Saudi Cultural Missions Theses & Dissertations
Permanent URI for this communityhttps://drepo.sdl.edu.sa/handle/20.500.14154/10
Browse
4 results
Search Results
Item Restricted Partial Learning for MIMO Detection(Saudi Digital Library, 2024) Babulghum, Abdulaziz; ElHajjar, Mohammed; Ng, Soon Xin; Xu, ChaoReliable and efficient multiple-input multiple-output (MIMO) detection remains a central challenge in modern wireless receivers. Optimal maximum-likelihood (Max-L) detection delivers the best performance. However, its exponential complexity is prohibitive, while linear schemes such as zero-forcing (ZF) and minimum mean square error (MMSE) are computationally attractive yet suffer from poor performance. Fully learned detectors improve robustness but introduce substantial parameter counts and computational complexity. Building on prior work on partial learning (PL), this thesis contributes a unified detection framework based on PL that addresses these trade-offs by applying learning only where it yields the most benefits: a subset of the weakest symbol streams, with the remaining streams detected using low-complexity linear detection. The first part of the thesis designs a soft-output PL demapper implemented with a small fully connected neural network (FCNN) for quasi-static channels and embeds it into an iterative detection scheme. The inner MIMO detector produces log-likelihood ratios (LLRs) that are exchanged with an outer convolutional decoder. EXIT charts and decoding trajectories are used to analyze convergence. Across representative 2×2 and 4×4 quadrature phase-shift keying (QPSK) systems, the iterative PL (Iter-PL) technique closes most of the gap to iterative Max-L and full-learning detectors while operating at a fraction of their complexity. Operation counts are reported and related to the number of learning-assisted streams *d*, demonstrating an explicit performance versus complexity trade-off. The second part extends Iter-PL to time-varying channels while also considering channel state information (CSI) error. The same FCNN-based soft demapper is trained using CSI errors. Results show that Iter-PL retains its iterative gains under 5% CSI error and remains markedly superior to purely linear detection. An adaptive PL strategy is further introduced to select *d* based on the average received signal-to-noise ratio (SNR), thereby achieving a near-constant target bit error rate (BER) with reduced average complexity. The final part addresses scalability in dynamic multi-user uplinks. A graph neural network (GNN)–based PL detector is proposed, where an approximate message passing (AMP) frontend supplies soft symbols and variance estimates to the GNN. The GNN then detects only the d weakest users, while ZF detects the remaining users. By operating on user graphs, the model generalizes across changing activity masks without requiring retraining and maintains a low parameter count. Simulations over multiple activity patterns consistently confirm low BER and favorable performance–complexity trade-offs. Overall, the thesis demonstrates that partial learning enables near-optimal soft detection with clear and quantifiable reductions in complexity, and that GNN-based partial learning offers the same benefits in multi-user scenarios. The proposed technique provides a practical approach to scalable, low-latency MIMO detection, making it suitable for evolving wireless systems.5 0Item Restricted SMART AUTHENTICATION MECHANISMS: UTILIZING BIG DATA FOR DYNAMIC AND PERSONALIZED SECURITY SOLUTIONS(The University of Western Ontario, 2024-08-25) Abu Sulayman, Iman; Ouda, AbdelkaderThe exponential growth of digital data is revolutionizing information security and reshaping defense strategies against unknown threats. Organizations are amassing vast amounts of personal data, collectively termed ”Big Data,” from various sources like social media, online transactions, and GPS signals. This surge in data presents new research challenges in information security, prompting organizations to leverage big data analytics for valuable insights within secure environments. As a result, organizations are redesigning network security protocols to effectively manage the characteristics of big data. While traditional research focuses on authenticating users to protect big data environments, an alternative perspective emerges: utilizing big data to raise a new generation of authentication mechanisms to safeguard other environments. To this end, we developed novel security solutions that harness big data analytics to generate unique patterns of users’ dynamic behaviors, enabling the design of smart knowledge-based authentication mechanisms to fulfill the requirements of the new era of the digital world. These solutions include three main modules. ”Data Security-based Analytics (DSA),” the first module, develops an innovative data transformation model. The model adapts big data’s characteristics to relevant human dynamic measures. The second module, known as ”Big Data Driven Authentication (BDA),” includes the Security User Profiles (SUP) creation model, which is responsible for identifying patterns in DSA’s output and then uses said patterns to detect legitimate but anomalous activity from the user and assemble a security profile about the user. BDA also includes another model, known as Just-in-time Human Dynamics-Based Authentication Engine (JitHDA), which uses the user’s security profiles to dynamically create secure challenge questions in real-time that derive from the user’s recent behavior. The third module describes the development of a novel “Big Data-Driven Authentication as a Service (AUTHaaS)” model. AUTHaaS is an authentication mechanism that is powered by SUP and JitHDA technologies to offer authentication services on the cloud. Another model in AUTHaaS is ”iAuth,” which is an integration framework for authentication services. We developed this model to offer a unified interface that enables collaboration and interoperability among various AUTHaaS service providers. Additionally, we have developed an algorithm-based data generation (ADG) engine that is capable of processing