Engineering Commons^™

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 …

Heat-Pipe-Based Thermal Management System Design For A 250-Kw Gan-Based Integrated Modular Motor Drive, Seyed Iman Hosseini Sabzevari, Salar Koushan, Armin Ebrahimian, Towhid Islam Chowdhury, Nathan Weise, Ayman El-Refaie

Electrical and Computer Engineering Faculty Research and Publications

Integrated modular motor drive (IMMD) is an effective approach for realizing high-efficiency, high-power-density, and fault-tolerant electric machines. However, designing an efficient thermal management system (TMS) for the motor drive becomes a challenge, particularly due to space constraints. This article presents the design of a TMS based on 3-mm heat pipes for a 250-kW IMMD intended for aviation applications. The power electronics module is simulated using PLECS software where an electrothermal analysis is conducted. A simplified thermal resistance model of the system is developed to estimate the die junction temperature of gallium nitride (GaN) semiconductors. The performance of the proposed TMS …

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 …

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 …

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 …

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 …

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 …

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 …

Retracted: Dynamics And Stability Analysis Of 8-Dimensional Hyperchaotic Systems: Study Of Lyapunov Exponents, Abdulsattar Abdullah Hamad, Nida Muhsin Ali, Muayyad Mahmood Khalil

Iraqi Journal for Computer Science and Mathematics

This research explores the complex dynamics of an 8D hyperchaotic system, focusing on its trajectory stability and behavior under various control parameters. By using numerical simulations, we investigate the relationship between the Lyapunov components and the stability of the system. It provides a quantitative measure of the chaos within the model of the matrix, whose derivation consists of the system's sensitivity to perturbation, simulating chaotic systems in high dimensions faces challenges such as high computational resource demands. Difficulty in ensuring numerical convergence and stability. The results highlight the profound impact of control parameters on the dynamic behavior of hyperchaotic systems. …

Corneal Elevation Maps Patterns Classification Using Correlation Method, Sura M. Ahmed, Nebras H. Ghaeb, Salman Yussof, Noor T. Al-Sharify, Husam Yahya Nser, Zainab T. Al-Sharify, Ong Hang See, Leong Yeng Weng

Iraqi Journal for Computer Science and Mathematics

The ophthalmologist uses various techniques to diagnose corneal abnormalities, including corneal topography and tomography devices. Currently generated color corneal elevation surface maps from topographic imaging devices are essential for detecting ocular diseases, while accurately classifying these maps to differentiate between different shapes remains an issue. This study aims to assess and compare parameters of the front and back corneal surface elevation map patterns of normal/abnormal corneas. Two hundred cases were randomly taken (100 normal and 100 abnormal) with a single normal reference image, and then an additional 25 cases were added later for the optimization process. The preprocessing of all …

Retracted: Comparative Study Based On Continuous Analysis Of Autism Spectrum Disorder Using Advanced Deep Learning With Model Interpretability Insights, Ayan Sar, Hussain Falih Mahdi, Sumit Aich, Pranav Singh, Tanupriya Choudhury

Iraqi Journal for Computer Science and Mathematics

Hysterical conversion has similar cognition and behaviours to those in the case of ASD; it is, therefore, complex when diagnosing and classifying the condition. The majority of employed diagnostic tests are cross-sectional and fail to describe the developmental and clinical features of ASD; for this reason, they are pretty inaccurate in the diagnosis of ASD and thus cause disparities in the efficiency of the therapeutic interventions used. The present study's research contribution is a new application of deep learning that aims to analyse the spectrum of ASD with gradient-based classifications. In this case, we use a DL model trained on …

Network Intelligence For Next-Generation Wireless Networks: Advancing Distribution And Coordination, Yonatan Melese Worku

Electrical and Computer Engineering ETDs

Next-generation wireless networks, encompassing 6G and beyond, face rigorous demands for ultra-low latency, ubiquitous connectivity, exceptionally high data rates, and robust security, necessitating innovative approaches to resource optimization and network protection. This dissertation proposes a pioneering framework that synergizes advanced methodologies—deep reinforcement learning, deep learning, blockchain, and multi-agent systems—to address these challenges. Distributed architectures, underpinned by AI-driven multi-agent systems, form the backbone of this framework, enabling seamless integration and intelligent orchestration across diverse domains. The research advances IoT-based systems leveraging machine learning for resource efficiency in healthcare applications, develops reinforcement learning-driven frameworks to optimize energy and coverage for Unmanned Aerial …

