Saudi Cultural Missions Theses & Dissertations
Permanent URI for this communityhttps://drepo.sdl.edu.sa/handle/20.500.14154/10
Browse
150 results
Search Results
Item Restricted Quantifying the Human Impact on Vegetation Health in Rawdat Al Khafs, Saudi Arabia, Using Multi-Source Geospatial Data and Machine Learning(Saudi Digital Library, 2026) Alajmi, Abdulhadi; Dewan, AshrafArid and hyper-arid environments are vulnerable to land degradation and have become focal targets for large-scale afforestation initiatives combating desertification. The One Million Tree Initiative at Rawdat Al Khafs, a hyper-arid rawdah ~100 km northeast of Riyadh receiving < 50 mm annual rainfall, operates under the Saudi Green Initiative and Vision 2030. Evaluating afforestation effectiveness in such settings remains methodologically challenging, as existing frameworks rarely separate climatedriven from human-induced vegetation change in hyper-arid conditions. This study addresses these gaps through three inter-connected objectives: (i) establishing a climate-driven vegetation baseline using a Random Forest (RF) regression model trained on pre-plantation Sentinel-2 imagery and multi-source climate data (20182021); (ii) detecting and quantifying residual vegetation trends (2018–2025) that exceed this baseline and may represent a non-climatic signal conditionally attributable to afforestation; and (iii) characterising the spatial fingerprint of the detected anomaly through phase-based proximity analysis and distance-decay modelling. The RF–RESTREND framework combines 10 m Sentinel-2 imagery, CHIRPS precipitation, and ERA5-Land temperature data with Mann–Kendall trend testing, Sen's slope, Difference-in-Differences (DiD) correction, and SHAP analysis, applied to both NDVI and EVI. A persistent positive vegetation anomaly was observed within the plantation boundary from mid-2022 onwards, consistent across both indices and not fully explained by the climate counterfactual. Within the study area, 77.6% of NDVI pixels and 81.7% of EVI pixels exhibited statistically significant greening (Mann–Kendall Z > +1.96), with mean Z-scores of +3.97 and +4.45, respectively. The EVI distance-decay model (R² = 0.53; decay length = 65 m) indicated a localised boundary effect, while SHAP analysis identified spatial position and long-term climatic trends as dominant predictors, consistent with micro-topographic moistureconcentration mechanisms in rawdah ecosystems. Attribution is framed as conditional, reflecting the short pre-plantation training window and the widening climate variability of the post-plantation period. These findings provide an early satellitebased, climate-corrected assessment of an ecological response associated with the One Million Tree Initiative. The RF–RESTREND framework is reproducible and scalable to comparable arid restoration contexts, supporting Vision 2030 monitoring.9 0Item Restricted Evaluating Hybrid AI Approaches in email Spam Detection: A Literature Review(Saudi Digital Library, 2026) Alshamrani, Husam A; Sabar, NasserSpam is still one of the most serious cybersecurity issues of the day, and serves as a method of delivering phishing and malware. In this thesis, two complementary parts are integrated: First, a PRISMA-based systematic review of 55 studies that were published from 2023 to 2025 and analyze the classical, AI-based and ensemble spam detection techniques; and second, a controlled proof-of-concept experiment on the Enron-Spam corpus, where three distinct classical classifiers (Naïve Bayes with Bag-of-Words, Logistic Regression with TF-IDF, Linear SVM with TF-IDF) are compared against a stacking ensemble of the three classifiers with a Logistic Regression meta-classifier. All four configurations were very close together and obtained an accuracy of between 0.989 and 0.993, with the stacking ensemble having the highest F1-score (0.9923) and the lowest false-positive rate (0.0088); but there were no significant differences between the four configurations when a paired statistical test was not used. The thesis contribution lies in the synthesis of the various perspectives of the 2023–2025 hybrid and ensemble approaches and an internally consistent baseline comparison on a standard corpus. The study is restricted to English-language email and to lexical features; further extensions of the study using deep-learning, multilingual, and adversarial techniques are suggested.10 0Item Restricted DEEP REINFORCEMENT LEARNING BASED SEMI AUTONOMOUS CYBERATTACK DETECTION FOR INTERNET OF THINGS (IOT) SYSTEMS(Saudi Digital Library, 2026) AlRuwaili, Ibtihaj; AlQawasmi, KhaledAbstract The Internet of Things (IoT) has made today's networked world more complex and vulnerable, thus making it an appealing target for advanced cyberattacks. Limited adaptability, poor generalization and responsiveness