Computer Engineering Commons^™

Iraqi’S Car License Plate Recognition Based On Deep Learning, Mushreq Abdulhussain Shuriji, Husam Al-Behadili, Hadel A. Hussain

Iraqi Journal for Computer Science and Mathematics

Vehicle license plate recognition is essential due to the rising number of operational cars, which leads to an increasing difficulty of this task even for humans. Systems for car license recognition normally consist of two branch systems, namely, license plate recognition and license plate detection. The aim of the detection part is to pinpoint the car and the position of its license plate, while the objective of the recognition part is to recognize characters on that plate. In this work, the emphasis is on Arabic car license plates. In this category of plates, there are three lines containing numerals and …

Retracted: High-Performance System For Predicting Icu Patient Durations Using Artificial Neural Networks With Transfer Learning, Mahmood. K. Awsaj, Yousif Al Mashhadany, Lamia Chaarifourati

Iraqi Journal for Computer Science and Mathematics

In the wake of disease outbreaks such as COVID-19, real-time health monitoring and prediction systems have become essential for ensuring effective patient care. These systems rely on sensors to monitor biometric parameters such as blood pressure, body temperature, and heart rate, providing continuous and accurate data that medical staff cannot collect manually around the clock. This study presents a robust framework for managing Intensive Care Unit (ICU) patients using Artificial Neural Networks (ANN) with Transfer Learning. The data is analyzed across five distinct time windows, each representing a period of ICU stay based on vital signs and medical test results. …

Fourier-Feature Mlp Toolkit For Gpu-Accelerated Cardiac-Mri 4dcmr Strain Analysis, Aarnav T. Sabale, Marco A. Prado, Craig J. Goergen

Discovery Undergraduate Interdisciplinary Research Internship

This paper explores the embedding of a Fourier-Feature—enhanced multiplayer perceptron(MLP-FEE) at the heart of a newly refactored python workflow for four-dimensional cardiac-MRI strain quantification demonstrating how a single, compact network can outperform traditional convolution and spline-based methods. The original code, capable of orientation normalization, displacement tracking, and finite-difference strain computation, has been translated and consolidated into pytorch. By injecting sinusoidal positional encodings at the network’s input layer supplied a rich set of high-frequency basis functions hence enabling multilayer MLP to resolve gradients that cubic splines and conventional CNNs typically blur or struggle with. Profiling on an Apple-silicon GPU shows interactive …

Performance Evaluation Of Delay-Aware Packet Delivery In Wireless Devices, Alvin Lee

Computer Science and Engineering Master's Theses

As wireless networks, such as WiFi, have evolved from a convenient alternative to wired internet into the backbone of modern digital life, with approximately 19.5 billion devices deployed in 2023, the emergence of Virtual Reality (VR) and Augmented Reality (AR) applications has introduced unprecedented Quality of Service (QoS) demands that challenge existing wireless capabilities. While recent wireless standards have largely addressed throughput limitations, achieving consistent low-latency performance remains a significant challenge.

This thesis focuses on the implementation and performance evaluation of existing solutions to latency bottlenecks in wireless networks, and their impacts on User Datagram Protocol (UDP) and Transmission Control …

Enhancing Credit Path Planning With Llm-Based Multi-Agent Systems, Sahar Yarmohammadtoosky

Dissertations

This work explores applying Multi-Agent (MA) Large Language Models (LLMs) to enhance credit card management, an underexplored area for their multi-step reasoning capabilities. Focusing on Equifax’s Optimal Path™ model [1]—a personalized solution for credit score optimization—the study addresses two key challenges: first, designing a natural language interface for financial credit models to improve accessibility and aid customer decision-making, and second, enhancing the reliability and real-world applicability of complex financial models prone to generating invalid or unfeasible recommendations caused by a lack of practical interpretability and susceptibility to edge cases. To tackle these, we propose and evaluate various MA designs, including …

Development Of A Control System For An 8-Dof Quadrupedal Robotic Research Platform, Jack Butler

Master's Theses

Quadrupedal robots offer a versatile locomotion option that can extend the operating space of a robot into uneven terrains. However, controlling these systems presents significant challenges due to nonlinearities introduced by various factors.

