Computer Engineering Commons^™

Navigating The Rules: Integrating Td3 And Sensor Fusion For Traffic-Aware Autonomous Vehicle Path Planning, Mahmoud Ayman Mohamed Elsayed

Theses and Dissertations

This work presents a novel algorithm for local path planning for autonomous vehicles (AVs) which prioritizes both safety and adherence to traffic regulations, addressing critical functions for AV navigation, such as navigating complex environments, avoiding obstacles, and ensuring passenger and road users safety. The algorithm integrates the Twin Delayed Deep Deterministic Policy Gradient (TD3) with sensor fusion based on Nvidia Convolutional Neural Network (NCNN). The study utilizes the CARLA simulator, and real-world datasets, including KITTI and WAYMO, to train and evaluate the proposed algorithm. The proposed algorithm leverages the complementary strengths of Imitation Learning (IL) and Deep Reinforcement Learning (DRL) …

Virtual Museum Tours Of The De Saisset Museum, Justin Enciso-Anaya, Karthik Tamil, Quoc Truong

Computer Science and Engineering Senior Theses

Our project transforms the California Stories exhibit at the de Saisset Museum into an immersive virtual tour, integrating Matterport technology and Human-Computer-Interaction (HCI) principles. Matterport’s high resolution 360 degree camera allows us to capture a physical space in high definition into a 3D virtual space while Matterport’s software helps to facilitate the creation and editing for our physical space in a virtual environment. HCI principles focus on how systems should work when direct interaction with users is a key component. We apply the principles of HCI to create a virtual museum tour that offers visitors a culturally enriching, interactive experience, …

Monterecycle: An Application For Streamlining Tracking Of Recyclables In Uruguay, Aayooshi Dharmadhakari, Danny Walsh, Eason Ke, Kamya Krishnan

Computer Science and Engineering Senior Theses

Recycling is a crucial process that has a positive impact on nature, cleans the environment, and saves time and money. Classifying recyclables by material and recycling these items accordingly helps make our world more environmentally-friendly and a better place to live.

In the recycling system in Montevideo, Uruguay, third-party contractors hired by San Vicente transport clients’ recyclables to a central recycling center or to a person that does recycling. In the past, San Vicente has transported recyclables though horse and buggy transportation. However, there has been a push from the city to replace the horses with motorcycles to reduce animal …

Iotsolate: Network Microsegmentation For Managing And Securing Iot Devices, Chloé Morali, Anagha Nair

Computer Science and Engineering Senior Theses

Developing solutions to secure IoT devices is a pressing issue facing us today. Although IoT devices improve everyday life in various ways, they are susceptible to security threats, impacting users in all environments. As the number of IoT devices increases, the attack surface expands exponentially. However, securing these devices proves to be a challenge because they are made with limited processing capabilities, which means they lack necessary security features. They also come in a wide range of variations in terms of operating systems, physical design, and network connectivity which complicates the establishment of standardized security options. Additionally, they tend to …

Performance Evaluation Of Databases For Packet Capture And Analysis, James Vong, Daniel Kareti

Computer Science and Engineering Senior Theses

Today, the presence of smart devices is constantly on the rise, especially for Internet of Things (IoT) devices. However, their utility-based design means that these devices are limited in computing power. Due to this limited computing power, the devices are more prone to cyber-security threats, and it is vital to construct a method to aid in network traffic analysis, bolstering defense mechanisms to thwart any malicious attacks. To analyze their network data efficiently and externally, we constructed a test-bed infrastructure to measure and evaluate the performance of databases. In this thesis, we have chosen to compare two databases which are …

Scdi: Privacy-Preserving Device Identification, Ethan Shenassa, Michael Castillo

Computer Science and Engineering Senior Theses

As internet security concerns grow due to the increasing complexity of cyberattacks, heterogeneity of network-connected devices, and popularity of insecure Internet of Things (IoT) devices, network administrators require more intelligent ways of managing and securing their networks. One crucial step in this regard is the ability to identify and classify devices from the edge of networks. However, many recent advances in network security come at the cost of user privacy, as device classification algorithms often require packet payload data, Internet Protocol (IP) addresses, or other sensitive information. This paper proposes the Shenassa-Castillo Device Identifier (SCDI): a software network device identifier …