to new and evolving attack behaviors are common problems with the traditional cybersecurity approaches that rely on static rules and supervised Machine Learning (ML). Furthermore, traditional IPSs are not equipped with the ability to adapt and learn over time in response to changing threats and vulnerabilities in the cyber landscape. To overcome the restrictions a novel Deep Reinforcement Learning (DRL) based cybersecurity framework is proposed for adaptive intrusion detection in heterogeneous enterprise-network and IoT based environment.The framework turns intrusion detection into a sequence of decisions, where a DRL agent keeps interacting with the environment and optimizes intrusion detection policies using rewards-driven learning. In order to test the diversity of the experiments and analyze the adaptive learning behavior, the framework was experimentally evaluated on two cybersecurity benchmark datasets: CICIDS2017 and TON_IoT.It was evaluated experimentally using CICIDS2017 and TON_IoT datasets, which are both widely used in the cybersecurity research community. Three DRL algorithms DDQN,PPO,DDPG were implemented and tested with various performance measures such as Accuracy, Precision, Recall, F1-Score, False positive rate (FPR) and ROC-AUC.Results of the experiments showed that the different evaluated DRL algorithms performed well in both cybersecurity test environments. However DDQN was found to be the best in terms of classification consistency, convergence stability and adaptive learning behavior in comparison to PPO and DDPG models and it was the most consistently and stably performing model. In particular, on the CICIDS2017 dataset, DDQN scored 97.3% on the Accuracy metric, 97.4% on the F1-Score metric, and 0.989 on the ROC-AUC metric, and on the TON_IoT dataset, the metrics were 95.6% for Accuracy, 95.6% for f1-score, and 0.978 for ROC-AUC. Moreover, DDQN achieved an FP rate of merely 2.1% and 3.4% in CICIDS2017 and TON_IoT respectively, suggesting a strong intrusion-classification capability under heterogeneous traffic conditions.The findings further showed that IoT environments bring in more complexity in cybersecurity with heterogeneous telemetry and dynamic communication patterns. Moreover, comparison showed that DRL-based method offers better adaptability, ongoing policy optimization, and better decision-support capability in dynamic cybersecurity scenarios.8 0Item Restricted AI-Enabled Autonomous Knowledge Extraction from Large-Scale Textual Data(Saudi Digital Library, 2026) Alharbi, Abdulrahman; Obradovic, ZoranThe rapid growth of large-scale textual data across social media platforms, news media, and scientific repositories presents both unprecedented opportunities and significant challenges for extracting meaningful insights. During global events such as the COVID-19 pandemic, understanding public discourse requires analyzing vast amounts of noisy, heterogeneous, dynamic, and geographically distributed data. At the same time, the exponential increase in scientific publications has made traditional evidence synthesis methods increasingly labor-intensive, time-consuming, and difficult to scale. Existing approaches to textual knowledge extraction often operate in isolation, lack interpretability, fail to integrate heterogeneous data sources, and do not support scalable end-to-end automation. This dissertation addresses these limitations by proposing a unified framework for AI-enabled autonomous knowledge extraction from large-scale textual data. The research introduces a comprehensive pipeline that integrate sentiment analysis, topic modeling, semantic interpretation, spatiotemporal reasoning, and multi-agent automation for scalable, robust and reproducible text analysis across heterogeneous domains. First, this work introduces TriLex, a novel unsupervised sentiment analysis framework that combines multiple lexicon-based sentiment analysis methods through weighted aggregation, majority voting, and dynamic thresholding technique to improve robustness and accuracy for short and noisy textual data. Building on this foundation, a hierarchical spatiotemporal framework is developed to capture the evolution of public sentiment across global, national, and regional scales. The framework integrates over 7 million social media posts and thousands of news articles to analyze COVID-19 vaccine discourse across time, geographic regions, and platforms. To enhance topic interpretability, this research integrates BERTopic with large language models (LLMs), enabling automated generation of coherent and context-aware topic representations for large-scale textual discourse. A cross-platform analytical framework is further introduced to examine temporal relationships between social media and news media discourse, demonstrating a bidirectional relationship in