In this thesis, model-predictive control (MPC) is applied to an 8-DOF legged robot developed by Cal Poly’s Legged Robotics group. The MPC framework employs a lumped rigid-body model that treats the robot as a single rigid body with forces applied directly at the foot contact points. The controller is developed within the ROS2 environment, with integration of state estimation and gait-pattern generation, to provide maximum modularity and …

Real-Time Fiducial Marker Based Localization For Autonomous Unmanned Aerial Vehicle Navigation, Sourav Raxit

LSU New Orleans Theses and Dissertations

By harnessing fiducial markers as visual landmarks in the environment, Unmanned Aerial Vehicles (UAVs) can rapidly build precise maps and navigate spaces safely and efficiently, unlocking their potential for fluent collaboration and coexistence with humans. Existing fiducial marker methods rely on handcrafted feature extraction, which sacrifices accuracy. On the other hand, some deep learning pipelines for marker detection fail to meet real-time runtime constraints crucial for navigation applications. In this work, I propose YoloTag- a real-time fiducial marker-based localization system. YoloTag uses a lightweight YOLO v8 object detector to accurately detect fiducial markers in images while meeting the runtime constraints …

Reinforcement Learning And Virtual Human Animation: A Novel Approach To Data-Driven Animation, Portraying Dynamic, Flexible Human-Like Behaviours, Vihanga Gamage

Dissertations

Virtual characters require animation capable of portraying dynamic, context-sensitive human-like behaviours. Several approaches to generating such animation have been developed, but each carries limitations. Motion capture can produce high-fidelity animation but is expensive and ill-suited to systems that must respond in real time. Physics-based reinforcement learning (RL) enables flexible, dynamic behaviour portrayal, yet relies on simulation feedback signals that are unavailable for social gestures. Supervised approaches can learn social behaviours from motion capture data but yield agents with limited flexibility and generalisation.

This thesis presents RLAnimate, a model-based, data-driven RL framework for character animation that enables a single agent to …

Traffic Prediction For Research And Education Networks: Anomaly-Aware Deep Learning And Benchmarking, Mohammad Arafath Uddin Shariff

School of Computing: Dissertations, Theses, and Student Research

Research and Education Networks (RENs) and High-Performance Computing (HPC) environments are critical infrastructures for modern scientific discovery, demanding sustained high-throughput and low-latency data transfers. Unlike commercial networks, RENs exhibit unique traffic characteristics, including predominant “elephant flows,” inherent burstiness, and complex temporal-spatial dynamics often decoupled from human-driven cycles. Traditional traffic forecasting methods, tailored for commercial Wide Area Networks (WANs), consistently fail to capture these distinct REN dynamics, leading to inefficient resource management and potential impediments to scientific progress.

This thesis addresses this critical gap by developing and validating a robust, scalable, and anomaly-aware traffic forecasting framework specifically tailored for REN/HPC networks. …

Machine Learning Based Medical Ultrasound Image Classification And Grad-Cam Interpretation, Victoria C. Hemphill

All Theses

This work takes a step in creating a diagnostic tool for the classification decision process of Achilles tendinopathy using ultrasound images. An attention-based multiple instance learning model is developed to classify the images. Typically, doctors capture multiple ultrasound images of the Achilles tendon during a study to determine a complete diagnosis. Multiple instance models adopt this behavior by providing a single label for a set of instances (images). The images are grouped into ”bags” at the study level and passed into the model. The MIL model then uses its attention property to assign an importance score to each image to …

Visor-Zt: A Visibility, Simulation, And Operational Resilience Framework For Zero Trust Security In Ros 2, Noah Tinker

All Theses

Robotic systems are becoming more and more prevalent in modern society, with Robot Operating System 2 (ROS 2) being the dominant operating system for these implementations. Its popularity can be attributed to its design, which is purpose-built for distributed systems and asynchronous communications. However, ROS 2 security is static and therefore less capable of responding to contemporary threats and network behavior. This becomes a greater issue when considering its applications in the military and defense sectors, where security is of the highest importance. In recent years, the U.S. Department of Defense (DoD) has implemented zero trust (ZT) security based on …

Intelligent Multi-Layer Optical Network Design And Network Softwarization, Boyang Hu

Dissertations and Doctoral Documents, University of Nebraska-Lincoln, 2023–

The growing demand for high-capacity, low-latency services has placed significant pressure on the design and operation of optical transport networks. Multi-layer optical network design—which coordinates the physical layer with higher-layer protocols—has emerged as a critical strategy to enhance resource efficiency, service flexibility, and fault resilience. Enabled by advancements in software-defined networking (SDN) and network softwarization, intelligent multi-layer architectures allow for adaptive, cross-layer control of routing, grooming, and protection mechanisms, ultimately reducing both capital and operational expenditures.

