whereas the opening of the S-category beams exceeds the limits. Through statistical characterization, the significance of the rebar distribution in crack opening and depth is demonstrated at a 5% significance level (95% confidence interval). Design recommendations include a slip multiplier of 0.63 for calculating the stress of spliced GFRP rebars and a bond coefficient of 0.88 for determining the flexural capacity of beams with this type of reinforcement. The implications of variable bond for the behavior of concrete beams with glass fiber reinforced polymer (GFRP) bars alongside shear-span-dependent load-bearing mechanisms is evaluated in chapter six. Experimental programs are undertaken to examine element- and structural-level responses incorporating fully and partially bonded rebars, which are intended to represent sequential bond damage. Conforming to published literature, three shear-span-to-depth (av/d) ratios are considered: arch action (av/d < 2.0), beam action (3.5 ≤ av/d), and a transition from arch to beam actions (2.0 ≤ av/d < 3.5). When sufficient bond is provided for the element-level testing (over 75% of 5db, where db is the rebar diameter), the interfacial failure of GFRP is brittle against a concrete substrate. An increase in the shear-span-to-depth ratio, aligning with a change from arch action to beam action, decreases the load-carrying capacity of the beams and the slippage of the partially bonded rebars dominates their flexural stiffness. Compared with the case of beams under beam action, the mutual dependency of the bond length and shear span is apparent for those under arch action. As far as failure characteristics are concerned, the absence of bond in the arch-action beam prompts crack localization; by contrast, partially bonded ones demonstrate diagonal tension cracking adjacent to the compression strut that transmits applied load to the nearby support. The developmental process of rebar stress is dependent upon the shear-span-to-depth ratios and, in terms of utilizing the strength of GFRP, beam action is favorable relative to arch action. Analytical modeling suggests design recommendations, including degradation factors for the calculation of rebar stresses with bond damage when subjected to arch and beam actions.28 0Item Restricted Developing a medical robot for MR guided cardiac catheterization(university college london, 2024) Almutairi, Abdullah; Muthurangu, VivekCardiac catheterization involves the insertion of a needle into the veins, enabling physicians to obtain images of the heart without invasive surgery. This procedure, therefore, plays a key role in the diagnosis and treatment of various heart diseases. In recent years, there has been widespread adoption of robotics in surgical procedures, whereby some of the benefits include efficiency, a faster operational speed, and a high rate of action reproducibility. The primary objective of this study was to evaluate the application of behavioural cloning in training robotic systems to perform robotic magnetic resonance–guided catheterization on 3D-printed heart models. Six 3D heart models were printed, and the time taken to perform the catheterization process was measured. The data collection process consisted of manual catheterization, catheterization using a joystick, and simulations of both processes. The results indicated that the manual catheterization process was faster than the robotic one. Nevertheless, the success of the robotic-assisted simulation indicates that it is possible to use behavioural cloning to train the robotic systems to perform catheterization. This study demonstrates that behavioural cloning can be effectively adopted in the catheterization process, whereby learning models can be developed for conducting catheterization procedures.16 0Item Restricted Synergising Learning Sciences, Learning Analytics, and Educational Technologies(The University of Queensland, 2024) Lahza, Hatim; Khosravi, Hassan; Demartini, GianlucaThe adoption of educational technologies in modern educational systems has significantly advanced the field of learning sciences. This shift, particularly evident within digital learning environments, has enriched pedagogical strategies and redefined educational evaluation methodologies by leveraging sophisticated developments in learning analytics. Despite these advancements, a notable gap persists in effectively applying learning theories within digital environments and in the design of learning analytics. This shortfall partly stems from the ongoing development of empirical evidence supporting these theories and a prevalent reliance on software engineering and data science perspectives, which may not fully integrate learning theory insights. To this end, this thesis addresses this gap by proposing two triadic relationships among learning theories, educational technologies, and learning analytics. The overarching aim is to leverage these relationships to enhance learning understanding and learning optimisation. First, I leverage the dyadic relationship between learning theory and educational technologies to influence the development of the third actor of the triad, learning analytics, to enhance learning understanding. I demonstrate the application of this relationship through two approaches using two authentic educational platforms with real-life course data. The first approach, LA-exam, uses an e-exam platform and Self-Regulated Learning (SRL) theory to develop analytics for e-exams on two levels: student level and item level. The second approach, LA-sourcing, uses a learnersourcing platform and SRL theory to develop analytics about student tactics and strategies when engaging with the platform activities. Second, I leverage the dyadic relationship between learning theory and