Saudi Cultural Missions Theses & Dissertations

Permanent URI for this communityhttps://drepo.sdl.edu.sa/handle/20.500.14154/10

Browse

Search Results

Now showing 1 - 10 of 25

Restricted
A Facial Expression-Aware Edge AI System For Driver Safety Monitoring
(Saudi Digital Library, 2025) Almodhwahi, Maram; Wang, Bin
This dissertation presents a driver monitoring system (DMS) that integrates emotion recognition to address critical issues in road safety. Road safety has become a global concern due to the significant increase in vehicle numbers and the rapid growth of transportation infrastructure. The number one cause of road accidents is human error, with a 90% ratio, with common contributing factors like distraction, drowsiness, panic, and fatigue. Traditional DMS approaches often fall short in identifying these emotional and cognitive states, limiting their effectiveness in accident prevention. To address these limitations, this research proposes a robust, deep-learning-based DMS framework designed to identify and respond to driver emotions and behaviors that may compromise safety. The proposed system utilizes advanced convolutional neural networks (CNN), specifically the inception module and Caffe-based ResNet-10 with a single-shot detector (SSD), to perform efficient facial detection and classification. These chosen model structures helped balance computational efficiency and accuracy. The DMS is trained on an extensive, diverse dataset comprising approximately 198,000 images and 1,600 videos sourced from multiple public and private datasets, ensuring the system’s robustness across a range of emotions and real-world driving scenarios. Emotions of interest include high-risk states such as drowsiness, distraction, and fear, alongside neutral conditions, and the model can perform well in different conditions, including low-light and foggy/blurry environments. Methodologically, the system incorporates essential data preprocessing techniques such as resizing, brightness normalization, pixel scaling, and noise reduction to optimize the model’s performance. On top of that, data augmentation and grayscale conversion improves the dataset’s variability, allowing the decrease of computational costs without sacrificing accuracy. This approach enabled the model to achieve high performance metrics, with an overall accuracy of 98.6% , an F1-score of 0.979, precision of 0.980, and recall of 0.979 across the four primary emotional states. This research contributes to the field by offering a less invasive, real-time solution for monitoring high-risk driver behaviors and providing insights for further advancements in automated driver assistance technologies. Future directions include optimizing the system for microcontrollers with low power consumption and implementing alerts for high-risk states to further mitigate accident risks, as well as including a multi-modal fusion of data from different sources (Infrared Camera, and a Microphone) to increase emotion recognition accuracy, which leads to taking better control and initiating more efficient proactive interventions.
18 0
Restricted
THE IMPACT OF INDUSTRY 4.0 TECHNOLOGIES ON SUPPLY CHAIN RESILIENCE IN SAUDI ARABIA
(Saudi Digital Library, 2025) Alanazi, Jawaher; Greasley, Andrew
This dissertation examines the impact of Industry 4.0 technologies on supply chain resilience in Saudi Arabia, where initiatives such as Internet of Things and the Global Supply Chain Resilience Initiative (GSCRI) are central to industrial transformation. A systematic literature review (SLR) guided by the PRISMA framework was conducted, covering academic and grey literature published between 2020 and 2025. The search initially yielded 315 records; after applying inclusion and exclusion criteria, 26 studies were selected for detailed analysis. The findings indicate thatInternet of Things (AI), blockchain, the Internet of Things (IoT), and digital twins are the leading technologies supporting resilience capabilities, particularly in risk mitigation, operational continuity, agility, and sustainability. However, barriers such as high implementation costs, limited absorptive capacity, institutional inertia, and fragmented infrastructure constrain their full potential. This research contributes by integrating insights from policy initiatives, industry practices, and recent empirical studies to show how Industry 4.0 adoption strengthens resilience in supply chains within an emerging economy context. It underscores the strategic role of digital transformation in enabling continuity, flexibility, and sustainability. The study concludes with practical recommendations for policymakers and practitioners in Saudi Arabia, emphasizing the need to strengthen digital infrastructure, enhance workforce skills, and foster cross-sector collaboration. It also highlights avenues for future research, including empirical studies on digital maturity and comparative analyses across sectors and regions.
21 0
Restricted
Resource Scheduling Strategies to Optimise QoS in Integrated IoT and Fog Computing Environments
(Saudi Digital Library, 2025) Alshammari, Naif Hamdan; Pervaiz, Haris; Ahmed, Hasan; Ni, Qiang