This dissertation investigates the intelligent design and simulation of multi-layer optical networks through the integration of SDN, machine learning, and high-fidelity physical-layer modeling. We …

Enhancing Emotional Accuracy And Behavioral Novelty In Robot Behaviors: A Generative-Discriminative Approach, Rista Baral

Boise State University Theses and Dissertations

Recent advancements in language modeling have improved robotic emotion expressiveness, yet several challenges remain. Many existing robotic expression models rely on fixed rules and static frameworks, which limit their ability to capture the dynamic nature of emotional expression. Additionally, these systems often struggle to balance emotional accuracy with generating novel and varied behaviors. These limitations underscore the need for method capable of delivering both emotionally accurate and diverse robot behaviors.

In this thesis, we addresses these challenges by introducing a new framework for expressive behavior generation in robots. We develop a generative model that generates robot behavior sequences that align …

Low-Power Hardware-Based Real-Time Cervical Spine Localization Via Image Processing, Patricia Angela R. Abu, Chao-Shin Liu, Sung-Hsin Tsai, Po Lin Huang, Hong-Kai Wang, Shih Wei Chung, Chiung-An Chen, Shih-Lun Chen, Sze-Teng Liong, Tsung-Yi Chen

Department of Information Systems & Computer Science Faculty Publications

With the growing prevalence of cervical spine degeneration in the aging population, there is an urgent need for accurate and real-time cervical image analysis to assist in preliminary evaluations during neurosurgical outpatient visits. This study suggests a hard-ware-based real-time cervical spine localization system that uses image preprocessing algorithms to address this need. The system can quickly finish image enhancement and greatly speed up the localization process by turning preprocessing steps like median filtering and binarization into hardware modules. With a power consumption as low as 4.859 mW, the proposed hardware-based median filter demonstrates over 60% reduction in power and 35% …

Multimedia Forensics: Identification And Verification Of Source Camera, Vehicle Speed Estimation, And Deepfakes Detection, Jiajun Jiang

Electrical & Computer Engineering Theses & Dissertations

This dissertation advances multimedia forensics by addressing three critical research areas that enhance the authenticity verification and analysis of digital media. Multimedia forensics, which encompasses techniques for examining images, videos, audio, and text, faces increasing challenges due to sophisticated editing tools and massive data volumes. In the first study, a fast source camera identification and verification method based on PRNU analysis is proposed for video forensic investigations. By integrating camera rolling and I-frame analysis, this approach achieves a processing speed improvement of at least 15 times over conventional frame-by-frame methods while reducing false positives. The second study focuses on vehicular …

Computational Modeling For Automatic Superconducting Cavity Fault Prediction And Classification Using Time Series Signals, Md Monibor Rahman

Electrical & Computer Engineering Theses & Dissertations

Processing multivariate time series signals collected from sensor networks is challenging because of complex temporal dependencies and non-stationarity. With the advent of artificial intelligence (AI) like machine learning and deep learning, it has become possible to process sensor-driven time series data more effectively than traditional statistical methods.

This dissertation aims to develop machine learning and deep learning models to address machine fault diagnosis using multivariate time series signals collected from the Continuous Electron Beam Accelerator Facility (CEBAF) at Jefferson Lab. The first goal of the proposed work is to develop deep learning–based classification models and an unsupervised fault clustering approach …

Succinctness Meets Transparency A Linking Framework Combining Hyrax And Kzg, And Its Applications, Argha Sardar

Master’s Dissertations

The thesis begins by introducing the concept of zero knowledge and exploring its various paradigms. It then focuses on a interesting problem: the construction of linking proofs. Chap- ter 2 addresses the challenge of binding two distinct polynomial commitment schemes so that they are consistent at a common evaluation point. The chapter further introduces a method for equating two different polynomials with different domains using an affine line construction. By applying certain optimizations to the bulletproofs protocol, the work achieves a reduction in both the prover’s time and the number of rounds required for proving a large committed inner product. …

