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 MULTIDIMENSIONAL APPROACHES IN BUG DETECTION FOR PARALLEL PROGRAMMING AND TEXT-TO-CODE SEMANTIC PARSING(University of Central Florida, 2025) Alsofyani, May; Wang LiqiangThis dissertation applies deep learning and large language models to two domains: parallel programming fault detection and text-to-code translation, aiming to enhance software reliability and natural language-driven code generation. Due to their unpredictable nature, concurrency bugs-particularly data race bugs— present significant challenges in fault detection for parallel programming. We investigate deep learning and LLM-based approaches for detecting data race bugs in OpenMP programs. Our proposed methods include a transformer encoder and GPT-4 through prompt engineering and fine-tuning. Experimental results demonstrate that the transformer encoder achieves competitive accuracy compared to LLMs, highlighting its effectiveness in understanding complex OpenMP directives. Expanding this research, we explore the role of LLMs in detecting faults in Pthreads, which requires a deep understanding of thread-based logic and synchronization mechanisms. We analyze ChatGPT's effectiveness in Pthreads fault detection through dialogue-based interactions and advanced prompt engineering techniques, including Zero-Shot, Few-Shot, Chain-of-Thought, and Retrieval-Augmented Generation. Additionally, we introduce three hybrid prompting techniques—Chain-of-Thought with Few-Shot Prompting, Retrieval-Augmented Generation with Few-Shot Prompting, and Prompt Chaining with Few-Shot Prompting—to enhance fault detection performance. In the semantic parsing domain, our research bridges the gap between natural language and executable code, focusing on text-to-SQL translation. To address SQL's limitations in statistical analysis, we introduce SIGMA, a dataset for text-to-code semantic parsing with statistical analysis capabilities. In addition, we address the gap in cross-domain context-dependent text-to-SQL translation for the Arabic language. While prior research has focused on English and Chinese datasets, no efforts have been made to explore Arabic cross-domain conversational querying. We introduce Ar-SParC, the first Arabic cross-domain, context-dependent text-to-SQL dataset. This dissertation contributes to fault detection in parallel programming and semantic parsing with statistical analysis, leveraging cutting-edge deep learning and LLMs techniques. Our findings advance bug detection in high-performance computing and natural language-based code generation, significantly improving software reliability and accessibility.30 0Item Restricted Human Action Recognition Based on Convolutional Neural Networks and Vision Transformers(University of Southampton, 2025-05) Alomar, Khaled Abdulaziz; Xiaohao, CaiThis thesis explores the impact of deep learning on human action recognition (HAR), addressing challenges in feature extraction and model optimization through three interconnected studies. The second chapter surveys data augmentation techniques in classification and segmentation, emphasizing their role in improving HAR by mitigating dataset limitations and class imbalance. The third chapter introduces TransNet, a transfer learning-based model, and its enhanced version, TransNet+, which utilizes autoencoders for improved feature extraction, demonstrating superior performance over existing models. The fourth chapter reviews CNNs, RNNs, and Vision Transformers, proposing a novel CNN-ViT hybrid model and comparing its effectiveness against state-of-the-art HAR methods, while also discussing future research directions.23 0Item Restricted ADAPTIVE SELF-LEARNING AND MULTI-STAGE MODELING FOR EFFICIENT MEDICAL AND DENTAL IMAGE SEGMENTATION(University of Missouir - Kansas City, 2025) Alqarni, Saeed; Yugyung, LeeMedical imaging has revolutionized healthcare by enabling non-invasive visualization of anatomical structures and pathologies, significantly improving diagnostic accuracy, treatment planning, and patient monitoring. Modalities like computed tomography (CT), magnetic resonance imaging (MRI), and ultrasound provide critical insights into the human body, yet precise medical image segmentation remains a challenging task. This difficulty arises from factors such as image variability, noise, artifacts, and the limited availability of annotated data necessary to train robust segmentation models. Overcoming these hurdles is essential to unlock the full potential of medical imaging in diverse clinical applications. This dissertation presents a novel framework for efficient and accurate medical image segmentation, incorporating multi-stage transfer learning, uncertainty-driven data selection, and weakly supervised learning. By combining human-guided refinement with adaptive data selection, this research addresses fundamental barriers such as data scarcity, computational resource limitations, and the high cost of annotation. The framework is structured around three key objectives: 1. Adaptive Uncertainty Sampling with SAM (AUSAM), which introduces a flexible, real-time data selection and segmentation approach, reducing reliance on large annotated datasets through dynamic thresholds and DBSCAN clustering. 