In recent years, there has been a tremendous increase in the internet and its applications, which has attracted the attention of scholars and industries to investigate how to improve the quality of services (QoS). Improving QoS is considered a major challenge for users of IoT devices. To address this challenge, several technologies have emerged to extend cloud computing, including fog computing, which provides computational resources at the network’s edge. Nevertheless, fog computing faces limitations due to the constrained resources, limited computational processes and storage in fog devices compared to cloud infrastructure. This thesis investigates resource scheduling strategies to optimise QoS in fog computing, focusing on task scheduling and resource allocation approaches. The thesis begins with a qualitative comparative analysis of existing resource management approaches to optimise QOS. It classifies resource management approaches into several categories: application placement, task scheduling, resource allocation, task offloading, load balancing, and resource provisioning. These categories are either task-oriented, such as application placement, task scheduling, and task offloading, or resource-oriented, including resource allocation, load balancing, and resource provisioning. It also introduces a novel intelligent resource scheduling model using gated graph convolution neural networks (GGCNs) to trade off between delay and network usage with a limited number of fog nodes. The GGCN model outperforms various other existing approaches like PSO, FCFS, and JSF by 86.09%, 98.53%, and 98.02% respectively, in terms of total network usage. Additionally, in terms of loop delay, it achieves improvements of 68.64% over PSO, 92.07% over FCFS, and 76.26% over SJF. Furthermore, it presents a novel multi-objective scheduling framework utilising an enhanced multi-layer perceptron (eMLP). This new mechanism optimises several parameters, including delay, power consumption, and cost, while simultaneously optimising bandwidth. Experimental results show that eMLP reduces delay, network usage and cost by 75%, 65%, and %70 respectively, compared to other benchmark schemes such as GNN, SMA, FCFS, and SJF. Finally, the thesis discusses the current gaps and future directions for enhancing and further investigating QoS through fog computing.
15 0
Restricted
Novel Framework for Integrating Blockchain Technology into Logistics and Supply Chain Services
(Saudi Digital Library, 2025) Alkhaldi, Bidah; Al-Omary, Alauddin
Bottlenecks and operational inefficiencies in supply chains still persist despite technological innovations, due to structural and managerial issues. Blockchain integration presents a viable solution to these long-standing issues by offering tamper resistant ledgers, secure transactions and automation capabilities. This research takes a novel approach by designing a blockchain integration framework for supply chains, modifying the MOHBSChain framework to create the Supply-Blockchain framework. This framework is validated by developing a functional prototype using Hyperledger Fabric, by considering a port decongestion use case scenario. This research adopted an inductive approach, starting with informal observations of real-world port operations and a targeted literature review to identify patterns and challenges. The framework development was guided by the principles of transaction cost economics, resource-based view, and diffusion of innovations theories. MoSCoW method was used to prioritize features, while agile project management was adopted to ensure timely completion. Hyperledger Firefly and its connector framework were used as the middleware to facilitate blockchain integration, while chaincode developed using Go language was packaged and deployed to implement smart contracts. Raft orderer consensus mechanism was chosen to ensure resilience and fault tolerance. From a core functionality standpoint, the prototype allows initiation of smart contracts corresponding to functions such as creating and editing supply chain process-related documents, minimizing manual interventions and enhancing efficiency to reduce port congestion. It also offers live tracking of blockchain transactions, facilitating transparency and oversight, the permissioned nature of Hyperledger Fabric ensures security and robust access controls. Results of functional and performance testing conducted using Hyperledger Caliper, Prometheus, and Grafana, were satisfactory; this indicates the prototype's potential in alleviating bottlenecks in supply chains and quickly delivering benefits to key stakeholders such as port authorities, customs officers, shipping line representatives and logistics providers. In terms of limitations, the prototype is limited to basic functionalities and lacks advanced features required to meet operational and regulatory standards. Future improvements can focus on integrating AI for tasks such as predictive analytics and automated document verification, while technologies such as NFT-based schemas can enhance ownership verification and improve asset tracking.
48 0
Restricted
Enhancing Robustness and Energy Efficiency of IoT-Coupled Machine Learning Applications
(University of Georgia, 2025) AlShehri, Yousef; Ramaswamy, Lakshmish
Machine learning (ML) applications continue to revolutionize many domains. In recent years, there has been considerable research interest in building novel ML applications for a variety of Internet of Things (IoT) domains, such as precision agriculture, smart cities, and smart manufacturing. However, IoT characteristics pose several fundamental challenges to designing and implementing effective ML applications at the edge, specifically, inference-time data incompleteness and quality induced by sensor failures and the energy management of such applications. This dissertation comprises four components aimed at addressing the aforementioned challenges to enhance IoT ML-based systems’ robustness, energy efficiency, and reliability against sensor failures at inference time. First, to tackle the sudden and concurrent missing data of sensors at the inference time of the ML application, it introduces an ensemble of a few sub-models, each trained with distinct subsets of sensors chosen based on correlation to make ML robust against missing data. This ensemble-based approach maintains the accuracy of the IoTMLapplication during the occurrence of missing data at inference time via performing predictions using