Internet Of Things And Modern Digital Evidence Collection, Muhammad T. Haider

Student Theses

The ever-evolving landscape of technology and its innovations are populating our houses, streets and all kinds of industries. The use of smart devices is booming from most developed nations to underdeveloped countries. The complications which come with the use of the Internet of Things has been an active discussion for the past many years. If we look around in a room of 30 people, we will most likely find double the amount of IoT devices than the people in that room. All of those devices are connected to the Internet, and are communicating with data servers across the world. The …

Multiple View Neural Regression Of A Facial Shape Model, Xiang Li

All Dissertations

Creating re-topologized 3D facial meshes is a critical step in high-quality facial animation pipelines, yet it remains a labor-intensive and time-consuming task. Traditional approaches typically rely on multiview stereo reconstruction and specialized photometric environments to acquire accurate geometric and reflectance data under controlled conditions. This dissertation presents work toward more efficient capture of production-ready meshes including (1) developmental aspects of VarIS, a custom-designed light sphere capable of capturing high-resolution stereo geometry and reflectance maps—including diffuse, specular, and normal components under programmable illumination; (2) a study of the effects of camera parameters on automatic 2D and 3D landmarking methods, (3) methods …

Effects Of Lossy Compression Data On Machine Learning Models, Max H. Faykus Iii

All Dissertations

Machine learning is a fundamental tool that is incorporated in every field across academia and other industries. Due to the large amount of data needed for training machine learning models, lossy compression plays a crucial role in storing data. Machine learning involves the use of algorithms and models to learn patterns in data. This allows the AI to make decisions without specific programming. On the other hand, compression utilizes encoding and decoding techniques to reduce the size of files. Compression is either lossy or lossless, lossy causes a loss of data while lossless preserves the data. This dissertation will explore …

Digital Twin For Real-Time Monitoring And Control Of Conveyor Systems Using Flexsim, Ai And Plc Integration, Jose Francisco Arvizu Astorga

Open Access Theses & Dissertations

Modern manufacturing is making significant advancements by innovating and automating most processes. However, a major challenge remains: systems are constantly evolving and becoming more complex to analyze. Fortunately, a powerful tool can help, Digital Twin (DT) technology. This technology enables the analysis and optimization of processes like never before. A Digital Twin is a real-time virtual model of a physical system that continuously up dates with live data. One of its greatest features is the ability to create infinite scenarios, allowing hundreds of configurations to be tested virtually, risk-free, and without making any real-world changes that could disrupt ongoing operations. …

Input Structure Based Optimization For Privacy Preserving Ai Systems, Feng Yizhou

Electrical & Computer Engineering Theses & Dissertations

As Artificial Intelligence (AI) systems become increasingly integrated into critical domains, ensuring privacy-preserving model design and system deployment has become a pressing priority. Safeguarding both sensitive user data and proprietary model parameters is critical throughout the AI model and system, from data acquisition and pre-processing to model inference and deployment. However, existing privacy-preserving frameworks face several limitations, including fragmented data ownership, incomplete protection across system stages, substantial computational overhead, and poor scalability to modern architectures such as large language models. This dissertation explores a unifying optimization strategy centered on input structure design to address these challenges. The core idea is …

Human Activity Recognition And Identification Driven Automated Deep Learning For Time-Series Classification, Justin Alan Gamble

Engineering Management & Systems Engineering Theses & Dissertations

The growing emphasis on Digital Engineering (DE) within the U.S. Department of Defense (DoD) demands advanced methods for leveraging vast time-series data generated by sensor-rich environments. Deep learning models offer promising solutions for complex timeseries classification tasks, however their design and optimization remain highly resource intensive, requiring specialized expertise. This dissertation addresses this challenge by developing and evaluating an Automated Machine Learning (AutoML) framework specifically tailored for the time-series classification task of Human Activity Recognition and Identification (HARI).

A systematic investigation was conducted using the Design Science Research Methodology (DSRM) comparing traditional search strategies of grid search and random search …

Genwriter: Reducing Gender Cues In Biographies Through Text Rewriting, Shweta Soundararajan, Sarah Jane Delany

Conference papers

Gendered language is the use of words that indicate an individual’s gender. Though useful in certain context, it can reinforce gender stereotypes and introduce bias, particularly in machine learning models used for tasks like occupation classification. When textual content such as biographies contains gender cues, it can influence model predictions, leading to unfair outcomes such as reduced hiring opportunities for women. To address this issue, we propose GenWriter, an approach that integrates Case-Based Reasoning (CBR) with Large Language Models (LLMs) to rewrite biographies in a way that obfuscates gender while preserving semantic content. We evaluate GenWriter by measuring gender bias …