Deep Learning Based Single Image Super-Resolution, Samuel Smith

Computer Science and Engineering Senior Theses

Single image super-resolution (SR) involves taking a given low-resolution (LR) image and generating a corresponding high-resolution (HR) image. This is a core task in the computer vision field due to its multitude of applications ranging from helping current-day issues of storage and transfer of data to restoration of low-resolution images. The current strategies, however, struggle to reach the quality needed for their widespread use and are often too resource-intensive for the average consumer. While other lightweight SR techniques exist with different techniques, like Cascading Residual Networks [3], their success comes at the cost of expensive technology inaccessible to most situations. …

Distant Horizon: Exploring Human-Ai Interaction Through Video Games, Gabe Labadie, Dalia Suszko, Max White

Computer Science and Engineering Senior Theses

As the field of Artificial Intelligence (AI) continues to grow and become more and more integrated into our everyday lives, it has begun to raise ethical concerns surrounding authority, autonomy, and responsibility. Researchers and consumers alike have begun to wonder how much trust we are willing to place in a non-human decision maker, especially if an Artificial General Intelligence (AGI) capable of surpassing human cognitive capabilities is ever developed. If we are willing to let an AI write essays for us, are we willing to let it manage a business? A government agency? What about a nuclear reactor?

Our project …

Daily Digest: A News Aggregation Site, Justin Wang, Jack Maguin, George Orloff, Justin Groves

Computer Science and Engineering Senior Theses

A staggering amount of news articles are uploaded every day – approximately 5,000 in the United States alone [1]. That volume of information causes difficulty for many people who try to stay up-to-date with current events. The number of articles and the multitude of sources that they come from can feel overwhelming. In our project, we attempt to tackle this issue. We use web scraping to collect a dataset of news articles and combine it with a Large Language Model (LLM) capable of processing those articles to generate news summaries for the user. The user interacts with the program through …

General Purpose Tuning Data Visualization, Chris Augustine, Francisco Salinas, Aakash Shetty

Computer Science and Engineering Senior Theses

This project centers on the visualization of High-Performance Computing (HPC) data obtained from the GPTune website. GPTune serves as a valuable resource for HPC experiments, providing a wealth of performance data from tuning studies and optimization tasks. Our objective is to develop an advanced data visualization framework tailored to GPTune’s datasets. Utilizing state-of-the-art visualization techniques, we aim to create an interactive platform that allows users to explore, analyze, and derive insights from the diverse tuning experiments conducted on HPC systems. The visualization tool will facilitate the identification of optimal configurations, performance trends, and patterns within GPTune data, empowering researchers and …

Applied Auto-Tuning On Lora Hyperparameters, Darren Inouye, Lucas Lindo, Robin Lee, Edmund Allen

Computer Science and Engineering Senior Theses

This senior design project explores the application of Bayesian optimization-based auto-tuning techniques on the low-rank adaptation (LoRA) fine-tuning of large language models (LLMs), demonstrating how fine-tuning methods can reduce training times and costs, albeit with a slight trade-off in accuracy. However, little is known about the optimal hyperparameters on LoRA and its variants for those methods. This project addresses this lack of knowledge by analyzing data gathered from auto-tuning LoRA hyperparameters to determine the most optimal parameter configurations for a model’s accuracy and training efficiency.

The team has implemented a pipeline utilizing many different technologies. The main technology driving the …

9-Axis Motion Tracking To Aid Therapeutic Recovery Via Visualization, Analysis And Progress Monitoring, Megan Wiser, Liam A'Hearn, Christopher Tamayo, Liam Kelly

Computer Science and Engineering Senior Theses

This paper presents an innovative approach to enhance at-home physical therapy exercises through the development of a wearable motion tracking system. The proposed system utilizes motion tracking bands worn by patients during exercises, specifically focusing on a squat jump for the initial phase of the project. The bands, placed around the ankle and knee, monitor the alignment of the user's motion and transmit data via Bluetooth Low Energy (BLE) to a dedicated webpage. This webpage integrates real-time data analysis, offering immediate feedback to users, enabling them to monitor their form and track progress over time. The collected data is stored …

