Computational Engineering Commons^™

Applying X-Ray Fluorescence With Monte Carlo Methods For Analysis Of Surface Defects On Coated Zr4, James Tyler Cahill

Theses and Dissertations

Chromium-coated Zircaloy-4 cladding represents a novel solution for creating nuclear cladding that has passive safety features. This and related developments aimed at improving nuclear safety are broadly categorized as accident-tolerant fuel and cladding. However, implementing this material presents practical challenges such as the vulnerability that cladding has to surface damage such as fretting wear. This research aims to determine if the pre-existing technique of X-ray fluorescence analysis is applicable for detecting these defects on the surface of the cladding. This was done by developing Monte Carlo N-Particle Transport models of a handheld device, the XL-5, alongside experimental measurements using this …

Finops-Driven Cloud Optimization Models For Enterprise Applications, Manikantha Varaprasad Inakollu

Computer Science and Engineering Faculty Publications

Cloud computing has revolutionized enterprise IT infrastructure, yet escalating costs and resource inefficiencies threaten to undermine these benefits. This research examines FinOps-driven optimization models that enable organizations to balance cloud performance, cost efficiency, and business value. The study addresses the critical challenge enterprises face in managing cloud expenditures while maintaining operational excellence. Through comprehensive analysis of FinOps principles and practical optimization frameworks, we develop models that integrate financial accountability, technical efficiency, and business alignment. Our research demonstrates that organizations implementing structured FinOps practices achieve 25-40% cost reductions without compromising application performance. The study contributes both theoretical frameworks for understanding cloud …

Enhancing Erp Auditability And Compliance Using Permissioned Blockchain, A Framework For Transparent And Immutable Enterprise Resource Planning Systems., Manikantha Varaprasad Inakollu

Computer Science and Engineering Faculty Publications

Enterprise Resource Planning systems serve as the backbone of modern organizational operations, yet their centralized architecture creates significant challenges for auditability and regulatory compliance. This research proposes a permissioned blockchain framework to enhance ERP auditability by creating immutable, transparent, and traceable records of all system transactions and modifications. The study addresses critical gaps in current ERP systems where transaction histories can be altered, audit trails prove insufficient, and compliance verification remains cumbersome. Through examination of existing ERP limitations and blockchain capabilities, we develop an integrated architecture that maintains operational efficiency while providing cryptographic assurance of data integrity. Our framework employs …

Disentangling Cyclic Causality: An Instance-Based Framework For Causal Discovery, Chase A. Yakaboski

Dartmouth College Ph.D Dissertations

Correlation does not imply causation" is one of the fundamental principles taught in science, emphasizing that associations between variables do not necessarily indicate causality. Yet, over the past three decades, extensive research has begun to challenge this perspective by developing sophisticated methods to differentiate causal from correlative relationships. This research suggests that correlations often involve a blend of confounded and causal interactions, which, given certain assumptions, can be disentangled to uncover actionable insights and deepen our understanding of physical, biological, and societal systems.

Accurately discovering causal relationships from data amidst cyclic dynamics remains a challenging open problem in causality research. …

Application Of Fusion Based Deep Learning Models To Improve Millimeter Wave Beamforming, Abishek Subramanian

Dissertations, Master's Theses and Master's Reports

This study addresses the challenge of selecting millimeter Wave (mmWave) beamforming pairs for vehicle-to-infrastructure (V2I) communication, to mitigate latency in highly dynamic vehicular environments. We investigate the use of out-of-band sensor data as side information to model mmWave ray tracing paths and predicting a subset of top-K optimal beamforming pairs for efficient and low-latency searches. Unimodal-Fusion Deep Learning (F-DL) networks was applied to enhance mmWave beamforming process. We started by first investigating the centralized architecture, and then explored a novel distributed architecture through federated learning to minimize resource and latency overheads. The distributed architecture incorporates two biased client selection strategies: …

The Integration Of Neuromorphic Computing In Autonomous Robotic Systems, Md Abu Bakr Siddique

