Computational intelligence approaches applied to various domains

dc.contributor.advisorLudwig, Simone
dc.contributor.authorAlibrahim, Hussain
dc.date.accessioned2023-08-21T06:36:05Z
dc.date.available2023-08-21T06:36:05Z
dc.date.issued2023-03-04
dc.description.abstractOver 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.
dc.format.extent93
dc.identifier.urihttps://hdl.handle.net/20.500.14154/68936
dc.language.isoen_US
dc.publisherSaudi Digital Library
dc.subjectMachine Learning
dc.subjectNeural Network
dc.subjectoptimization
dc.subjectimage processing
dc.titleComputational intelligence approaches applied to various domains
dc.typeThesis
sdl.degree.departmentDepartment of Computer Science
sdl.degree.disciplineComputer Science
sdl.degree.grantorNorth Dakota State University
sdl.degree.nameDoctor of Philosophy
Files
Collections