learning analytics to inform the design choices of the third actor of the triad, educational technologies, to enhance learning optimisation. I demonstrate the application of this relationship through two approaches that report the results of randomised controlled experiments conducted on a learnersourcing platform. The first approach, ET-create, uses a set of learning analytics and SRL theory to inform the design choices of SRL scaffolding strategies for content creation. The second approach, ET- review, uses a set of learning analytics and SRL and scripting theories to inform the design choices of scaffolding strategies for peer review.11 0Item Embargo ENHANCING LOCATION INFORMATION PRIVACY AND SECURITY IN IoBT USING DECEPTION-BASED TECHNIQUES(Florida Atlantic Uniiversity, 2024-09) Alkanjr, Basmh; Imadeldin, MahgoubIoBT stands for the Internet of Battlefield Things. This concept extends the principles of the Internet of Things (IoT) for military and defense use. IoBT integrates smart devices, sensors, and technology on the battlefield to improve situational awareness, communication, and decision-making in military operations. Sensitive military data typically includes information crucial to national security, such as the location of soldiers and equipment. Unauthorized access to location data may compromise operational confidentiality and impede the element of surprise in military operations. Therefore, ensuring the security of location data is crucial for the success and efficiency of military operations. We propose two systems to address this issue. First, we propose a novel deception-based scheme to enhance the location-information security of IoBT nodes. The proposed scheme uses a novel encryption method, dummy IDs, and dummy packets technology. We develop a mathematical model to evaluate our scheme in terms of safety time (ST), probability of failure (PF), and the probability of identifying the real packet in each location information update (PIRP). Then, we develop NetLogo simulations to validate the mathematical model. The proposed scheme increases ST, reduces PF and PIRP. We develop a scheme to protect the node's identity using dummy ID, silence period, and sensitive area’s location privacy enhancement concepts. We generate a pseudonym location for each node in the IoBT environment to protect the node's real location information. We propose a new metric called the average probability of linkability per dummy ID (DID) change to assess the attacker's effectiveness in linking the source node with its new DID following the silent period. We develop Matlab simulations to evaluate our scheme in terms of average anonymity and average probability of linkability per DID change. The results showed further privacy enhancement by applying the sensitive area concept. Tampering with location information, such as falsification attacks, can lead to inaccurate battlefield assessments and personnel safety risks. Thus, we design ANFIS and ensemble methods for detecting position falsification attacks in IoBT. Using the VeReMi dataset, our method achieved high detection accuracy while reducing false negative rate and computation complexity. Cross-validation further supports the reliability of our model.29 0Item Restricted Exploring Ridgeless Regression in High-Dimensional Data: A Numerical Investigation into Predictive Accuracy(University of Nottingham, 2024) Alderaan, Saad; Preston, SimonThe rise of high-dimensional datasets, where the number of predictors p exceeds the number of observations n, comes with significant challenges for linear models with the Ordinary Least Squares (OLS) method. This report investigates the application of ridgeless regression, an OLS method with a minimum-norm solution, in such high-dimensional settings, particularly when p ≫ n. The minimum-norm OLS is compared against ridge regression in terms of predictive accuracy in high-dimensional settings. Using simulation studies on the spiked covariance model, this report shows that the minimum-norm OLS can outperform ridge regression under certain high-dimensional datasets where p ≫ n, contradicting the traditional assumptions that regularization techniques are necessary in high-dimensional settings. Moreover, this report shows that the optimal regularization parameter λ in ridge regression can be negative in such cases, challenging the conventional belief that the regularization parameter λ is always positive. This is due to the inherent structure of the data, which may provide sufficient implicit regularization, making additional penalization unnecessary or even counterproductive. The implications of these findings extend to practical applications in fields such as genomics and finance, where high-dimensional data is common. The conclusions drawn from this work highlight the potential of ridgeless regression as a viable alternative to ridge regression in high-dimensional data, especially when traditional methods encounter issues like overfitting. The report contributes to the ongoing discussion in statistical machine learning by providing new insights into when and why ridgeless regression may be preferred.7 0Item Restricted Detecting Makeup Activities using Internet-of-Things(University of Maryland Baltimore County, 2019-07) Alqurmti, Fatimah; Roy, NirmalyaThis thesis focuses on identifying human activities for rendering make-up activities using sensors’ data and a supervised machine learning approaches. We considered five make-up activities in our work, such as, applying cream, lipsticks, blusher, eyeshadow, and mascara. We collected the data from ten participants using two smart-watch built-in sensors, accelerometer and gyroscope. We preprocessed the data and trained with different predictive machine learning models and we evaluated