Open Access. Powered by Scholars. Published by Universities.®
- Discipline
-
- Electrical and Computer Engineering (40)
- Hardware Systems (32)
- Digital Communications and Networking (31)
- Computer and Systems Architecture (25)
- Other Electrical and Computer Engineering (21)
-
- Computational Engineering (17)
- Physical Sciences and Mathematics (16)
- Data Storage Systems (15)
- Robotics (15)
- Computer Sciences (12)
- Electrical and Electronics (10)
- Mechanical Engineering (10)
- Arts and Humanities (9)
- Digital Circuits (8)
- Signal Processing (8)
- Education (7)
- Controls and Control Theory (6)
- Social and Behavioral Sciences (6)
- VLSI and Circuits, Embedded and Hardware Systems (6)
- Other Computer Sciences (5)
- Art and Design (4)
- Business (4)
- Graphics and Human Computer Interfaces (4)
- Other Mechanical Engineering (4)
- Software Engineering (4)
- Systems and Communications (4)
- Aerospace Engineering (3)
- Keyword
-
- Machine Learning (11)
- Computer Vision (10)
- Android (9)
- Game (9)
- Arduino (8)
-
- IOS (8)
- Artificial Intelligence (7)
- Software (7)
- AI (6)
- App (6)
- Bluetooth (6)
- Web (6)
- Education (5)
- Graphics (5)
- Java (5)
- Linux (5)
- Unity (5)
- Database (4)
- Mobile (4)
- Music (4)
- Virtual Reality (4)
- Website (4)
- Application (3)
- Audio (3)
- Cloud (3)
- Computer vision (3)
- Deep Learning (3)
- Drone (3)
- GUI (3)
- JavaScript (3)
- Publication Year
- Publication
- Publication Type
Articles 1 - 30 of 271
Full-Text Articles in Other Computer Engineering
Hyperchaotic Noise Generation For Adversarial Encryption In Privacy-Preserving Image Classification, Neeraja Beesetti
Hyperchaotic Noise Generation For Adversarial Encryption In Privacy-Preserving Image Classification, Neeraja Beesetti
Master's Theses
Artificial intelligence systems make useful predictions by taking in data and returning a classification, recommendation, or decision. Obtaining that prediction, however, requires sharing the data first. This creates a fundamental privacy challenge in machine learning: users must expose their data to receive a valuable prediction. Machine learning systems increasingly rely on cloud-based image classification for this reason, transmitting images from edge devices to remote servers rather than running large models locally. This creates a conflict between the accuracy a classifier requires and the privacy a data owner wants. Traditional encryption destroys the image structure on which a classifier depends, while …
Reproducing And Evaluating Charger Surfing: Robustness Of Smartphone Charging-Line Side-Channels, Colby M. Watts
Reproducing And Evaluating Charger Surfing: Robustness Of Smartphone Charging-Line Side-Channels, Colby M. Watts
Master's Theses
Smartphones are frequently connected to external, untrusted charging hardware, creating opportunities for side-channel attacks that do not require malware or direct access to device data. Charger Surfing, a recently proposed charging-line power analysis side-channel attack, reported high accuracy in inferring touchscreen input from voltage measurements collected from a smartphone’s charging cable; however, the reproducibility and robustness of these results under different conditions remain unclear. This thesis presents an independent replication and evaluation of Charger Surfing, including the development of an end-to-end data collection pipeline consisting of a modified charging cable, oscilloscope-based recordings, custom Android app, automated trace processing, and convolutional …
Polysaber: A Custom Reactive Lightsaber Soundboard, Pedro B. Medeiros
Polysaber: A Custom Reactive Lightsaber Soundboard, Pedro B. Medeiros
Computer Engineering
The PolySaber project was developed as a custom reactive lightsaber control system built as a fully custom PCB design. The purpose of the project was to create a lower-cost and more customizable alternative to commercially available lightsaber soundboards while simultaneously providing hands-on experience in PCB design, embedded systems development, and hardware integration. Commercial lightsaber soundboards are expensive, proprietary, and difficult for hobbyists to customize. The PolySaber project addresses this by creating a modifiable hardware platform built around the ESP32 microcontroller. The system supports programmable firmware, RGB NeoPixel blade control, motion sensing, reactive swing and clash effects, onboard audio amplification, and …
Design And Parametric Study Of A Mems-Based Reservoir Computer For Reinforcement Learning, Andrew P. Carr
Design And Parametric Study Of A Mems-Based Reservoir Computer For Reinforcement Learning, Andrew P. Carr
Master's Theses