synthetic user data. We designed ADG to accommodate dual-mode user behavioral data, encompassing both normal and abnormal instances. More importantly, the engine does not necessitate an initial dataset or data distribution and serves as the dataset source for the DSA model as it generates data from five different application domains.12 0Item Restricted Computational intelligence approaches applied to various domains(Saudi Digital Library, 2023-03-04) Alibrahim, Hussain; Ludwig, SimoneOver the past decade, machine learning has revolutionized a wide range of fields, from self-driving cars to speech recognition, web search, and even the human genome. However, the success of machine learning algorithms depends on a thorough understanding of the problem, mechanisms, properties, and constraints. This dissertation explores various aspects of machine learning, including hyperparameter optimization, nature-inspired algorithms for semi-supervised learning, image encryption using Particle Swarm Optimization with a logistic map and image originality. In the first chapter, three models - Genetic Algorithm, Grid Search, and Bayesian Optimization - are compared to improve classification accuracy for neural network models. The objective is to build a neural network model with a set of hyperparameters that can improve classification accuracy for data mining tasks, which aim to discover hidden relationships between input and output data to predict accurate outcomes for new data. The second chapter focuses on using nature-inspired algorithms, such as Particle Swarm Optimization (PSO) and Anti Bee Colony (ABC), to correctly cluster unlabelled data in semi-supervised learning problems. Two hybrid versions of K-means clustering, one with PSO and the other with ABC, are developed. The third chapter uses PSO to develop an image encryption algorithm using the logistic map to aid in the encryption process. The optimization problem is formulated by converting the image encryption problem into an optimization problem. In the final chapter, a new algorithm is developed using different techniques such as classification, optimization, and image analysis to detect whether an image is original or has been edited and modified. Overall, this dissertation investigates a variety of machine learning techniques and their practical applications across numerous fields. The techniques have the potential to be applied in diverse areas, such as biology, meteorology, healthcare, and finance.25 0Item Restricted DEEP LEARNING APPROACH TO LARGE-SCALE SYSTEMS(2023) Altamimi, Abdulelah; Lagoa, ConstantinoThe significance of large-scale systems has increased recently due to the growth in data and the number of users. The computational cost of analyzing these high-dimensional systems due to the curse of dimensionality raises the urge for developing efficient approaches. Deep learning methods have the capability and scalability to process high-volume data with significantly lower computational complexity. In this work, deep learning algorithms are utilized to solve large-scale systems in different applications. We design and solve high-dimensional systems using tractable algorithms. In particular, the deep reinforcement learning method and deep neural network are employed in our work in maximizing problems and classification problems, respectively. Comparisons with conventional algorithms are performed for validation purposes. Moreover, this work proposes an approach to exploiting the knowledge of the physical structure of plants inspired by deep learning algorithms. An application in the forest management field considered in this work is a large-scale forest model for wildfire mitigation. A high-dimensional forest model is designed in the Markov decision process framework. The model includes the probability of wildfire occurrence in a large number of stands. The probability of wildfire in each stand is a function of wind direction, flammability, and the stand's timber volume. Wildfire reduction is achieved by maximizing the timber volume in the forest through management actions. A deep reinforcement learning approach, i.e., the actor-critic algorithm, is used to solve the Markov decision process and propose management policies. Furthermore, the performances of conventional Markov decision process solutions, i.e., the value iteration algorithm and the genetic algorithm, are compared to the proposed approach. It outperforms these algorithms in terms of the value of the timber volume and the computational cost. Another interesting application considered in this thesis is fast stochastic predictive control. In the proposed approach, the computational complexity of solving stochastic predictive control is significantly reduced using deep learning. In particular, the number of constraints in the sampled method is reduced to the minimal set required to solve the optimization problem. Determining these constraints,i.e., the policies, is considered a classification problem to be solved using a neural network. The small number of constraints and the solvable quadratic optimization problem introduced by the sampled method result in a fast stochastic model predictive control. In this thesis, we also propose an approach to exploiting the prior knowledge of the physically interconnected systems in the parameter estimation domain. Unlike the physics-informed neural network, the proposed approach can estimate the parameters for every system in the interconnection. It has a general form that can be applied to any system as well as an objective function. We also combine the case of prior knowledge of system function with the case of the unavailability of this information. The Fourier series approximation method is used when knowledge of system functions is not available. The first-order gradient descent algorithm is considered to minimize the estimation error in the objective function. For that, we provide a systematic way to compute the gradients of the objective function. Using several versions of the gradient descent algorithm, the proposed solution shows promising results in the estimation of the system parameters.38 0