sub-model(s) that are built using the correlated sensors to the faulty sensors, excluding the faulty sensors. The second component involves an extensive study to identify energy bottlenecks for operating our ensemble-based approach, SECOE, on a resource-constrained edge device and find the number of ensemble models that further maintain the ML application’s performance while optimizing energy consumption. The third component introduces an energy-aware ensemble of models with enhanced energy management capabilities for handling data incompleteness during inference time to fit resource-constrained IoT devices. Finally, our research offers an innovative autoencoder model for correcting inaccurate/faulty sensor readings caused by the malfunctioning of multiple sensors simultaneously at inference time. This model treats different faulty readings (e.g., drift and bias) as one type via a correlation-based masking mechanism. The experimental results have demonstrated that our methods have effectively alleviated the impact of IoT sensor failures on the performance of theMLapplication during the inference time while optimizing its energy consumption, thereby decisively outperforming existing methods and significantly improving the overall reliability of ML coupled IoT applications.
22 0
Restricted
OPTIMIZING INTRUSION DETECTION IN IOT NETWORK ENVIRONMENTS THROUGH DIVERSE DETECTION TECHNIQUES
(Florida Atlantic University, 2025-03-11) Al Hanif, Abdulelah; Ilyas, Mohammad
The rapid proliferation of Internet of Things (IoT) environments has revolutionized numerous areas by facilitating connectivity, automation, and efficient data transfer. However, the widespread adoption of these devices poses significant security risks. This is primarily due to insufficient security measures within the devices and inherent weaknesses in several communication network protocols, such as the Message Queuing Telemetry Transport (MQTT) protocol. MQTT is recognized for its lightweight and efficient machine-to-machine communication characteristics in IoT environments. However, this flexibility also makes it susceptible to significant security vulnerabilities that can be exploited. It is necessary to counter and identify these risks and protect IoT network systems by developing effective intrusion detection systems (IDS) to detect attacks with high accuracy. This dissertation addresses these challenges through several vital contributions. The first approach concentrates on improving IoT traffic detection efficiency by utilizing a balanced binary MQTT dataset. This involves effective feature engineering to select the most important features and implementing appropriate machine learning methods to enhance security and identify attacks on MQTT traffic. This includes using various evaluation metrics such as accuracy, precision, recall, F1-score, and ROC-AUC, demonstrating excellent performance in every metric. Moreover, another approach focuses on detecting specific attacks, such as DoS and brute force, through feature engineering to select the most important features. It applies supervised machine learning methods, including Random Forest, Decision Trees, k-Nearest Neighbors, and Xtreme Gradient Boosting, combined with ensemble classifiers such as stacking, voting, and bagging. This results in high detection accuracy, demonstrating its effectiveness in securing IoT networks within MQTT traffic. Additionally, the dissertation presents a real-time IDS for IoT attacks using the voting classifier ensemble technique within the spark framework, employing the real-time IoT 2022 dataset for model training and evaluation to classify network traffic as normal or abnormal. The voting classifier achieves exceptionally high accuracy in real-time, with a rapid detection time, underscoring its efficiency in detecting IoT attacks. Through the analysis of these approaches and their outcomes, the dissertation highlights the significance of employing machine learning techniques and demonstrates how advanced algorithms and metrics can enhance the security and detection efficiency of general IoT network traffic and MQTT protocol network traffic.
38 0
Restricted
Design, Development and Deployment of Customisable Mobile and IoT Systems to Enhance Mosquito Surveillance
(University College London, 2025-04-10) Aldosery, Aisha; Kostkova, Patty
Mosquito-borne diseases pose significant public health challenges in tropical and subtropical regions, requiring precise and efficient surveillance methods. Traditional field data collection methods often lack the accuracy, timeliness and efficiency required to control outbreaks. This research advances mosquito field surveillance by designing, developing, and deploying two digital solutions customised for distinct environmental settings in Northeast Brazil and Madeira Island: a Mobile Surveillance System and an Internet of Things (IoT) Environmental Monitoring System. Developed through iterative processes and stakeholder engagement, these adaptable and scalable systems enhance the accuracy and granularity of data collection. The Mobile Surveillance System was adapted to regional requirements: in Brazil, it comprises a mobile app for field agents and a web platform for supervisors; in Madeira, it combines both functionalities into a single, unified mobile app. The implementation of both applications shares a common architecture that not only proves the systems’ generalisability but also boosts operational efficiency and data accuracy by digitising field data, supporting field agents, and aiding supervisors in managing activities. The IoT-based Environmental Monitoring System, featuring a five-layer architecture, including Arduino microcontrollers, weather and water sensors, and a water pump, autonomously and continuously captures high-resolution data, offering deeper insights into environmental influences on mosquito populations and supporting precise, location-specific predictive modelling. Detailed statistical analyses using Bayesian hierarchical models and correlation studies were conducted to pinpoint critical environmental predictors of mosquito breeding. Furthermore, a neural network classification-based predictive model was developed, enhancing weekly mosquito presence predictions by analysing temporal and sequential environmental patterns. This research distinguishes itself through its real-world deployments, addressing infrastructure, logistics, and technology challenges, while underscoring the importance of a process-oriented approach in tool development and recommending longitudinal deployments to assess the long-term impact of these technologies on mosquito population control and disease management in diverse environments.