Designing A User-Centered Bias System To Enhance Media Literacy And Factual Accuracy, Anjali Majan

Theses and Dissertations

In an era of rapid news consumption, readers often struggle to detect bias and misinformation. This study examined whether interface design can support more critical engagement with news. We developed a progressive disclosure interface that encouraged users to reflect as they read by gradually revealing bias and factual cues. Participants were assigned to either Progressive Disclosure or Ground News. The experiment involved two phases. In the intervention phase, participants used an interface with support features. In the assessment phase, they completed tasks without the tool. We evaluated their performance using five measures: bias recognition accuracy, bias shift, factuality judgment, overlap …

How Developers Use Type-System Related Programming Language Features, Samuel W. Flint

School of Computing: Dissertations, Theses, and Student Research

Optional type annotations are a popular feature of programming languages that allow developers to omit explicit type information in code while, in some cases, retaining many of the benefits of static typing, such as in-code documentation, improved detection of type errors, or enforcement of code properties. However, how developers use and understand optional type annotations is not clear. The focus of this dissertation is to understand the use and comprehension of optional type annotations.

Optional type annotations are examined through four lenses: first, by examining the evolution of usage in a statically typed programming language (Kotlin, the default language for …

Low-Level Memory Attacks On Edge Assisted Robotic Applications, William Arnold

Master of Engineering Theses

This thesis investigates how low-level memory faults can undermine edge-assisted robotic systems that rely on memory optimization. As robots are utilized in real world applications, the ability to operate safely and successfully in mission critical deployment becomes important. To help achieve these goals, developers are increasingly starting to place computation nodes at network edges to meet latency and reliability requirements. Edge nodes, however, are resource-constrained and resources conservation techniques such as Kernel Same-page Merging (KSM) are enabled to deduplicate identical pages across processes or virtual machines. This thesis shows that this optimization technique quietly widens the attack surface and can …

Multi-Material Cell Clipping On The Gpu, Melanie Cassidy Walsmith

Open Access Theses & Dissertations

The process of clipping a multi-material cell finds diverse applications across fields such as numerical simulations and computer graphics visualization. Computational fluid dynamics problem often combines multiple materials with different physical properties. The interfaces between those materials may be a part of the solution and evolve in time and can be non-aligned with the mesh. When volume conservation is crucial, interface reconstruction methods are used to approximate such material interfaces. They involve multiple steps, one of which is the process known as clipping. Clipping consists of intersecting and cutting a given cell with a material interface (represented by a line …

Advancing Real-World Implementation Of The Well Optimized Linear Finder (Wolf) High-Speed Atmospheric Turbulence Compensation Method, Timothy Evan Coon

Theses and Dissertations

This dissertation advances the real-world implementation of the Well Optimized Linear Finder (WOLF) method for high-speed Atmospheric Turbulence Compensation (ATC). Atmospheric turbulence introduces phase aberrations into optical wavefronts and degrades image quality in terrestrial imaging systems. Traditional phase diversity methods are computationally intensive and poorly suited to real-time operation. The WOLF method addresses these limitations through a novel, point-wise formulation of the optical transfer function (OTF) as a structured autocorrelation of the generalized pupil function (GPF). This formulation enables the estimation of phase aberrations at individual spatial coordinates with distributed computational complexity.

The research begins by developing a MATLAB-based simulation …

Applying Large Language Models For Surgical Case Length Prediction, Adhitya Ramamurthi, Bhabishya Neupane, Priya Deshpande, Ryan Hanson, Srujan Vegesna, Deborah Cray, Bradley H. Crotty, Melek Somai, Kellie R. Brown, Sachin S. Pawar, Bradley Taylor, Anai N. Kothari

Electrical and Computer Engineering Faculty Research and Publications

Importance Accurate prediction of surgical case duration is critical for operating room (OR) management, as inefficient scheduling can lead to reduced patient and surgeon satisfaction while incurring considerable financial costs.

Objective To evaluate the feasibility and accuracy of large language models (LLMs) in predicting surgical case length using unstructured clinical data compared to existing estimation methods.

Design, Setting, and Participants This was a retrospective study analyzing elective surgical cases performed between January 2017 and December 2023 at a single academic medical center and affiliated community hospital ORs. Analysis included 125493 eligible surgical cases, with 1950 used for LLM fine-tuning and …