Saudi Cultural Missions Theses & Dissertations
Permanent URI for this communityhttps://drepo.sdl.edu.sa/handle/20.500.14154/10
Browse
5 results
Search Results
Item 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.47 0Item Restricted Explainable AI Approach for detecting Generative AI Imagery(Aston University, 2024-09-29) Alghamdi, Sara; Barns, ChloeThe rapid advancement of Artificial Intelligence (AI) and machine learning, particularly deep learning models such as Convolutional Neural Networks (CNNs), has revolutionized image classification across diverse fields, including healthcare, autonomous vehicles, and digital forensics. However, the proliferation of AI-generated images, commonly referred to as deepfakes, has introduced significant ethical, societal, and security challenges. Deepfakes leverage AI to create highly realistic yet synthetic media, complicating the ability to differentiate between authentic and manipulated content. This has heightened the need for robust tools capable of accurately detecting and classifying such media to combat the risks of misinformation, fraud, and erosion of public trust. Traditional models, while effective in classification, often lack transparency in their decision-making processes, limiting stakeholder trust. To address this limitation, this study explores the integration of Explainable AI (XAI) techniques, such as SHAP (SHapley Additive exPlanations), with CNNs to enhance interpretability and trust in model predictions. By employing CNNs for high-accuracy classification and XAI methods for feature-level explanations, the research aims to contribute to digital forensics and content moderation, offering both technical reliability and transparency. This study highlights the critical need for trustworthy AI systems in the fight against manipulated media, providing a framework that balances efficacy, transparency, and ethical considerations.47 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.12 0Item Restricted Optimizing Deep Learning Architectures for Enhanced Breast Cancer Detection on Mammography Images(University of Liverpool, 2024) Albalawi, Alaa; Anosova, OlgaBreast cancer is a major health issue affecting millions of women globally, and early detection through mammography is critical for improving survival rates. However, mammography often faces challenges, such as imbalanced datasets and poor image quality, especially in dense breast tissue, which complicates accurate detection. This project explores the use of deep learning techniques, including Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs), to address these challenges and enhance breast cancer detection. Five models—ResNet50V2, MobileNetV2, VGG16, ResNet from scratch, and ViT—were compared using various evaluation metrics. Two datasets, RSNA and MIAS, were used, with preprocessing applied only to the RSNA dataset. The experiments were divided into three stages: the first stage evaluated the original RSNA dataset without preprocessing, the second stage tested the balanced and preprocessed RSNA dataset with and without data augmentation, and the third stage applied similar experiments on the MIAS dataset. The results showed that preprocessing and balancing the RSNA dataset significantly improved model performance, while data augmentation further enhanced accuracy and generalization. ViT models outperformed other CNN architectures, demonstrating superior detection abilities after augmentation. ResNet from scratch also showed strong results, benefiting from its controlled architecture that adapted well to high-resolution images. This study highlights how addressing class imbalance and optimising model architectures can lead to more effective breast cancer detection using deep learning.18 0Item Restricted Applications and effectiveness of using artificial intelligence in the assessment of individuals with aphasia, A scoping review(Saudi Digital Library, 2023-11-03) Alhejji, Bader; Caroline, Haw; Stuart, CunninghamAim: This review aims to examine the current uses of artificial intelligence (AI) in evaluating individuals with aphasia and assessing the effectiveness of these AI-based tools. Methodology: The scoping review methodology was employed to comprehensively investigate the role of artificial intelligence (AI) and machine learning in aphasia assessment. This encompassed systematic searches across databases such as ScienceOpen and PubMed, supplemented by Google Scholar and StarPlus for grey literature inclusion. Eligibility criteria targeted machine learning and AI techniques applied to adult aphasia patients, with a focus on post-2010 publications. The data extraction process involved documenting study particulars, AI algorithms, outcome measures, and findings. Descriptive analysis and statistical methods facilitated AI approach identification, categorization, and accuracy assessment. The PRISMA checklist was utilized for study quality evaluation, promoting transparency and rigor. Findings: Predominant AI approaches within this review were Support Vector Machines (SVMs) and Convolutional Neural Networks (CNNs), prominently featured across the selected studies. AI-based tools for the assessment of aphasia exhibited an average effectiveness of 88.3%, drawn from insights gleaned from 24 studies with 1546 participants. Remarkably, one of the AI apps achieved an accuracy of 95%, underscoring SVMs and CNNs' technology potential for accurate and impactful aphasia assessment outcomes. These findings emphasize the effectiveness and capacity of SVMs and CNNs to enrich clinical practice and expand research in aphasia evaluation. Conclusion: The present study identifies AI-based systems for assessing aphasia as a promising field, yet it acknowledges limitations concerning patient privacy and the need for a comprehensive AI-based system that covers the entire assessment process of aphasia.30 0