Hiv3: An Efficient Beehive Monitoring System, Jack Ursillo, Aneal Kuverji, Connor Merhab, Anshuman Sahu

Computer Science and Engineering Senior Theses

Beehive monitoring plays a major role in ensuring the health of beehives by checking for overpopulation or underpopulation within a hive. Beehive monitoring provides beekeepers with the opportunity to take action and save the hive before the problem becomes irreversible. Most solutions are too expensive for everyday beekeepers and lack elements of sustainability, making it impractical for small scale beekeepers. In this thesis, we propose a solution to this problem, demonstrating its sustainability and user-friendliness, which enables us to effectively reach a larger consumer market. We support these claims through the use of sustainable systems such as using a solar …

Enhancing Vqgan-Based Model With Connext For Blind Super-Resolution, Lebin Zhou

Computer Science and Engineering Master's Theses

This thesis presents a novel super-resolution model based on Vector Quantized Generative Adversarial Network (VQGAN) to enhance image resolution. Inspired by recent advancements in the field of image reconstruction, we apply VQGAN to the super-resolution task, leveraging its powerful generative capabilities to produce higher quality high-resolution images.

Building on the VQGAN framework, we propose an improved architecture that incorporates an additional ConvNeXt feature extractor based on Convolutional Neural Networks (CNN) to effectively capture and refine features from low-resolution images. To further enhance model performance, we implemented various strategies to optimize the utilization of the codebook, including capacity optimization, improved initialization, …

Finding The Shortest Path Using Dijkstra’S Algorithm, Orit D. Gruber, Deborah Sturm

Open Educational Resources

This lab experiment explores an algorithm which is used to find the shortest path between two or more locations. After completing the lab, you will be able to answer the following questions in the final lab report:

1. What is an Algorithm?
2. What is a Graph ?
3. What is the purpose and operation of Dijkstra’s Algorithm ?

Ultra Low-Power, High-Performance Presence Detection System, Dante Bajarias, Cristian Medal, Jashan Kaeley

Computer Science and Engineering Senior Theses

The proliferation of Internet of Things (IoT) devices emphasizes a greater connection between humans and smart technology. From computer peripherals, personal electronics, and domestic appliances to building access management, healthcare, and security systems, modern applications are generating as much data or more than they are receiving from other sources. Human presence is a type of data that is becoming a compelling requirement for a plethora of today’s applications that must ensure seamless interactions of users with the systems and their associated services. The ultra low-power, high performance presence detection system is an accelerometer-based system capable of person detection, people counting, …

Edge-Connected Microcontroller Security, Divya Syal, Gavin Ryder, Neena Ekanathan

Computer Science and Engineering Senior Theses

With a wide range of applications and the rise of cyber attacks, securing microcontrollers has become imperative; however, ensuring microcontroller performance is also crucial given how interconnected today’s systems are. This project examines the security and performance of next-generation microcontroller units leveraging new security solutions for IoT edge applications. By benchmarking these MCUs against key performance metrics, their viability will be assessed to facilitate the widespread adoption of this latest firmware.

Our research focuses on profiling the power consumption and performance of the new STM32H573 and the integrated Secure Manager, a new technology from ST Microelectronics that allows for privileged …

Autonomous Microgrid System, Xavier Kuehn, Brian Xiong

Computer Science and Engineering Senior Theses

Microgrids have made a revolutionary change in the realm of energy distribution due to the features that they offer, including localized, resilient, and sustainable energy solutions. Operating renewable resources in a microgrid while maintaining generation-load balance and acceptable voltage-frequency limits has been an open research problem. This thesis presents smart python agents for microgrid systems to automate the operations and control of microgrid renewable resources in an effort to provide resilient solutions to the intermittence issues that could potentially arise within the microgrid energy system. The smart agents operate the microgrids by not only integrating the use of renewable energy …

Uhd: Unary Processing For Lightweight And Dynamic Hyperdimensional Computing, Mehran Shoushtari Moghadam, M. Hassan Najafi

