Computer Engineering Commons^™

Advancing Machine Learning Approaches Through Robust Methodologies In Llm Code Generation, Adversarial Text Classification, And Unsupervised Learning, Anahita Samadi

Computer Science and Engineering Dissertations - Archive

This dissertation combines insights across text, code, and image modalities to advance the robustness, efficiency, and adaptability of machine learning models. Specifically, we address challenges like adversarial vulnerability in text, the impact of test strategies on code generation, and dimensionality in image representation in unsupervised learning domain. These efforts highlight pipelines for designing machine learning systems that are not only efficient, but also adaptable to complex environments. In addition, these efforts together help form the basis for a multimodal AI capable of thriving in medical applications that this dissertation prototypes for future efforts.

Optimizing Architecture And Software For Next-Generation Memory Systems, Lingfeng Xiang

Computer Science and Engineering Dissertations - Archive

The rapid advancement of memory technologies presents new challenges and opportunities for system software and architectural design. This dissertation investigates how to optimize modern computing systems for next-generation memory, mostly focusing on persistent memory and Compute Express Link (CXL)-based memory. First, we conduct a detailed characterization of Intel Optane DC Persistent Memory, identifying the distinct behaviors of its on-DIMM read and write buffers and analyzing their impact on application performance. These insights motivate optimizations that decouple read and write paths, revealing that random read latency—especially in pointer-chasing workloads—is a dominant performance bottleneck. Second, we present NOMAD, a page management framework …

Medical Ai: Solving Healthcare Challenges And Inspiring Ai Innovation, Xiaowei Yu

Computer Science and Engineering Dissertations - Archive

Artificial Intelligence (AI) is transforming healthcare by enabling large-scale analysis of medical data and integrating multimodal information for more comprehensive diagnostics. I present my work addressing fundamental and challenging problems in developing state-of-the-art AI models for medical data analysis, including multimodal brain data and other medical datasets. Additionally, I design brain-inspired AI models by integrating insights from organizational principles of brain networks. Specifically, my research tackles three critical aspects: (1) AI in Computational Neuroscience, where I design deep learning models for brain network analysis to uncover the organizational principles of brain networks; (2) Brain-Inspired AI, where I integrate superior brain …

3d Perception, Mapping, And Navigation For Mobile Cobot, Tuan T. Dang

Computer Science and Engineering Dissertations - Archive

Service robots are migrating from tightly controlled factory lines into offices, hospitals, and homes, where they must perceive, remember, and act amid people, clutter, and perpetual change. Humans solve this daily by forming compact, task-relevant “cognitive maps”: we sample just enough sensory detail to guide the moment, stitch those snapshots into a sparse topological scaffold, and continuously refine it as we move. Guided by that insight, this dissertation proposes a biologically inspired mapping framework that turns partial RGB-D observations into a hybrid temporal-spatial memory—locally metric for centimeter-scale navigation yet globally topological for room-to-building navigation. The system first distills raw depth …

Breaking Granularity Barriers: Overcoming I/O Abstraction Limitations For High-Performance Storage Systems, Chen Zhong

Computer Science and Engineering Dissertations - Archive

Modern storage hierarchies exhibit performance differences spanning eight orders of magnitude. Each tier in the hierarchy presents fundamentally different optimal access sizes and patterns. Most systems read and write data in fixed-size units across different tiers, typically power-of-2 sizes. It simplifies data management but also suffers from large write amplification when handling small accesses in many real-world workloads. This fundamental disconnect between fixed-size I/O design assumption and real-world usage patterns represents the core challenge.

The storage community has recognized the limitations of fixed-size I/O abstractions and is exploring alternatives, like the new emerging NVMe-KV interface and object-based storage, which aim …

Environment And Intention Awareness For Navigation And Collaboration, Bhaskar Chandra Trivedi

Computer Science and Engineering Dissertations - Archive

Unmanned Aerial Systems (UAS) have become increasingly popular as versatile platforms for tasks such as surveillance, inspection, delivery, and maintenance. In many applications, UAS operate in environments frequented by people or containing sensitive infrastructure, which introduces physical risks in case of vehicle failure, as well as psychological and privacy concerns that may limit their acceptability. Ensuring safe and efficient operation thus requires that UAS consider these risks when planning navigation strategies. While prior information, such as city maps and building layouts, can partially inform risk assessment, such data is often incomplete, necessitating real-time augmentation of risk maps using sensor information. …