2. AUSAM-SL - Active Self-Learning with SAM, which integrates entropy-based active learning with iterative self-labeling, supported by SAM for initial training, refining the selection criteria, and enhancing model predictions. 3. AUSAM-3D- 3D Modeling for Domain-Aware Segmentation and Aggregation, which builds upon AUSAM by incorporating a spatial and volumetric dimension, improving segmentation accuracy for organs and tumors, and enabling more clinically relevant outcomes. Preliminary results on medical and dental imaging datasets (MRI, CT, X-ray) validate the effectiveness of the proposed framework in improving segmentation accuracy while maintaining computational efficiency. The research offers scalable solutions suitable for resource-constrained environments by integrating human feedback with semisupervised and weakly supervised learning techniques. This work advances the field of medical and dental image segmentation and provides practical methods for leveraging multi-stage learning in real-world applications where data and computational resources are limited.20 0Item Restricted Rasm: Arabic Handwritten Character Recognition: A Data Quality Approach(University of Essex, 2024) Alghamdi, Tawfeeq; Doctor, FaiyazThe problem of AHCR is a challenging one due to the complexities of the Arabic script, and the variability in handwriting (especially for children). In this context, we present ‘Rasm’, a data quality approach that can significantly improve the result of AHCR problem, through a combination of preprocessing, augmentation, and filtering techniques. We use the Hijja dataset, which consists of samples from children from age 7 to age 12, and by applying advanced preprocessing steps and label-specific targeted augmentation, we achieve a significant improvement of a CNN performance from 85% to 96%. The key contribution of this work is to shed light on the importance of data quality for handwriting recognition. Despite the recent advances in deep learning, our result reveals the critical role of data quality in this task. The data-centric approach proposed in this work can be useful for other recognition tasks, and other languages in the future. We believe that this work has an important implication on improving AHCR systems for an educational context, where the variability in handwriting is high. Future work can extend the proposed techniques to other scripts and recognition tasks, to further improve the optical character recognition field.50 0Item Restricted Enhance Deep Learning for Cybersecurity Challenges in Software-Defined Networks(University of Warwick, 2024-09) Alsaadi, Sami; Leeson, Mark and Lakshminarayana, SubhashTraditional network devices, such as a router or switch, incorporate the control plane and the data plane. IT operators independently set traffic policies on each device. Nonetheless, this architectural setup raises operational expenses and complicates the dynamic adaptation and maintenance of secure network configurations. Software-defined Networking (SDN) represents a revolutionary approach to network management, offering enhanced flexibility. SDN promotes rapid innovation in networking by centralizing control and making it programmable. However, security concerns pose significant barriers to the broader adoption of SDN, as this new architecture potentially opens novel attack vectors previously non-existent or more challenging to exploit. Machine Learning (ML) strategies for SDN security rely heavily on feature engineering, requiring expert knowledge and causing delays. Therefore, enhancing intrusion detection is essential for protecting SDN architectures against diverse threats. The thesis develops techniques for detecting malicious activities in SDN using Deep Learning DL. It starts by evaluating CNNs on an SDN dataset, leading to a new CNN-based detection approach that employs a novel regularization method to reduce kernel weights and address overfitting, improving effectiveness against unrecognized attacks. Additionally, a semi-supervised learning method using an LSTM autoencoder combined with One Class SVM is introduced, specifically designed to detect DDoS attacks. This approach enhances the detection capabilities within SDN environments, showcasing the potential of DL in advancing network security.20 0Item Restricted DEEP LEARNING-ASSISTED EPILEPSY DETECTION AND PREDICTION(Florida Atlantic University, 2024) Saem Aldahr, Raghdah; Ilyas, MohammadEpilepsy is a multifaceted neurological disorder characterized by superfluous and recurrent seizure activity. Electroencephalogram (EEG) signals are indispensable tools for epilepsy diagnosis that reflect real-time insights of brain activity. Recently, epilepsy researchers have increasingly utilized Deep Learning (DL) architectures for early and timely diagnosis. This research focuses on resolving the challenges, such as data diversity, scarcity, limited labels, and privacy, by proposing potential contributions for epilepsy detection, prediction, and forecasting tasks without impacting the accuracy of the outcome. The proposed design of diversity-enhanced