Faculty Scholarship

Hyperdimensional computing (HDC) is a novel computational paradigm that operates on long-dimensional vectors known as hypervectors. The hypervectors are constructed as long bit-streams and form the basic building blocks of HDC systems. In HDC, hypervectors are generated from scalar values without considering bit significance. HDC is efficient and robust for various data processing applications, especially computer vision tasks. To construct HDC models for vision applications, the current state-of-the-art practice utilizes two parameters for data encoding: pixel intensity and pixel position. However, the intensity and position information embedded in high-dimensional vectors are generally not generated dynamically in the HDC models. Consequently, …

Enhanced Adaptive Image-Codebook Learning For Image Reconstruction, Yutong Ge

Computer Science and Engineering Master's Theses

In the field of image reconstruction and super-resolution, using codebooks has shown promising results despite various image degradations. Previous methods either use distinct codebooks for each image category or multiple codebooks per category, with the latter achieving better performance by capturing more nuanced image features. Our research proposes a novel method that employs enhanced sets of codebooks and weight maps tailored to each image category. These weight maps dynamically combine different codebook bases to adapt to various reconstruction tasks, resulting in improved image recognition and robustness. This approach significantly enhances the expressiveness and quality of reconstructed images, making it versatile …

E-Scooter Black Box, Soham Phadke, Suvass Ravala, Joshua Jerome, Raghav Batra, Mubashir Hussain

Computer Science and Engineering Senior Theses

The burgeoning market for shared e-scooters is significantly hampered by the short lifespan of commercial e-scooters, which currently average just three months due to rough handling by users. To address this challenge, our project aims to extend the lifespan of shared e-scooters through an innovative onboard solution that discourages detrimental riding behaviors.

Our solution integrates a portable sensor hub from STMicroelectronics to capture ride data, which is then processed and sent via a user’s iOS app to a Google Firebase backend. A machine learning model running in the cloud analyzes the data to extract valuable metrics. These metrics are displayed …

Residual Transformer Unet For Medical Image Segmentation, Ruopu He

Computer Science and Engineering Master's Theses

With the continuous development of deep learning theory in the field of medical images, information technology-assisted treatment methods represented by medical image segmentation technology can help doctors to quickly determine the shape and location of the lesions and improve the diagnosis efficiency of brain tumors. Based on deep learning technology, this thesis carries out related research work on MRI image segmentation. The main contents are as follows:

To begin with, acquire and prepare the brain tumor (MRI) image segmentation dataset from the official MICCAI Society website. This involves normalizing the images, cropping, and slicing, as well as scaling the data …

Comprehensive Network Redundancy Implementation And Cybersecurity Hardening Project: Ensuring Resilience And Defending Against Dhcp Starvation, Stp Man-In-The-Middle, And Brute Force Attacks, Seth Shaheen

Williams Honors College, Honors Research Projects

I have created a network topology that contains three Cisco routers, three Cisco switches, and three endpoints. The network has been built using the software GNS-3. The endpoints on the topology include one VPC, one Kali Linux VM, and one Ubuntu Server VM. The main purpose of this network topology is to show the skills I have learned during my tenure at The University of Akron. This will be done by hardening this network to ensure that the network is impervious to cyber-attacks. The Kali Linux VM will act as the attacker on the network and conduct three attacks: STP …

Exploring The Impact Of Artificial Intelligence On Project Management Across The Manufacturing, Technology, And Construction Industries, Susie Diaz Ferrera

Harrisburg University Dissertations and Theses

This study explores the impact of Artificial Intelligence (AI) on project management across the manufacturing, technology, and construction industries. The research focuses on understanding the benefits, challenges, and long-term implications of AI utilization in these sectors. Key findings indicate that 46% of participants use AI mainly for task automation and enhancing functions like brainstorming and communication, which significantly boosts efficiency and team productivity. Despite these benefits, the research identifies several obstacles, including high initial costs, inadequate training, technical issues, and unclear regulatory guidelines. The study addresses four main questions, revealing that AI not only enhances project management processes but also …

Sustaining Digital Assets Through Mobile Estate Planning, Norliza Katuk, Asvinitha Muniandy, Norazlina Abd. Wahab, Ijaz Ahmad