Examining Terraform And Bicep: A Comparative Analysis Of Infrastructure As Code Tools For Provisioning Azure Environments, Richard Coffey, Kevin Bayliss

Academic Poster Collection

Examining Terraform and Bicep: A Comparative Analysis of Infrastructure as Code Tools for Provisioning Azure Environments

Nomad Vs. Kubernetes, Alexandru Constantin Cardas, Omar Portillo

Academic Poster Collection

Nomad vs. Kubernetes

Investigation Into Finops Techniques To Optimise Cost In Aws Cloud Deployments, Denis Parker, Kevin Bayliss

Academic Poster Collection

Investigation Into FinOps Techniques To Optimise Cost in AWS Cloud Deployments

The Business-Day Cloud: A Hybrid Kubernetes And Serverless Solution For Sustainable Scaling With Predictable Load Patterns, Brendan Burnside, David White

Academic Poster Collection

The Business-Day Cloud: A Hybrid Kubernetes and Serverless solution for Sustainable Scaling with Predictable Load Patterns

An Evaluation Of Zero Trust Principles In Modern Software Development, Cezar Vararu, David White

Academic Poster Collection

An evaluation of Zero Trust Principles in modern software development

Cost Optimization In Open Telemetry, Niksa Jadric, Cormac Keogh

Academic Poster Collection

Cost Optimization in Open Telemetry

Exploring Rust’S Performance In A Serverless Environment, Saoirse Mullen, Gary Clynch

Academic Poster Collection

Exploring Rust’s Performance in a Serverless Environment

Performance Evaluation Of Zabbix And Azure Monitor In Hybrid It Infrastructure, Ivan Godoy, Cormac Keogh

Academic Poster Collection

Performance Evaluation of Zabbix and Azure Monitor in Hybrid IT Infrastructure

Ai-Based Predictive Analytics For Network Operations, Timur Nikisin, David White

Academic Poster Collection

AI-Based Predictive Analytics for Network Operations

Sharing The Stage With The Future: Humans And Robots Together At Last, Donna L. Clevinger

Honors in Practice Online Archive

This essay presents a co-curricular collaboration bringing ancient comedy to a modern audience. Students and faculty at a large, public R1 university combine art and engineering to create a STEAM-based approach to theatrical production. The author describes how integrating classical text, creative expression, and transformational technologies demonstrates that collaboration between disciplines can produce gains for each, fostering advancements and human understanding that would be unattainable independently. Script writing, casting, stage production, and outcomes are presented.

Design And Evaluation Of A Thai Speech Emotion Recognition Corpus With Ambiguous Annotations, Chompakorn Chaksangchaichot

Chulalongkorn University Theses and Dissertations (Chula ETD)

THAI-SER is the first large-scale Thai speech emotion recognition corpus, comprising 41.6 hours (27,854 utterances) from 100 recordings across diverse environments (Zoom and studio). The data includes both scripted and improvised speech by 200 professional actors (112 females, 88 males, aged 18–55), covering five emotions: neutral, angry, happy, sad, and frustrated. Utterances were labeled via crowdsourcing, with rigorous quality control ensuring a majority agreement score above 0.71. Annotation reliability, measured by Krippendorff’s alpha, reached 0.692 (above the 0.667 threshold), and human emotion recognition accuracy reached 0.772 after filtering. We also report benchmark results from models trained and evaluated on both …

Nobocap: Unlocking Mdr/Ivdr Regulations For Innovators In Europe, Graham Gavin, Claire Brougham

Conference Papers

The NoBoCap project (nobocap.eu) is aimed at addressing some of the challenges encountered by both SMEs and Notified Bodies across the EU. It is a multi-organizational consortium including universities, a Notified Body, and Bio-health and Innovation Hubs and Clusters. The NoBoCap project has several work packages focussed on:• Design and delivery of funded short-term courses.• Creating a dedicated NB job board.• Design and delivery of funded university accredited modules.• Design and development of e-tools to support manufacturers.• Develop a community platform to act as a voice for start-ups and SMEs

Detection Of Data Leakage And Disruption Of Covert Timing Channel In Secure Drone Communication Using Machine And Deep Learning, Jonathan Walatkiewicz

Master's Theses and Doctoral Dissertations

The utilization of recreational drones has experienced a substantial increase in both the United States and globally. However, it is noteworthy that most drones, classified as Internet of Things devices, are produced with a limited security lifecycle. This study's findings are of paramount importance, as traditional computing exploits can be applied to drones, designating them as high- value targets. This study examines the detectability and disruptability of covert timing channel traffic in secure drones. The investigation aims to ascertain the effects of multiple interarrival times, distances ranging from 1 to 330 feet, various detection algorithms, and stream sizes between 32-bit …