Dissertations, Master's Theses and Master's Reports

Deep Neural Networks (DNNs) have come a long way in many cognitive tasks by training on large, labeled datasets. However, this method has problems in places with limited data and energy, like when planetary robots are used or when edge computing is used [1]. In contrast to this data-heavy approach, animals demonstrate an innate ability to learn by communicating with their environment and forming associative memories among events and entities, a process known as associative learning [2-4]. For instance, rats in a T-maze learn to associate different stimuli with outcomes through exploration without needing labeled data [5]. This learning paradigm …

Reinforcement Learning From Human Feedback For Ethically Robust Ai Decision-Making, Marco M. Plasencia

Honors Undergraduate Theses

The emergence of reinforcement learning from human feedback (RLHF) has made great strides toward giving AI decision-making the ability to learn from external human advice. In general, this machine learning technique is concerned with producing agents that learn to work toward optimizing and achieving some goal, advanced by interactions with the environment and feedback given in terms of a quantifiable reward. In the scope of this project, we seek to merge the intricate realms of AI robustness, ethical decision-making, and RLHF. With no way to truly quantify human values, human feedback is an essential bridge in the learning process, allowing …

Efficient Data Collection In Chemistry Via Active Learning And Uncertainty Quantification, Khash Rafei

Theses and Dissertations

Abstract In this study, we investigate active learning in machine learning for chemical systems, with a focus on improving model performance and reducing data collection costs through uncertainty quantification methods. Data collection in chemistry is often resource-intensive, and active learning offers a cost-effective alternative by selectively choosing informative data points for iterative training. We evaluated various uncertainty quantification techniques, including ensemble-based methods (Evidential Ensemble and MVE Ensemble), dropout, and random se- lection, across several chemical datasets of varying properties. Our findings highlight that ensemble-based methods significantly improve predictive performance and are effective across a range of datasets. Evidential Ensemble and …

Enhancing Pipeline Simulations Through Artificial Intelligence And Machine Learning: A Smart Proxy Modelling Approach, Afeez Shittu

Graduate Theses, Dissertations, and Problem Reports (ETD)

ABSTRACT

Enhancing pipeline simulations is essential for improving operational efficiencies and effectively managing risks in the oil and gas industry. Traditional pipeline simulators, relying heavily on mathematical modeling assumptions, often face limitations due to their high energy and computational demands. This thesis addresses these challenges by introducing an innovative approach that integrates artificial intelligence (AI) and machine learning (ML) through a smart proxy model, offering a more efficient, cost-effective, and flexible alternative to conventional full-physics models used in pipeline simulation software.

The primary aim of this research is to develop and implement a smart proxy model capable of accurately predicting …

A Domain Adaptation Approach For Morphology-Independent Cell Instance Segmentation, Voke Rotimi Brume

Graduate Theses, Dissertations, and Problem Reports (ETD)

In recent years, there has been an upward trend of utilizing deep learning to automate cell segmentation processes. As global storage capacities grow exponentially, so have microscopy data collections become larger and more frequent. To benefit from them, accurate and precise quantitative analysis tools like cell instance segmentation have become necessary. However, the highly variable nature of these data collections necessitates retraining segmentation models to maintain high accuracy on new data collections. This process is time-consuming and labor-intensive since a user must annotate much of the new data, usually under the supervision of a medical professional. The problem is further …

Fingerphoto Deblurring Using Wavelet Style Transfer, David Connard Keaton

Graduate Theses, Dissertations, and Problem Reports (ETD)

This work focuses on a deblurring network designed specifically for the task of deblurring contactless fingerprints, a.k.a fingerphotos. This network takes the general idea of style transfer, and applies it to the realm of deblurring. The standard use case for style transfer networks is artistic style transfer, which is used for recreational purposes. For this work, though, style transfer is used in the context of deblurring. Since style transfer can transfer artistic styles from one image to another, who's to say it can’t transfer clarity and sharpness as well? This is the focus of this work; taking a blurry fingerphoto, …