An-Najah University Journal for Research - B (Humanities)

Many people own online accounts, with some having financial values like Internet banking, e-wallet and cryptocurrency. In the case of sudden death, their heirs are unaware of the digital assets possessed by the deceased person, which causes the assets to be lost forever, and the heirs might not receive the assets. If an estate plan did not account for digital assets properly, the beneficiaries would not be able to access them. Therefore, this paper addresses this issue by implementing a software development approach in designing a suitable model for sustaining digital assets through smartphones to allow the inheritance of digital …

Waypoint Profiler, Jeff Ke, Ricky Schober, Alexander Collins, Kevin Wang

Computer Science and Engineering Senior Theses

Ocean health monitoring is crucial for maintaining the health of the ocean ecosystem. Currently, divers are deployed to collect data manually, which is both time and resource-consuming. Additionally, this process poses significant dangers to the divers. Therefore, a more efficient method for collecting oceanic data is needed. This thesis describes the design of a novel autonomous marine vehicle, the waypoint profiler. Launched from shore with scientific sensors, it autonomously navigates to ocean locations of interest and dives to measure key ocean health markers. The system integrates subsystems for scientific sensing, health monitoring, structural integrity, communications, and navigation/control, tailored to meet …

Piloted Autonomous Crisis Reconnaissance Robot (Pacrr), Aidan O’Hare, Luca Chierotti, Tyler Costello, Nicholas Kenny

Computer Science and Engineering Senior Theses

PACRR stands for Piloted/Autonomous Crisis Reconnaissance Robot. The aim of PACRR is to create a low-cost, autonomous-capable quadruped robot for first responder applications such as search and rescue, detecting gas leaks, mapping obstructed areas, and other situations that are dangerous or too confined for humans. The design process for PACRR involved the addition of perception sensors to use with a simultaneous localization and mapping (SLAM) algorithm, alterations to the power delivery system, adjusting the control of the robot, as well as other hardware and software modifications to an open-source 3D-printed design originally developed at Monash University called DINGO.

Nautilus: Deep Sea Dexterity, Quinn Bates, Saunder Salazar, Morgan Watts, Davis Robertson, Sarah Abruzzo, Ian Staff, Nick Aguilar

Computer Science and Engineering Senior Theses

Global warming and climate change are prevalent issues in today's society. As a result, research in the ocean, earth's biggest ecosystem, is imperative in efforts to protect the environment. Santa Clara University's Robotic Systems Lab contributes to this field through work and development on remotely operated vehicles (ROVs). Nautilus was built to support geologists and other researchers, primarily in the Lake Tahoe and Monterey Bay area. Thus far the ROV s sole scientific instrument has been its onboard camera, though partner geologists desire the ability to collect physical samples using a robotic arm attachment at depths up to 100 meters. …

Deep Learning-Based Video Prediction, Mareeta Mathai

Engineering Ph.D. Theses

The task of video prediction is to generate unseen future video frames based on the past ones. It is an emerging, yet challenging task due to its inherent uncertainty and complex spatiotemporal dynamics. The ability to predict and anticipate future events from video prediction has applications in various prediction systems like self-driving cars, weather forecasting, traffic flow prediction, video compression etc. Due to the success of deep learning in the computer vision field, several deep learning Artificial Intelligence (AI) architectures such as convolutional neural networks (CNNs), long short-term memory (LSTMs), convolutional LSTMS (ConvLSTMs) and transformers have been explored to improve …

Technocene, Vir Joseph Naidu

Masters Theses

Embodied human communication within the Anthropocene. Existing at the intersection of technology, and the body.

The design industry has developed technology that is, paradoxically, isolating. The exposure to a vast audience in the digital sphere has introduced new societal pressures, leading to a disconnection from our immediate surroundings, detached, and donning metaphorical masks. Technocene lives on the fringes of the discipline by blending conceptual thinking with practical application. Through curious, experimental artifacts, it prompts us to shed our masks and embrace vulnerability. Technocene endeavors to reimagine the human experience by acting as a discursive design project. It probes the boundaries …