Immersive Executive Functions Assessment System (Iexec): Integrating Embodied Cognition And Virtual Reality, Hamza Reza Pavel

Computer Science and Engineering Dissertations - Archive

Executive functions (EFs) are higher-order cognitive processes that include working memory, inhibitory control, and cognitive flexibility. These higher-order processes facilitate the achievement of goal-directed behavior and enable both adaptive decision-making and emotional regulation. Traditional EF assessment tools depend on static pen-and-paper tasks or basic computer-based tasks, which fail to capture real-world cognitive complexity and dynamics. Some of these assessment tools are specifically geared towards children or older adults, while others are more generic and designed to be used for people of all ages. This dissertation addresses these limitations by introducing iExec: The Immersive Executive Functions Assessment System, which functions as …

Enabling Energy And Water Sustainability Through Out-Of-Band Emi Sensing And Infrastructure Modeling, Pranjol Sen Gupta

Computer Science and Engineering Dissertations - Archive

As demand for Internet and cloud services surges, data centers have emerged as critical infrastructure—but they are also among theworld’s most energy- andwater-intensive facilities. Effective power management, particularly at the server level, is essential for improving efficiency, reliability, and sustainability. However, server-level power monitoring remains uncommon due to the high cost of hardware instrumentation and the intrusiveness of software-based solutions, especially in shared colocation environments. My research introduces a novel, low-cost, and non-intrusive method for server-level power monitoring using conducted electromagnetic interference (EMI). By analyzing EMI signals captured from higher levels in the power distribution network, this approach estimates individual …

Optimizing Indoor Localization Using Rssi And Iq Data With Machine Learning, Gokdeniz Tingur

Computer Science Theses

This paper explores implementing and evaluating a Bluetooth Low Energy (BLE)-based indoor localization system using Received Signal Strength Indicator (RSSI) and Angle of Arrival (AoA) data via machine learning. A survey of localization technologies (RFID, GPS, ZigBee, and BLE) provides context on capabilities and limitations in indoor positioning. IQ data and phase-based angle estimation show how BLE 5.1’s direction-finding features enable sub-meter accuracy. A multi-phase experiment in a three-story academic building examines model performance with different tag distributions, movement patterns, and environmental constraints. Machine learning models such as Support Vector Machines and Deep Neural Networks are trained and evaluated across …

Improving The Operator-Swarm Dynamic Under Mental Fatigue Constraints In Search And Rescue Operations, Jordan Morrow

Masters Theses

"Human-robot applications that allow for work to be done remotely are largely dependent on the lassitude of the operators. The exhaustion of these operators is a result of work completion and duration. Previous research attempts to evaluate the impact on reaction by quantiying human weariness. This paper examines how human weariness affects the human-robot dynamic in UAV-assisted search and rescue missions. An explanation of the connection between mental exhaustion and operator responsiveness over prolonged durations is provided by the search and rescue operations using UAV swarms (SAROUS) model. Through the use of artificial intelligence, SAROUS is modernized. This allows the …

Advanced 3d Lidar-Based Systems For Urban Traffic And Pedestrian Monitoring: Integrating Elevated Lidar, Data Collection, And Deep Learning For Precise Detection And Activity Classification, Nawfal Guefrachi

Masters Theses

"Accurate and real-time monitoring of urban traffic and pedestrian activities is crucial for intelligent transportation systems (ITS) and smart cities. Traditional camera-based methods struggle with issues like lighting and privacy. This research leverages advanced three-dimension light detection and ranging (3D LiDAR) technology and computational frameworks to address these challenges, providing transformative solutions for urban traffic management and pedestrian safety. By strategically deploying elevated LiDAR sensors, detailed 3D point cloud data is captured, enabling precise monitoring of urban environments. Enhancements to LiDAR-based frameworks, such as fine-tuning the Point Voxel Region-Based Convolutional Neural Network (PV-RCNN), improve the detection of vehicles and pedestrians …

Lidar From The Skies: A Uav-Based Approach For Efficient Object Detection And Tracking, Baya Cherif