which news coverage and public discourse influence each other over time. Extending beyond discourse analysis, this dissertation introduces an Agentic AI framework that automates the end-to-end process of large-scale multilingual knowledge extraction and evidence synthesis. The proposed multi-agent system coordinates specialized agents for query generation, multilingual retrieval, metadata harmonization, title and abstract screening, and full-text analysis. Evaluated on a multilingual corpus of over 52,000 scientific records, the framework achieves high screening performance while substantially reducing processing time from months to hours, demonstrating significant improvements in scalability, robustness, and reproducibility. Collectively, this dissertation bridges the gap between analytical understanding and autonomous knowledge extraction from large-scale textual data. By integrating robust sentiment analysis, interpretable topic modeling, spatiotemporal discourse analysis, and autonomous AI systems within a unified framework, this work establishes a scalable and extensible paradigm for transforming heterogeneous textual data into actionable knowledge. The proposed methodologies are validated using real-world datasets spanning social media, news media, and scientific literature across diverse application domains.13 0Item Restricted Harmonic Impact Assessment and Prediction in a Power System with Nonlinear Loads(Saudi Digital Library, 2025) Almogargesh, Yousef Yaqoob Y; Swamidoss, SathiakumarThis thesis presents a simulation-based and machine learning framework for predicting power quality (PQ) indices in residential power systems with nonlinear loads. Four MATLAB/Simulink models representing nonlinear loads, induction motor loads, thyristor converters, and photovoltaic grid-connected systems were developed to generate voltage and current waveforms under different operating conditions. Time-domain and frequency-domain features were extracted from the simulated signals and used to train artificial neural network (ANN) models for predicting six key PQ indices: Total Harmonic Distortion (THD), Crest Factor, Form Factor, Power Factor, RMS Voltage, and Peak Voltage. Both shallow and deep neural network architectures were implemented and evaluated using statistical performance metrics including Mean Squared Error (MSE), Mean Absolute Error (MAE), and Pearson correlation coefficient. The results demonstrate that the proposed approach accurately predicts future power quality conditions while reducing the need for repeated analytical calculations. This framework provides an efficient tool for power quality monitoring and supports the development of intelligent and proactive power system management strategies.21 0Item Restricted Personalized Course Recommendations Leveraging Machine & Transfer Learning Toward Improved Student Outcomes(Saudi Digital Library, 2026) Algarni, Shrooq; Frederick, SheldonAt matriculation, university advising typically operates under tight informational constraints, often with no access to post-enrolment interaction history. We propose a unified, leakage-controlled pipeline that (i) predicts early dropout risk and (ii) generates cold-start programme recommendations using only pre-enrolment signals, with an optional early-warning variant that additionally incorporates first-term academic aggregates. The pipeline instantiates lightweight multimodal components: a tabular RNN, a DistilBERT encoder for short profile sentences, and a cross-attention fusion module, trained and evaluated end-to-end on a public benchmark (UCI id 697; n = 3630 students across 17 programmes). For dropout prediction, fusing text with numeric features yields the strongest thresh olded performance (Hybrid RNN–DistilBERT: F1 ≈ 0.9161, MCC ≈ 0.7750), while simple ensembling modestly improves threshold-free discrimination (AUROC up to ≈ 0.9488 via Stacking Ensemble, compared to ≈ 0.9459 for Weighted Ensemble). A text-only branch performs substantially worse, indicating that numeric demographics and early curricular aggregates carry most of the predictive signal at this horizon. For programme recommendation, pre-enrolment demographics alone support actionable rankings (De mographic MLP: NDCG@10 ≈ 0.5793, Top-10 ≈ 0.9380), outperforming a popularity prior by roughly 25–27 percentage points in NDCG@10; adding text yields only marginal improvements in hit rate and does not improve NDCG on this cohort. Methodologically, we apply leakage guards, deterministic preprocessing, stratified splits, and comprehensive metric reporting to enable reproducibility on non-proprietary data. Practically, the pipeline supports orientation-time triage via high-recall early warning and shortlist generation for programme selection. Overall, the results cast matriculation-time advising as a joint