Computer Sciences

Robotic prosthetic arms typically rely on muscle-based control systems, but alternative approaches may enable more flexible interaction with the environment. This project explores the use of artificial intelligence and external sensing to control a robotic arm using environmental inputs rather than direct muscle signals. An ESP32 microcontroller connects the robotic arm to a computer via Bluetooth, allowing commands generated through ... Read More

Recent advancements in vehicle autonomy have spurred interest in understanding the impact of autonomous vehicles on traffic systems. In this paper, we study a traffic assignment problem in a mixed-autonomy setting where both human-driven and autonomous vehicles coexist. We model the interaction between the two types of vehicles as a simultaneous routing game, where human drivers act selfishly to minimize ... Read More

Prostate cancer (PrCa) is the second leading cause of cancer-related death in American men. Although mechanisms to determine PrCa aggressiveness exist, they are subject to significant inter-observer variability. One example is Gleason grading, which determines PrCa severity based on glandular morphology. Scoring variability, which occurs even between experienced pathologists, poses a challenge when developing treatments. A promising way to mitigate ... Read More

The rapid spread of AI-generated video has made robust deepfake detection essential for public trust and media integrity. Although current detectors perform well on standard benchmarks, prior studies show they remain highly vulnerable to adversarial perturbations. Yet, existing research primarily evaluates single-modality attacks, leaving open the question of whether coordinated audio-visual perturbations can further compromise detector reliability. This project aims ... Read More

Energy-Based Models (EBMs) are a generative machine learning framework that can be applied to many types of data. They work by learning the energy function in a Boltzmann distribution, which measures the compatibility between the input and the target data distribution. Training EBMs probabilistically can be difficult since it requires calculating the partition function, which integrates over all possible inputs, ... Read More

Semaglutide, sold under the brand name Ozempic, is a medication that is aimed for individuals with diabetes to aid in blood sugar management. However, in the last decade, Ozempic has become a popular drug for weight loss due to the influence of social media. Many users of this drug have reported negative side effects, but the general reaction to the ... Read More

A color space is an organization and representation of colors in terms of specified components. While RGB is the most common, it is not less useful when looking at how humans perceive skin tones under different lighting conditions. Other color spaces, like CIELAB and HSV, are developed to separate lightness and chromatic information. However, these color spaces are still based ... Read More

With just a collection of images captured of a space, 3D Gaussian Splatting (3DGS) can recreate an almost exact looking 3D representation of that space, enabling the usage of realistic 3D environments for video games and even Virtual reality. 3D Gaussian Unscented Transform (3DGUT) is an extension of 3D Gaussian Splatting (3DGS) that allows training using fisheye cameras. However, its ... Read More

Data attribution methods have become more studied in literature to estimate the influence of each training sample on the model. This work has important implications for data privacy laws, copyright compensation, and more. However, recent work has shown that this method of data attribution can be vulnerable to adversarial manipulation. In this project, we investigate how such vulnerabilities can be ... Read More

This project aims to discover the effectiveness of the QAM-16, QAM-64, and QAM-256 constellations in Quadrature Amplitude Modulation (QAM) systems, with the goal of improving machine learning based classification of radio signal transmissions. Traditional communication systems rely on expensive and inflexible hardware for signal decoding. However, this research, conducted in Dr. Davids’ lab and sponsored by INdigital, investigates a software-based ... Read More

Groundwater overextraction poses a critical threat to agricultural and environmental sustainability worldwide. Recent work developed by Cialenco and Ludkovski (2025) introduces a stochastic game-theoretic model of groundwater trading markets, in which farmers optimize their reward through crop production, water trading, and intertemporal water banking, all subject to a stochastic aquifer recharge. While the resulting Nash equilibrium is fully characterized in ... Read More

Depth estimation for wearable systems is of significant interest in fields such as extended reality, robotics, and human-computer interaction due to its central role in enabling spatial understanding. However, traditional eye tracking methods are either expensive, uncomfortable, or invasive, making them impractical for wearable applications. Advances in electrooculography (EOG) have made lightweight and non-invasive eye tracking increasingly practical, but current ... Read More