Masters Theses

"Recently, there has been a growing interest in deploying the Light Detection and Ranging (LiDAR) technology to gain traction in the autonomous vehicle industry, its applications are expanding into areas like smart cities, agriculture, and renewable energy. This work proposes an advanced approach to enhance aerial traffic monitoring using Li- DAR. We aim to provide accurate, real-time object detection and tracking from an aerial perspective by integrating Unmanned Aerial Vehicle (UAV) with LiDAR, culminating in a smart UAV-integrated LiDAR (A-LiD) sensor for traffic surveillance. We introduce an adapted version of one of the newest methods of the cutting-edge 3D object …

On Optimizing Sensor Data Collection, Processing, And Storage For Industrial Additive Manufacturing, Steven Thompson

Masters Theses

The widespread adoption of digital data management methods for transformative technologies, such as additive manufacturing (AM), within the aerospace industry is impeded by poor interoperability between AM component manufacturing processes. Moreover, data quality may be compromised due to sensor failures or other corruptions. Additionally, massive amounts of data are collected during these processes, often needing to remain accessible for decades. These storage costs can place a significant financial burden on smaller suppliers. This work aims to make digital data management methods more affordable and, therefore, approachable for smaller suppliers.

First, the design and initial implementation of an affordable and adaptable …

Ai-Driven Traffic Scene Understanding Using Static Lidar Sensors, Elham Binshaflout, Chaima Zaghouani, Charalampos Antoniadis, Hakim Ghazzai, Nawfal Guefrachi, Ahmad Alsharoa, Sameh Najeh, Gianluca Setti

Electrical and Computer Engineering Faculty Research & Creative Works

Traffic congestion and road safety remain critical challenges in urban environments, driving the need for more effective traffic monitoring solutions. While recent advancements in computer vision have enhanced traffic perception, the dynamic viewpoint of autonomous vehicles is often insufficient for comprehensive traffic management. To address this gap, we propose an AI-driven framework for enhanced traffic scene understanding using static LiDAR sensors at road intersections. The system collects 3D point clouds from roadside static LiDAR sensors, providing a complete view of vehicles and pedestrians. We integrate state-of-the-art 3D object detection (i.e., PV-RCNN) and instance segmentation models (i.e., PointGroup3heads) to accurately identify …

Focused Feature Extraction For Driver Drowsiness Detection Using An Enhanced Attention-Based Resnet Model, Nada Ayman Atia, Rawan Sameh

The Undergraduate Research Journal

In the context of increasing road safety concerns, particularly in Egypt, this paper addresses the critical issue of driver drowsiness, a significant contributor to road accidents worldwide. With alarming statistics from the World Health Organization citing human error, chiefly drowsiness, as the cause for a majority of road accidents in Egypt, there is a compelling need for an effective drowsiness detection system. This research introduces a novel, vision-based driver drowsiness detection system leveraging a multi-dimensional approach with a Residual Neural Network (ResNet) architecture and attention layers. This system aims to accurately identify drowsiness by analyzing key facial features. The paper …

Comparing Funders' Altruism Versus Self-Interest: Leveraging The Context Of Crisis, Dan Liu, Guangzhi Shang, Cynthia Fan Yang

Journal of International Technology and Information Management

While reward-based crowdfunding has widespread popularity, the motivations driving funders, balancing self-interest and altruism, have remained puzzling. Prior research has been constrained by examination methods and produced mixed findings regarding the weight of altruism versus self-interest among funders. Our study takes a fresh perspective, delving into funder behavior amid a major crisis—the tumultuous backdrop of the COVID-19 pandemic. Our findings reveal that funders not only display an increased willingness to contribute but also significantly amplify their contributions, particularly to projects in crisis-affected regions, irrespective of external incentives like rewards. This underscores the prevalence of altruistic motives among funders in challenging …

Understanding The Determinants Of Blockchain Adoption: An Empirical Study, Amarpreet Kohli, Nihar Kumthekar, Piyush Shah, Rebecca Jauch

Journal of International Technology and Information Management

Blockchain technology (BT) has the potential to enhance security and robustness of transactions through a distributed ledger bookkeeping process. This study employs technology-organization-environment (TOE) framework and threat-rigidity theory (TRT) to examine whether perceived disruption caused by COVID-19 pandemic significantly impacted the adoption of BT, and inclination to adopt BT in the US. The COVID-19 pandemic provided a unique backdrop, as it affected businesses across all industries, sizes, and geographies. Results show a non-significant effect of perceived pandemic disruption on the current stage of BT adoption and intention to adopt BT. However, disruption readiness positively influences the current stage of BT …