prediction–recommendation problem solvable with carefully engineered pre-enrolment views and lightweight multimodal models, without relying on historical interactions.13 0Item Restricted Machine Learning Algorithms for Secure and Reliable Electric Grid Operations and Control(Saudi Digital Library, 2026-09) Bahwal, Obai; Sankar, LalithaThis dissertation develops Machine Learning (ML) algorithms for secure and reliable electric grid operations and control by addressing three related problems. The first part studies real-time event identification using synchrophasor measurements, physics-based modal decomposition, and interpretable classifiers to distinguish generation loss from load loss events. Targeted adversarial attacks are developed to evaluate robustness under both white box and gray box settings, showing that learned event identification models are susceptible to adversarial attacks and that simpler models such as logistic regression are generally more vulnerable than gradient boosting. The second part builds on this vulnerability analysis and focuses on enhancing the security of ML event identification models in a white box adversarial setting. Two mitigation strategies are developed: robust classification through iterative adversarial retraining, and a dual-classifier architecture that combines event classification with attack detection. Numerical results on the synthetic South Carolina 500-bus system show that while robust retraining provides only modest improvement, the dual classifier approach is highly effective, reducing successful undetected attacks to under 0.1%. The third part addresses reliable grid control through a forecast-integrated rolling-horizon Model Predictive Control (MPC) framework for net-demand balancing using Distributed Energy Resource Aggregators (DERAs). Each DERA is modeled as a generalized battery with state-of-charge, power, and ramping constraints, while Linear Regression (LR) and Long Short-TermMemory (LSTM) forecasting models are integrated with MPC to generate real-time allocation policies. Using high-resolution California Independent System Operator (CAISO) net-demand data, results show close tracking of net-demand and reveal clear tradeoffs among forecast horizon, update frequency, and control performance, with LSTM generally benefiting longer time-shifts and LR remaining competitive for shorter update intervals. These three parts show that effective ML for power systems must be accurate, physically grounded, cyber-resilient, and compatible with real-time operational constraints.Item Restricted Algorithms for Growth Pattern Based Analysis of Lung Adenocarcinoma Histology(Saudi Digital Library, 2026) AlRubaian, Arwa; Rajpoot, Nasir; Raza, ShanLung Adenocarcinoma (LUAD) is a leading cause of cancer deaths and shows considerable variation in patient outcomes due to its complex histological, immune, and molecular diversity. Traditional computational pathology methods use global, pattern-agnostic representations that do not capture the structured organization of tumor tissue. This thesis develops new, pattern-aware computational approaches to address this gap. First, we introduce CellOMaps, a biologically informed image representation that encodes the cellular organization of LUAD tissue. By focusing on spatial structure rather than raw visual appearance, CellOMaps enables robust, scalable characterization of LUAD histological growth patterns. Using this representation, we propose a framework for dense, patch-level growth pattern classification across Whole Slide Images (WSIs), offering a reproducible and spatially resolved alternative to conventional predominant-pattern assessment and demonstrating improved robustness across institutions. Next, we investigate immune heterogeneity in LUAD by analyzing the spatial distribution of Tumor-Infiltrating Lymphocytes (TILs). We introduce GPS-TILs, a growth pattern–specific digital biomarker that quantifies the presence, density, abundance, and spatial dispersion of immune infiltration within distinct morphological patterns. This pattern-aware immune profiling improves prognostic stratification compared to global TILs assessment and manual grading, highlighting the importance of incorporating histological context into immune analysis. Finally, we address molecular inference from histopathology by predicting Tumor Mutational Burden (TMB) from WSIs. We introduce GRIL-GNN, a graph-based learning framework that aggregates information across spatially organized tissue regions while preserving detailed morphological features. This approach uses a novel unified learning objective that combines supervised learning with self-supervised regularization, enabling robust representation learning under weak supervision. By restricting analysis to localized tissue regions with shared histological patterns, this