SACM - United States of America
Permanent URI for this collectionhttps://drepo.sdl.edu.sa/handle/20.500.14154/9668
Browse
2 results
Search Results
Item Restricted DEEP LEARNING APPROACHES FOR OBJECT TRACKING AND MOTION ESTIMATION OF ULTRASOUND IMAGING SEQUENCES(Saudi Digital Library, 2023) Alshahrani, Mohammed; Almekkawy, MohamedIn recent decades, object tracking and motion estimation in medical imaging have gained importance. It is a powerful tool that can be used to improve diagnostic accuracy and therapy efficiency. This importance has led researchers to search for faster and more accurate algorithms for object tracking. Different approaches have been used to perform object tracking, such as object detection, motion estimation, and similarity matching, which are the focus of this study. Different avenues can be used to address similarity matching. First, the classical method, which takes an object and searches for a similar object in the subsequent frame (because it is an object tracking in a video sequence) by examining all the sub-windows in the subsequent frame and measuring a cost function between the reference object and the sub-window. This approach is inefficient and cannot achieve real-time tracking. The deep learning method for similarity matching utilizes twin convolutional networks that produce a feature map that is later combined using a correlation layer. This layer provides a score map that points to a high-similarity area. This study examined and developed object tracking algorithms to track objects of interest in the human liver using a correlation filter-based neural network (CFNet). The dataset used in this study was CLUST-2D, which was provided by the Swiss Federal Institute of Technology in Zürich (ETH). It contains approximately 96 ultrasound sequences of the liver from different patients. Three versions of the CFNet network were tested in this study. First, baseline-CFNet was used for training. Baseline-CFNet struggled to track objects under significant displacements and deformations. To address this limitation of the baseline-CFNet, a second version was developed. Advanced-CFNet is the second version of CFNet implemented in this study. This is the main contribution of this study. This version incorporates a dynamic template update and motion prediction modules, which improve object tracking by preventing tracker drift and maintaining the template from being polluted with inappropriate appearances of the tracked object. The third version implemented in this study is Kalman-CFNet, which utilizes a linear Kalman filter to estimate an object's motion and enhance its robustness against unexpected motions. The comparative analysis demonstrated the superiority of Advanced-CFNet, as it achieved lower root mean square error (RMSE) values than the other methods, particularly in challenging scenarios. These findings highlight the effectiveness of the advanced CFNet for object tracking in liver ultrasound imaging.13 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.12 0