data augmentation initially averts data scarcity and inter-patient variability constraints for multiclass epilepsy detection. The potential features are extracted using a graph theory-based approach by analyzing the inherently dynamic characteristics of augmented EEG data. It utilizes a novel temporal weight fluctuation method to recognize the drastic temporal fluctuations and data patterns realized in EEG signals. Designing the Siamese neural network-based few-shot learning strategy offers a robust framework for multiclass epilepsy detection. Subsequently, Federated Learning (FL) architecture enables epileptic seizure prediction and enhances the generalization capability by utilizing numerous seizure patterns across diversified and globally distributed epileptic patients. By capturing the potential patterns, the hybrid model design potentially offers superior prediction accuracy by integrating a spiking encoder with graph convolutional neural networks. The preictal probability of each local model then aggregates the weights of the local medical centers with the global FL. Furthermore, applying the adaptive neuro-fuzzy inference system ensures a patient-specific preictal probability by combining the local model with patientspecific clinical features. Finally, epileptic seizure forecasting utilizes Self-Supervised Learning (SSL) capabilities to overcome the limitations of annotated EEG data. This selfsupervised transfer learning improves the training efficiency in massively arriving EEG data streams. The dual-feature embedding enhances the learning ability while a lightweight prediction utilizes the embeddings from the pretext task for epilepsy forecasting in the downstream task. The performance testing on the benchmark datasets reveals the accuracy of epilepsy detection, prediction, and forecasting by addressing the limitations of the existing approaches for effective patient management. The research outcomes ultimately enable real-time, transparent, and personalized solutions to ensure commitment towards the quality of life.21 0Item Restricted Leveraging Deep Learning for Change Detection in Bi-Temporal Remote Sensing Imagery(University of Missouri-Columbia, 2024) Alshehri, Mariam; Hurt, J. AlexDeforestation in the Brazilian Amazon poses significant threats to global climate stability, biodiversity, and local communities. This dissertation presents advanced deep learning approaches to improve deforestation detection using bi-temporal Sentinel-2 satellite imagery. We developed a specialized dataset capturing deforestation events between 2020 and 2021 in key conservation units of the Amazon. We first adapted transformer-based change detection models to the deforestation context, leveraging attention mechanisms to analyze spatial and temporal patterns. While these models showed high accuracy, limitations remained in effectively capturing subtle environmental changes. To address this, we introduce DeforestNet, a novel deep learning framework that integrates advanced semantic segmentation encoders within a siamese architecture. DeforestNet employs cross-temporal interaction mechanisms and temporal fusion strategies to enhance the discrimination of true deforestation events from background noise. Experimental results demonstrate that DeforestNet outperforms existing models, achieving higher precision, recall, and F1-scores in deforestation detection. Additionally, it generalizes well to other change detection tasks, as evidenced by its performance on the LEVIR-CD urban building change detection dataset. This research contributes a robust and efficient framework for accurate change detection in remote sensing imagery, offering valuable tools for environmental monitoring and aiding global efforts in sustainable forest management and conservation.28 0Item Restricted Enhancing Breast Cancer Diagnosis with ResNet50 Models: A Comparative Study of Dropout Regularization and Early Stopping Techniques(University of Exeter, 2024-09-20) Basager, Raghed Tariq Ahmed; Kelson, Mark; Rowland, SarehEarly detection and treatment of breast cancer depend on accurate image analysis. Deep learning models, particularly Convolutional Neural Networks (CNNs), have proven highly effective in automating this critical diagnostic process. While prior studies have explored CNN architectures [1, 2], there is a growing need to understand the role of dropout regularization and fine-tuning strategies in optimizing these models. This research seeks to improve breast cancer diagnosis by evaluating ResNet50 models trained from scratch and fine-tuned, with and without dropout regularization, using both original and augmented datasets. Assumptions and Limitations: This research assumes that the Kaggle Histopathologic Cancer Detection dataset is representative of real-world clinical images. Limitations include dataset diversity and computational resources, which may affect generalization to broader clinical applications. ResNet50 models were trained on the Kaggle Histopathologic Cancer Detection dataset with various configurations of dropout, early stopping, and data augmentation [3–6]. Performance was assessed using accuracy, precision, recall, F1-score, and