16 0
Restricted
Software-based Fault-Tolerant Internet of Things (IoT) Multi-Sensor Device using the BEAM Virtual Machine
(Newcastle University, 2024-08-22) Alghamdi, Abdulrahman; Bystrov, Alex
The use of Internet of Things (IoT) devices in many industries, such as healthcare, agriculture, and transportation, has led to the reliability of such devices to become an essential requirement. It was argued that future business models would be dependent on IoT infrastructure. This project aimed to implement fault-tolerant IoT software using the Erlang virtual machine (BEAM) on the Raspberry Pi. The faults addressed are software faults, stuck-at-fault, and data loss faults. The objective was to build a multi-sensor IoT device that links the sensors to the cloud. It was decided to use the Elixir programming language as it had better support for external dependency and embedded systems. As for hardware, two sensors connected to the Raspberry Pi were used. A supervision tree was implemented using the Elixir language in Raspberry Pi, and experiments were then conducted to test the implementation. The implementation achieved a mean time to recovery (MTTR) of 2.16 milliseconds and 296 milliseconds in publish time. Moreover, it was found that increases in BEAM processes tend to be efficient in CPU usage due to a logarithmic relationship. The results proved BEAM as a substantial solution for IoT to meet digital business needs. The author is confident to recommend the BEAM as the tool for future reliable IoT devices.
23 0
Restricted
Adaptive Resilience of Intelligent Distributed Applications in the Edge-Cloud Environment
(Cardiff University, 2024-04) Almurshed, Osama; Rana, Omer
This thesis navigates the complexities of Internet of Things (IoT) application placement in hybrid fog-cloud environments to improve Quality of Service (QoS) in IoT applications. It investigates the optimal distribution of a Service Function Chain (SFC), the building blocks of an IoT application, across the fog-cloud infrastructure, taking into account the intricate nature of IoT and fog-cloud environments. The primary objectives are to define a platform architecture capable of operating IoT applications efficiently and to model the placement problem comprehensively. These objectives involve detailing the infrastructure's current state, execution requirements, and deployment goals to enable adaptive system management. The research proposes optimal placement methods for IoT applications, aiming to reduce execution time, enhance dependability, and minimise operation costs. It introduces an approach to effectively manage trade-offs through the measurement and analysis of QoS metrics and requires the implementation of specialised scheduling and placement strategies. These strategies employ concurrency to accelerate the planning process and reduce latency, underscoring the need for an algorithm that best corresponds to the specific requirements of the IoT application domain. The study's methodology begins with a comprehensive literature review in the area of IoT application deployment in hybrid fog-cloud environments. The insights gained inform the development of novel solutions that address the identified limitations, ensuring the proposal of robust and efficient solutions.
32 0
Restricted
Efficient Deep Learning for Plant Disease Classification in Resource Constrained Environment
(The University of Georgia, 2024) Alqahtani, Ola; Ramaswamy, Lakshmish
Deep Neural Networks (DNNs) have been widely used in today’s applications. In many applications such as video analytics, face recognition, computer vision, and classification problems like plant disease classification, etc. DNN models are constrained by efficiency constraints (e.g., latency). Many deep learning applications require low inference latency, which must fall within the parameters set by a service level objective. The prediction of the inference time of DNN models raises another problem which are the limited resources of Internet of Things devices. These devices need an effective way to run DNN models on them. One of the most widely discussed technological developments since the Internet of Things is edge machine learning (Edge ML), and with good reason. Edge Machine Learning is a fast-growing well-known technological improvement since the existence of the Internet of Things (IoT). Edge ML allows smart devices to use machine learning and deep learning techniques to analyze data using servers locally or at the device level, which reduces the need for cloud networks. This is caused by a variety of issues, including poor internet access, expensive cloud resources, low-resource edge devices, and a high failure rate of Internet of Things (IoT) devices, either because of battery or connection issues. Finding a way to effectively run the DNN models locally on IoT devices is crucial.
35 0

Saudi Cultural Missions Theses & Dissertations

Browse

Filters

Settings

Sort By

Results per page

Search Results