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 Modeling, Optimization, and Characterization for Choke Horn Antennas(University of Arkansas, 2024) Alquaydheb, Ibrahim Nasser I; El-Ghazaly, Samir M.This dissertation presents a comprehensive study focusing on the modeling, optimization, and characterization of choke horn antennas (CHAs). An analytical model designed to capture the parameters of CHA and derive the total radiated fields from the choke and waveguide elements is primarily focused on in this work. Compared to the use of simulation software, such as ANSYS HFSS (High Frequency Structure Simulator) or CST Studio, which employs numerical methods to simulate and calculate antenna performance, numerous advantages are offered by the analytical model. Analytical models provide deeper insight into electromagnetic interactions and the principles governing antenna behavior, leading to a better understanding of antenna operations and allowing for the prediction of antenna performance without the need for extensive optimization sweeps commonly used in numerical methods. Moreover, in terms of computational resources, analytical solutions can be more efficient. Substantial computational power and time, especially for complex models or fine resolution, are required by numerical methods and simulations, whereas results are often produced more quickly and with less demand on computing resources by analytical models. The first modeling approach that was explored incorporated the application of the Geometrical Theory of Diffraction (GTD), which extends Geometrical Optics principles to include diffraction alongside direct, reflected, and refracted waves. The curved edges of the choke were simplified into wedges, which facilitated the application of GTD. Additionally, the calibration of the GTD analytical model against simulation results, through the adjustment of constants derived from waveguide far-field components, established an accurate comparison with ANSYS HFSS simulations, validating the GTD approach and revealing an excellent agreement between the model and simulation data. Another modeling technique is presented for a single and double choke, which leverages the electrical current distribution of the parasitic elements to obtain the total radiated fields. The electrical current distribution of the choke will be simulated using software (the empirical part) and then imported into a derived mathematical formulation (the analytical part), resulting in a hybrid model. The electric and magnetic fields, which are excited directly from the distribution of the source currents, will be calculated through vector potentials, and the analysis will be simplified by discretizing the current distribution and employing Riemann sums for field approximation. The results of the model will be validated against ANSYS HFSS simulations which demonstrated significant computational speed improvements over conventional methods, enabling rapid design iterations and optimizations, thereby confirming its potential to enhance antenna design processes. Finally, a novel rectangular choke horn antenna was designed and analyzed using the hybrid method. The geometry of the antenna’s feed removes the need for rectangular-to-circular waveguide transitions, successfully tackling the issues of mode conversion and the possible compromise of signal integrity caused by imperfections in transitions. Gradient boosting and neural network algorithms were used to predict the current distributions and antenna performance values. The antenna was fabricated, and its radiation patterns were measured to validate the model and simulation results, which showed excellent agreement.31 0Item Restricted Sketch compression(University of Surre, 2023-09) Alsadoun, Hadeel Mohammed; song, Yi-Zhe; Ashcroft, AlexanderIn the rapidly evolving field of digital art and animation, traditional sketching techniques often rely on pixel-based methods, leading to less meaningful representations. This dissertation aims to transform this paradigm by rigorously investigating the efficacy of autoencoders for vector sketch compression. We conducted experiments using two distinct neural network architectures: Long Short-Term Memory (LSTM) and Transformer-based autoencoders. The Transformer model, which has significantly impacted the field of sequence-to-sequence tasks, especially in natural language processing, serves as a focal point of our study. Our experiment aims to answer a compelling question: Can these impressive results be replicated in the domain of vector sketch compression? The answer is a resounding yes. The Transformer model not only excelled in reconstructing sketches but also simplified the strokes and enhanced the overall quality of the sketch, achieving an impressive 85.03% classification accuracy. The LSTM model, known for its ability to capture temporal dependencies, served as our baseline, achieving a classification accuracy of 56.139% on a pre-trained classifier. Our findings strongly advocate for the adoption of Transformer-based models in vector sketch compression, offering a more compact and semantically rich representation. The LSTM model’s respectable performance also suggests its potential utility in less complex scenarios. Overall, this study opens new avenues for research in digital art, particularly in optimizing Transformer architectures for sketch compression.12 0Item Restricted Utilising Technical Analysis, Commodities Data, and Market Indices to Predict Stock Price Movements with Deep Learning(Cardiff University, 2024) Aloraini, Osama Mohammed A; Sun, XianfangThis study investigates the efficacy of deep learning models, specifically Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN), for forecasting stock price movements in the U.S. stock market. The dataset used includes 133 stocks across 19 different sectors and covers the period from 2010 to 2023. Moreover, to enrich the dataset, eleven technical indicators and their corresponding trading strategies, represented as vectors, were integrated along with market indices and commodities data. Consequently, various experiments were conducted to assess the effectiveness of different feature combinations. The findings reveal that the CNN model outperforms the LSTM model in both accuracy and profitability, achieving the highest accuracy of 59.7%. Furthermore, models demonstrated an ability to identify significant trend-changing points in stock price movements. Another finding shows that translating trading strategies into vector form plays a critical role in enhancing the performance of both models. However, it was observed that incorporating external features like market indices and commodities data led to model overfitting. Conversely, relying only on stock-specific features triggered a risk of model underfitting.Item Restricted Applications of Hyper-parameter Optimisations for Static Malware Detection(Saudi Digital Library, 2023-05-30) ALgorain, Fahad; Clark, JohnMalware detection is a major security concern and a great deal of academic and commercial research and development is directed at it. Machine Learning is a natural technology to harness for malware detection and many researchers have investigated its use. However, drawing comparisons between different techniques is a fraught affair. For example, the performance of ML algorithms often depends significantly on parametric choices, so the question arises as to what parameter choices are optimal. In this thesis, we investigate the use of a variety of ML algorithms for building malware classifiers and also how best to tune the parameters of those algorithms – a process generally known as hyper-parameter optimisation (HPO). Firstly, we examine the effects of some simple (model-free) ways of parameter tuning together with a state-of-the-art Bayesian model-building approach. We demonstrate that optimal parameter choices may differ significantly from default choices and argue that hyper-parameter optimisation should be adopted as a ‘formal outer loop’ in the research and development of malware detection systems. Secondly, we investigate the use of covering arrays (combinatorial testing) as a way to combat the curse of dimensionality in Gird Search. Four ML techniques were used: Random Forests, xgboost, Light GBM and Decision Trees. cAgen (a tool that is used for combinatorial testing) is shown to be capable of generating high-performing subsets of the full parameter grid of Grid Search and so provides a rigorous but highly efficient means of performing HPO. This may be regarded as a ‘design of experiments’ approach. Thirdly, Evolutionary algorithms (EAs) were used to enhance machine learning classifier accuracy. Six traditional machine learning techniques baseline accuracy is recorded. Two evolutionary algorithm frameworks Tree-Based Pipeline Optimization Tool (TPOT) and Distributed Evolutionary Algorithms in Python (Deap) are compared. Deap shows very promising results for our malware detection problem. Fourthly, we compare the use of Grid Search and covering arrays for tuning the hyper-parameters of Neural Networks. Several major hyper-parameters were studied with various values and results. We achieve significant improvements over the benchmark model. Our work is carried out using EMBER, a major published malware benchmark dataset of Windows Portable Execution (PE) metadata samples, and a smaller dataset from kaggle.com (also comprising of Windows Portable Execution metadata). Overall, we conclude that HPO is an essential part of credible evaluations of ML-based malware detection models. We also demonstrate that high-performing hyper-parameter values can be found by HPO and that these can be found efficiently.