AUC-ROC metrics [7, 8]. The best-performing model was a ResNet50 trained from scratch without dropout regularization, achieving a validation accuracy of 97.19%, precision of 96.20%, recall of 96.90%, F1-score of 96.55%, and an AUC-ROC of 0.97. Grad-CAM visualizations offered insights into the model’s decision-making process, enhancing interpretability crucial for clinical use [9,10]. Misclassification analysis showed that data augmentation notably improved classification accuracy, particularly by correcting previously misclassified images [11]. These findings highlight that training ResNet50 without dropout, combined with data augmentation, significantly enhances diagnostic accuracy from histopathological images. Original Contributions: This research offers novel insights by demonstrating that a ResNet50 model without dropout regularization, trained from scratch and with advanced data augmentation techniques, can achieve high diagnostic accuracy and interpretability, paving the way for more reliable AI-powered diagnostics.15 0Item Restricted Early Detection of Pleuropulmonary Blastoma Using Transformers Models(Bowie State University, 2024) Almenwer, Sahar; El-Sayed, HodaChildhood cancer is the second leading cause of death among children under the age of fifteen, according to the American Cancer Society. The number of diagnosed cancer cases in children continues to rise each year, leading to many tragic fatalities. One specific type of cancer, pleuropulmonary blastoma (PPB), affects children from newborns to those as old as six years. The most common way to diagnose PPB is through imaging; this method is quick, cost-effective, and does not require specialized equipment or laboratory tests. However, relying solely on imaging for early detection of PPB can be challenging because of lower accuracy and sensitivity. It is time consuming and susceptible to errors because of the numerous potential differential diagnoses. A more accurate diagnosis of PPB depends on identifying mutations in the DICER1 gene. Recent advancements in biological analysis and computer learning are transforming cancer treatment. Deep learning (DL) methods for diagnosing PPB are becoming increasingly popular. Despite facing some challenges, DL shows a significant promise in supporting oncologists. However, some advanced models possess a limited local receptive field, which may restrict their ability to comprehend the overall context. This research employs the vision transformer (ViT) model to address these limitations. ViT reduces computation time and yields better results than existing models. It utilizes self-attention among image patches to process visual information effectively. The experiments in this study are conducted using two types of datasets, medical images and genomic datasets, employing two different methodologies. One approach uses the ViT model combined with an explainability framework on large medical image datasets with various modalities. The other involves developing a new hybrid model that integrates the vision transformer with bidirectional long short-term memory (ViT-BiLSTM) for genomic datasets. The results demonstrate that the ViT model and the new hybrid model, ViT-BiLSTM, significantly outperform established models, as validated by multiple performance metrics. Consequently, this research holds great promise for the early diagnosis of PPB, reducing misdiagnosis occurrences, and facilitating timely intervention and treatment. These findings could revolutionize medical diagnosis and shape the future of healthcare.11 0Item Open Access Parking Occupancy Classification: Deep learning model compression for edge device classification(Queen Mary University of London, 2024) Tamim, Ziad; Ansari, Tayyab AhmedUrban areas face severe traffic congestion due to poorly managed parking systems. Advanced parking management, like automated and smart parking guidance systems, offers a feasible solution requiring real-tim occupancy data. Traditional sensor-based methods are costly and inefficient for large scale parking, whereas video-based sensing is more effective. Deep learning methods improve accuracy but have high computational costs, affecting real-time performance. Central servers or cloud platforms are often used but can be impractical due to high resource demands. Instead, utilising edge devices with model compression techniques—such as quantisation and knowledge distillation enhances efficiency. This study aims to boost the inference speed of parking classification algorithms by developing a custom model called QCustom based on the MobileNet Depthwise Separable Convolution blocks and using compression techniques to reduce the inference time further. Contributions include developing an edge-based real-time occupancy system, setting performance benchmarks, optimising models for edge devices, and testing on a prototype parking lot. The goal is efficient and accurate parking management for smart cities. Results of the paper include accuracy of 98.8% on the CNRPark-EXT dataset, real world implementation accuracy of 97.44%, and an inference speed for one parking slot of 0.746ms on the Raspberry Pi 5.44 0