Exploring Immune System Through Computational Modeling: A Comprehensive Study Of Lymph Nodes And Immune Response Scaling, Vaccine Efficacy, And Large-Scale Extreme First Passage Time, Jannatul Ferdous

Computer Science ETDs

The adaptive immune response is a complex defense mechanism that develops over time to recognize and eliminate pathogens with remarkable precision and durability. This dissertation investigates the dynamics, scaling, and efficiency of the adaptive immune response through a synthesis of computational modeling, mathematical analysis, and agent-based simulations. First, we analyze the topology of the lymphatic network and investigate the T cell search time to find the lymph node that is containing the matching dendritic cell. Second we show how the scaling of lymph node number and volume with body mass, leads to scale-invariant search times for T cells locating antigen-bearing …

Isar Imaging Of Drone Swarms At 77 Ghz, Remzi̇ye Büşra Çoruk, Ali̇ Kara, Eli̇f Aydin

Turkish Journal of Electrical Engineering and Computer Sciences

The proliferation of easily available, internet-purchased drones, coupled with the emergence of coordinated drone swarms, poses a significant security threat for airspace. Detecting these swarms is crucial to prevent potential accidents, criminal misuse, and airspace disruptions. This paper proposes a novel inverse synthetic aperture radar (ISAR) imaging technique for high-resolution reconstruction of drone swarms at 77 GHz millimeter wave (mmWave) frequency, offering a valuable tool for military and defense anti-drone systems. The key parameters affecting down-range and cross-range resolution (0.05 m), ultimately enabling the generation of detailed ISAR images are discussed. Here, we create diverse scenarios encompassing various swarm formations, …

Magnetic Macro Pendulum Design And Real-Time Control Application: Simulation And Experiment, Hüseyi̇n Yildiz, Serdar Yilmaz, Yasemi̇n Poyraz Koçak, Erol Uzal

Turkish Journal of Electrical Engineering and Computer Sciences

Over the last decade, the number of studies in the field of magnetic micro robots has significantly increased due to expectations of performing microsurgery, drug delivery, and similar medical procedures. Magnetic micro robots have advantages over other types of micro robots in terms of having independent designs for rotor and stator structures. Magnetic micro robots can be controlled by magnetic fields and can be programmed to move in certain directions and to perform various functions. This paper implements the computer-aided real-time control of a single-arm micro-pendulum structure to (eventually) perform cell manipulation tasks. The mechanical structure, mathematical model, control circuit …

Adaptive Backstepping Control With Real-Time Fuzzy Logic Parameter Selection Of A Field- Oriented Control-Based Permanent Magnet Synchronous Motor Driver, Fati̇h Bayir, Erkan Zergeroğlu

Turkish Journal of Electrical Engineering and Computer Sciences

This study proposes an adaptive backstepping control approach integrated with a real-time fuzzy logic parameter selection algorithm to enhance the robustness and stability of a permanent magnet synchronous motor (PMSM) controller under parametric uncertainties and external disturbances. Although backstepping control performs well under varying disturbances, it must be supported by an adaptive control algorithm to effectively handle both variable disturbances and parameter uncertainties. Moreover, because the fixed parameters of the adaptive backstepping controller limit the dynamic performance of the velocity tracking loop, this study incorporates fuzzy logic control—a soft computing algorithm capable of real-time parameter adjustment—to achieve more robust outcomes. …

Excitation Of Synchronous Machine By Contactless Power Transfer - Review From The Perspective Of Electric Vehicles, Erhan Tuncel, Emi̇n Yildiriz

Turkish Journal of Electrical Engineering and Computer Sciences

Electrically excited synchronous machines (EESMs) are one of the best choices for propulsion motor appli cation in electric vehicles (EVs) due to their wide torque-speed characteristics. Moreover, the air gap flux density can be easily controlled by varying the excitation current. Despite these advantages, it is difficult to transfer the current required by the rotating excitation winding into the motor under conventional methods, so it is not widely used in EVs. In this study, the emerging literature on contactless power transfer methods is reviewed for applicability to an EESM that can operate as an EV propulsion motor. Design criteria such …

Optimization And Model Averaging Of Histogram-Based Place Cell Firing Rate Maps Using The Point Process Framework, Murat Okatan