make-up activity prediction built on using Naïve Bayes, Simple Logistic, k-nearest neighbors’, and the random forest algorithms. We investigated the models' performance on three different datasets that differ by the environment they were collected in. The first dataset was collected from the participants using a controlled environment. In this staged setting, we provided the participants specific instructions on how to perform the five make-up activities. The second dataset was collected from the participants in an uncontrolled environment. We did not inform the participants with any prior instructions on how to perform the five activities and therefore, naturally they performed the make-up activities in their own way. Third, we synthetically generated a dataset by combining the existing datasets from the participants who were under both controlled and uncontrolled environments. Our results showed a 92.7 % accuracy for the controlled environment case given by the Gradient Boosting classifier and an 89.20 % accuracy for the uncontrolled environment case shown by the Random Forest classifier. Finally, Random Forest classifier registered the highest accuracy 92%, for the hybrid case where both the datasets from controlled and the uncontrolled environments were combined. We believe that this early work on recognizing and discovering a multitude of make-up activities has potential application in assessing and training the performance of various stakeholders in the future work of fashion industry.7 0Item Restricted Early Prediction of Cancer Using Supervised Machine Learning: A Study of Electronic Health Records From The Ministry of National Gurad Health Affairs(University College London (UCL), 2024-08) Alfayez, Asma; Lai, Alvina; Kunz, HolgerEarly detection and treatment of cancer can save lives; however, identifying those most at risk of developing cancer remains challenging. Electronic health records (EHR) provide a rich source of "big" data on large patient numbers. I hypothesised that in the period preceding a definitive cancer diagnosis, there exist healthcare events, such as a history of disease, captured within EHR data that characterise cancer progression and can be exploited to predict future cancer occurrence. Using longitudinal phenotype data from the EHR of the Ministry of National Guard Health Affairs, a large healthcare provider in Saudi Arabia, I aimed to discover health event patterns present in EHR data that predict cancer development in periods prior to diagnosis by developing predictive models using supervised machine learning (ML) algorithms. I used two different prediction periods: six months and one year prior to cancer diagnosis. Initially, the thesis focused on the prediction of both malignant and benign neoplasms, before moving on to predicting the future risk of malignant neoplasms (cancer), since predicting life-threatening illness remains the most important clinical challenge. To refine the approach for specific cancer types, predictive models were built for the top three malignancies in this population: breast, colon, and thyroid cancers. ML predictive models were developed using the following algorithms: (1) logistic regression; (2) penalised logistic regression; (3) decision trees; (4) random forests; (5) gradient boosting; (6) extreme gradient boosting; (7) k-nearest neighbours; and (8) support vector machine. Model performance was assessed using k-fold cross-validation and area under the curve—receiver operating characteristics (AUC-ROC). After developing different models, their performance was compared with and without hyperparameter tuning using tree-based pipeline optimization (TPOT) and GridSearch. This study provides novel proof-of-principle that ML algorithms can be applied to EHR data to develop models that can be used to predict future cancer occurrence.26 0Item Restricted Evaluating CAMeL-BERT for Sentiment Analysis of Customer Satisfaction with STC (Saudi Telecom Company) Services(The University of Sussex, 2024-08-15) Alotaibi, Fahad; Pay, JackIn the age of informatics platforms such as Twitter (X) plays a crucial role for measuring public sentiment, especially in both private and public sectors. This study explores the application of machine learning, particularly deep learning, to perform sentiment analysis on tweets about Saudi Telecom Company (STC) services in Saudi Arabia. A comparative analysis was conducted between pre-trained sentiment analysis models in English and in Arabic to assess their effectiveness in classifying sentiments. In addition, the study highlights a challenge in existing Arabic models, which are based on English model architectures but trained on varied datasets, such as Modern Standard Arabic and Classical Arabic (Al-Fus’ha). These models often lack the capability to handle the diverse Arabic dialects commonly used on social media. To overcome this issue, the study involved fine-tuning a pre-trained Arabic model using a dataset of tweets related to STC services, specifically focusing on the Saudi dialect. Data was collected from Twitter (X), focusing on mentions of the Saudi Telecom Company (STC). Both English and Arabic models were applied to this data, and their performance in sentiment analysis was evaluated. The fine-tuned Arabic model (CAMeL-BERT) demonstrated improved accuracy and a better understanding of local dialects compared to its initial version. The results highlight the importance of model adaptation for specific languages and contexts and underline the potential of CAMeL-BERT in sentiment analysis for Arabic-language content. The findings offer practical implications for enhancing customer service and engagement through more accurate sentiment analysis of social media content in the service providers sector.15 0