work examines the distribution of the TMB predictive signal within different morphological patterns. Overall, this work demonstrates that integrating spatial and pattern-aware analysis improves the interpretation of morphological, immune, and molecular signals in LUAD. The approaches proposed here provide a framework for more precise, clinically relevant computational pathology, with potential applications to other cancers characterized by complex tissue structure.Item Restricted Saudi Dialect Sentiment Analysis: A Hybrid Approach and Evaluation on Real-World Consumer Reviews(Saudi Digital Library, 2026) Alsemaree, Ohud; Singh Gill, SukhpalThis thesis presents a hybrid sentiment analysis framework for the Saudi dialect, addressing the limited availability of linguistic resources and annotated datasets for Arabic sentiment analysis. The proposed approach combines lexicon-based methods with machine learning and deep learning techniques to improve sentiment classification performance. A Saudi dialect sentiment lexicon (LSAnArTe) and a large-scale annotated dataset were developed to support the research. Experimental results demonstrate that the hybrid framework outperforms baseline models, achieving high classification accuracy and providing valuable resources for future research in Arabic Natural Language Processing and sentiment analysis.11 0Item Restricted MALWARE CLASSIFICATION VIA BYTECODE VISUALIZATION AND MULTIMODAL DEEP LEARNING(Saudi Digital Library, 2026) مكاوي, صالح; Kenneth, Barner; Michael De. LuciaThe rapid proliferation of Android malware poses a critical threat to mobile security, driven by the open-source nature of the Android ecosystem, broad access to its Software Development Kit (SDK), and the availability of multiple app distribution channels. Traditional detection methods, including signature-based, static, and dynamic analysis, often fail against novel or obfuscated variants that use encryption, packing, and polymorphism to evade detection. This dissertation addresses these limitations through three progressive, interconnected contributions. Contribution I introduces a semantic bytecode-to-image encoding method based on Shannon entropy, computed over sliding windows of Dalvik Executable (DEX) bytecode and mapped to the red and blue channels of an RGB image. This encoding directly exposes obfuscation artifacts in encrypted, packed, and compressed code regions that blind color-mapping approaches cannot distinguish. Evaluated on 184,474 samples from AndroZoo for binary malware classification, the entropy encoder outperforms the MalNet and Classbyte baselines across five state-of-the-art CNN architectures, achieving up to 95.77% accuracy and 98.25% ROC-AUC. Contribution II extends this encoding into a full multiclass framework and dataset, MalVis, by incorporating byte-level N-gram frequency statistics into the green channel. By combining entropy and N-gram signals, MalVis images capture both low-level randomness and high-level structural code patterns. To support the research community, we release the MalVis dataset, the largest publicly available Android malware visualization resource, comprising over 1.3 million labeled RGB images spanning nine malware families and benign samples. To validate that CNN models rely on the proposed encodings rather than spurious image artifacts, we apply Grad-CAM and Grad-CAM++ attention mapping, confirming that model attention consistently aligns with the entropy- and N-gram-encoded channels across all malware classes. Contribution III introduces ViCoMal, a late-fusion multimodal framework that addresses the single point of failure (SPOF) inherent in unimodal approaches. ViCoMal pairs MalVis image-based malware representations with 65 DEX-based contextual features, including 19 novel engineered features consisting of normalized risk scores, binary capability indicators, and rule-based behavioral profiles extracted using static analysis. Five CNN architectures and seven classical machine learning models are trained independently per modality, and their class-probability outputs are combined through eight fusion strategies. To handle a severe 169:1 class imbalance, SMOTE oversampling and class-weighted training are applied jointly. Evaluated under five-fold stratified cross-validation on the full 1.3M ViCoMal dataset, the best ensemble, which averages the predictions of the top three models (Random Forest, ResNet50, and XGBoost), achieves 91.84% accuracy, outperforming the strongest image-only baseline by 3.43 percentage points and the strongest contextual-only baseline by 2.05 percentage points. Together, these contributions establish a scalable, interpretable, and high-performing pipeline for Android malware detection, advancing the state of the art in both malware visualization and multimodal security analysis.13 0