Turkish Journal of Electrical Engineering and Computer Sciences

The firing rate of hippocampal place cells depends on the spatial position of the organism in an environment. This position dependence is often quantified by constructing spike-in-location and time-in-location histograms, the ratio of which yields a firing rate map. The purpose of this study is to present a new method for optimizing the spatial resolution of histogram-based firing rate maps. It is pointed out that histogram-based firing rate maps are conditional intensity functions of inhomogeneous Poisson process models of neural spike trains, and, as such, they can be optimized through model selection within the point process framework. The point process …

Rescon: Residual Consistency For Real-World Super-Resolution, Erdi̇ Saritaş, Hazim Kemal Ekenel

Turkish Journal of Electrical Engineering and Computer Sciences

Real-world super-resolution is a highly challenging problem in the field of computer vision. Besides enhancing image resolution and improving visual details, information loss due to complex real-world degradations is desired to be restored. One of the primary hardness of this problem is finding sufficiently large paired datasets for training. Researchers have developed techniques that generate synthetic low-resolution pairs using high-resolution images with a generative adversarial network-based degradation generator to address this issue. In these approaches, the degradation generator is trained by utilizing real-world low-resolution images as the target domain, generating a degraded low-resolution counterpart of the high-resolution input. However, in …

Adaptive Multi-Agent Reinforcement Learning For Electric Vehicle Charging Optimization Under Dynamic Traffic Conditions, Shaghayegh Rabbanian

LSU Master's Theses

Electric vehicle (EV) charging optimization is a critical challenge in sustainable transportation. This study focuses on three fundamental questions: (1) when is the best time to charge an EV, (2) where is the optimal charging location, and (3) how should charging be planned considering navigation and routing decisions. Our primary objective is to determine the optimal time and location for EV charging while accounting for key factors such as real-time traffic conditions, spatial distribution of charging stations, and EV-specific attributes such as state of charge (SOC), driving range, and efficiency. To develop a robust and adaptive EV charging recommendation system, …

Multi-Scale Color Correction And Contrast Enhancement Via Leaf In Wind Optimization For Improved Weld Defect Detection In Non- Destructive Testing, Senthil Anand N Mr

Theses and Dissertations

Image enhancement is an essential process in numerous fields, including industrial inspection, medical imaging, remote sensing, and photography, as it improves image quality for accurate analysis and interpretation. Among the advanced image enhancement techniques, Focused Super Resolution (FSR) with Self-Attention Single Candidate Optimizer-based Generative Adversarial Networks (GANs) is specifically designed for weld defect detection, while Advanced Image Enhancement through Multi-scale Color Correction and Contrast Stretching using Leaf in Wind Optimization focuses on enhancing the overall visual quality of images. Although both approaches aim to improve image quality, they differ significantly in their objectives and application areas. The FSR method concentrates …

Cost-Effective Automated Uhi Mapping With Ai: A Case Study Of A Scalable Framework For Climate Equity In San José, California, Martin Alvarez Lopez

Master's Theses

Urban areas experience the Urban Heat Island (UHI) effect, with higher temperatures than rural areas, disproportionately impacting low-income communities. Mapping UHIs is a process that usually requires significant amount of human resources, and is not scalable. The lack of accurate and detailed UHI maps makes it difficult for decision makers to design effective mitigation strategies. In this work we introduce a cost-effective, scalable, and universally applicable UHI mapping framework that leverages open-source data and AI-driven feature extraction from remote sensing imagery. Using various causative factors such as city characteristics, anthropogenic heat, city canyons, and meteorological variables, we create UHI maps …

Quantization On Graph Neural Networks For Image Classification, Rithik Reddy Katpally

Master's Theses

Quantization has become a key approach for reducing storage and computational demands of deep neural networks while maintaining high accuracy. Although 8-bit quantization is well-established for convolutional architectures such as ResNet50 and MobileNetV2, its application to graph-based vision models remains underexplored. In this work, we extend quantization-aware training to Vision Graph Neural Networks (ViGs) and conduct comparisons with quantized CNNs on the CIFAR-100 dataset. To ensure parity, all models have same training hyperparameters such as learning rate, batch size, optimizer, number of epochs. We used numerous techniques to preserve performance for low-bit precision. First, Pauta Quantization clips activation outliers based …

Stead: Spatio-Temporal Efficient Anomaly Detection For Time And Compute Sensitive Applications, Andrew Gao