Conjugated polymers (CPs) are promising materials for electronic and sensor applications. However, current methods of catalyst-transfer polymerization (CTP) can only produce a small range of CPs, limiting the use of the technology. Additionally, current step-growth polymerization techniques lack control, and the most promising CPs are too complex to synthesize efficiently. This study proposes a polymer characterized by a π-conjugated backbone ... Read More

This project focuses on developing the 1502 Cleaning Supplies Website, a digital system designed to improve how cleaning materials are organized, tracked, and accessed in the 1502 RC Office. While the current housekeeping process functions adequately, students often experience difficulty locating supplies or determining what materials are available. These inefficiencies can slow daily routines and create confusion among residents. The ... Read More

This project examines the alignment between artificial intelligence credentialing programs and the practical application of AI across major industries, including education, healthcare, technology, transportation, finance, manufacturing, agriculture, and energy. As AI tools become increasingly integrated into professional environments, the demand for standardized training and certification has grown significantly. However, a potential gap may exist between the skills these programs advertise ... Read More

A neuromuscular junction is a specialized cell system in our body where neuronal signals from the brain innervate muscle fibers responsible for flexion and extension. Repetitive muscle contractions lead to a depletion of calcium storage, causing muscle fatigue. Understanding SR release, SERCA pumping (moving calcium ions back to the SR), buffering, and the role played by calcium cycling is critical ... Read More

Traditional game AI architectures, including Finite State Machines (FSMs) and behavior trees, face significant scalability limitations as game environments grow more complex, requiring developers to manually script each behavioral state and transition. Goal-Oriented Action Planning (GOAP) introduced declarative planning to games but brought computational overhead and complex authoring requirements. This project proposes an ABL-style (A Behavior Language) reactive planning system ... Read More

Computer vision models are algorithms that classify and interpret images, typically through neural networks trained with machine learning. One common application of computer vision is in drones, which are being used for surveillance, defense, and traffic monitoring. Computer vision models can often be vulnerable to adversarial patches attacks. Adversarial patches are created to deceive object detection systems into causing objects ... Read More

Transformers are a type of neural network designed to process sequential data all at once rather than in order. Today, they have applications in everything from chatbots to translational tools, yet we continue to formulate a clear mathematical understanding of how they process information. Existing studies demonstrate transformer functionality, but do not investigate them from first-principles. This study applies an ... Read More

Recent developments in artificial intelligence enable machine learning algorithms to learn representations of complex information, including language and sounds, in a numerical format. This project seeks to examine if emotional information presented in text can be related to emotional information presented in audio signals. Emotional states presented in text were converted into semantic embeddings using a transformer-based language model, whereas ... Read More

The aim of this study was to evaluate and design machine learning models to perform gesture classification on Electromyography(EMG) signals. EMG signals are the electrical activity produced by neurons to stimulate and manipulate muscles. These signals have become a central modality for decoding human motor intent in applications such as prosthetic control and human-machine interaction. However, these signals are inherently ... Read More

Extreme rainfall is becoming more frequent and is increasing the risk of transportation disruptions that can delay access to healthcare. Previous studies have measured regions based on different risk indicators in a flood plain. Another study uses these same factors in determining road network access during a flood during COVID-19. This study quantifies the impact of flooding on population accessibility ... Read More

The growing presence of drones enables their use as embodied AI assistants for routine tasks. However, users often lack programming or piloting expertise, necessitating interfaces that facilitate high-level interactions. Although extended reality (XR) has been used to control flight-level drone operation, there is limited understanding of which XR and Agentic AI capabilities are needed for task-level interaction with drone assistants. ... Read More

Catching moving objects represents a fundamental challenge in robotics, requiring the integration of real-time vision, data processing, trajectory prediction, and dynamic control. Numerous previous approaches use onboard vision systems, but this paper instead presents a framework that uses an external motion capture system to achieve highly precise tracking and interception of a moving ball. An OptiTrack motion capture system provides ... Read More

Autonomous driving technologies have the potential to revolutionize transportation by reducing accidents, improving traffic efficiency, decreasing fuel consumption, and increasing mobility. An autonomous vehicle’s ability to generate a safe future trajectory depends on several subsystems, including environment perception, intention prediction, trajectory prediction, and planning. However, many of these subsystems are challenged in construction zones, where environments are complex, cluttered, and ... Read More