Master's Theses

This paper presents a new method for anomaly detection in automated systems with time and compute sensitive requirements, with unparalleled efficiency. As these systems become increasingly popular, ensuring their safety has become more important than ever. Therefore, this paper focuses on how to quickly and effectively detect various anomalies in the aforementioned systems, with the goal of making them safer and more effective. Many detection systems have been developed with great success under spatial contexts; however, there is still significant room for improvement when it comes to temporal context. While there is substantial work regarding this task, there is minimal …

Using Facial Recognition For Selective Pose Detection, William J. Parker

Master's Theses

Pose detection involves locating and identifying key body points for all individuals within a frame. This enables the ability to convert the pose into a digital format, which can then be recorded and analyzed for a variety of purposes. Advancements in the field have already opened applications in areas such as digital fitness coaches, fall detection, and virtual reality. Existing approaches primarily focus on tracking all detected individuals, which limits the practical applications when attempting to analyze a single or specific subject when there are other people in frame. Previous work has discussed integrating identification, but these approaches use identification …

Quantum Algorithm Emulation Using Fpgas, Samuel Petruescu

Master's Theses

Field Programmable Gate Arrays (FPGAs) have been used in most of the physics sub-fields for various unique purposes. This includes particle physics, quantum optics, and, more recently, quantum computing. FPGAs boast many benefits over previous experimental and computational setups. They are versatile, easy to program, and cost-effective, leading to an understandable desire to incorporate them into the new field of quantum computing. While FPGAs have been used to help control the readout and control of physical qubits, they can also be a good tool for improving algorithm simulations, which is the focus of this paper. Different algorithms have different computational …

Sirilla: Predicting Traffic Flow Via Stacked Decentralized Federated Learning, Andrew Selvia

Master's Theses

Billions of people today rely on traffic predictions to optimize their travels. Digital mapping services deliver accurate predictions by learning from vast troves of historical data. Impressive as these systems are, their assumptions do not always apply. They depend on an endless flow of sensitive user data to a central authority, a stable Internet connection, and trustworthiness on both sides of the traditional client-server model. This thesis explores a novel architecture which bucks those assumptions. In the proposed model, traffic data remains on edge devices which individually train models via federated learning. Beyond the obvious privacy benefits, this architecture enables …

Structural Differential Privacy In Graph Neural Networks, Bibek Giri

Master’s Dissertations

Graph Neural Networks (GNNs) have demonstrated impressive performance across a range of graph-based learning tasks. However, their application to domains with sensitive relational data raises serious privacy concerns, as the graph structure itself may leak confidential information. This thesis investigates a decentralized framework for enforcing edge-level local di!erential privacy (LDP) in graph-structured data. We introduce two mechanisms that perturb a node’s neighborhood in a privacy-preserving yet utility-aware manner. The first approach replaces randomly selected neighbors with feature-similar nodes from the 2-hop neighborhood, ensuring structural realism while preserving degree. The second approach eliminates the need for explicit 2-hop propagation and dummy …

Investigating The Impact Of Agent Openness On Planning In Multi-Agent Systems, Bala Subramanyam Duggirala

School of Computing: Dissertations, Theses, and Student Research

Multi-agent systems (MAS) possess significant potential for modeling real-world scenarios requiring coordinated actions (like wildfire fighting or ridesharing) among autonomous entities or agents (e.g., wildfire fighting agents) in complex, dynamic environments. Effective decision-theoretic planning (where each agent must carefully consider both the immediate and the future situations or states, and coordinate with the other agents (neighbors) to evaluate what needs to be done at present) within MAS, especially multiagent planning, where the planning agent directly models its neighbors in order to estimate their optimal actions, is critical, yet challenged by factors like partial observability, openness, and diverse agent types with …

Dynamic Sparsification In Secure Gradient Aggregation For Federated Learning, Bikash Samanta

Master’s Dissertations

Secure aggregation is a critical component of privacy-preserving federated learning. However, existing fixed-sparsity approaches often incur unnecessary communication overhead. We present DynamicSecAgg, a novel framework that introduces dynamic sparsity while preserving coordinate-level privacy. Our method achieves significant improvements in communication efficiency while maintaining — and in some cases improving — model accuracy across both IID and non-IID user distributions. The framework maintains information-theoretic privacy guarantees via adaptive gradient thresholding and polynomial-based aggregation, proving particularly effective under heterogeneous data settings. These results establish dynamic sparsity as a key optimization for efficient and privacy-preserving federated learning.