Single-node reservoir computing (RC) is a hardware-efficient approach to machine learning, leveraging the dynamics of physical systems. In this work, two reinforcement learning algorithms, Q-learning and Proximal Policy Optimization (PPO), are applied to a simulated micro-electro-mechanical system (MEMS)-based reservoir computer to solve both discrete and continuous control tasks. MEMS-based reservoirs are low-power, compact, and their natural frequencies (kHz to MHz) pair well with real-time control loops. To explore the relationship between reservoir dynamics and learning performance, a parametric study is conducted on two reservoir hyperparameters, reservoir size and neuron separation, using CartPole-v1 and MountainCar-v0. The RC successfully learns multiple tasks …
Trustworthy Intelligence Fusion For Search And Rescue: Designing Grounded And Secure Multi-Agent Ai For Mission Decision Support, Yayun Tan
Master's Theses
Search and rescue (SAR) operations require teams to integrate uncertain information under severe time pressure. Large language model (LLM)-based multi-agent systems (MAS) can support decision-making, but they also risk producing hallucinated outputs and processing unreliable or malicious data. This thesis addresses these risks through three linked studies. First, it proposes a modular eight-agent SAR MAS architecture that reflects the structure of real SAR missions by assigning specialized roles to different agents. Second, it introduces a post-hoc probabilistic verification framework that checks LLM agent outputs against a probabilistic knowledge graph built from historical SAR incidents. Third, the thesis examines indirect adversarial …
Mozgus, Damian Cerda, Madison Lopez
Mozgus, Damian Cerda, Madison Lopez
Computer Science and Software Engineering
The indie game market is flooded with genre experiments, yet few successfully combine fast-paced action with meaningful strategic decision-making. Our project aims to fill this gap by creating a game that fuses top-down action combat with resource-management tycoon mechanics. We found that in many games, the management phases lack mechanical stakes. Our goal was to intertwine these systems so that choices made in one phase meaningfully impact the other.
Ai-Powered Accessibility Tracker For Inclusive Public Spaces, Yenny Ma, Kevin Beltran
Ai-Powered Accessibility Tracker For Inclusive Public Spaces, Yenny Ma, Kevin Beltran
College of Engineering Summer Undergraduate Research Program
This research project will develop and evaluate a smartphone-based, AI-powered system to crowdsource and analyze accessibility features and barriers in public spaces. Using computer vision and geospatial mapping, the system will identify and categorize issues such as uneven sidewalks, missing or inadequate curb ramps, damaged tactile paving, obstructive overhangs, and the absence of visual or auditory wayfinding cues. The overarching goal is to generate a dynamic, real-time accessibility map that empowers individuals with diverse mobility, sensory, and cognitive needs to navigate public spaces more safely and confidently. The project will integrate technologies and methods from applied machine learning, mobile computer …
Ai Agents For Search And Rescue (Ai4sar), Nathan Huang, Lakshana Viswa
Ai Agents For Search And Rescue (Ai4sar), Nathan Huang, Lakshana Viswa
College of Engineering Summer Undergraduate Research Program
The goal of this summer research activity is to expand the capabilities of a system developed in the larger AI in Search and Rescue project. This project supports volunteer organizations participating in the search for missing persons by providing a basic framework for the collection and organization of relevant information, augmented with specific components that utilize a variety of AI methods. The focus of the summer research will be on the development of agent components for selected roles and tasks in a search and rescue mission. The agents utilize generative AI methods such as Large Language Models (LLMs) to provide …
How Does User Control Reduce Irritation Of Mid-Roll Ads, Elijah Villanueva
How Does User Control Reduce Irritation Of Mid-Roll Ads, Elijah Villanueva
College of Engineering Summer Undergraduate Research Program
Large video platforms like YouTube and Twitch rely extensively on advertising for revenue. Often, they deploy mid-roll advertising: ads that play in the middle of video content, interrupting it. Such interruptions can irritate consumers significantly. This project primarily involves conducting user testing of an already-developed YouTube browser extension that that gives users some control over when mid-roll ads play. We hope to ascertain how effectively the design mitigates user irritation from mid-roll ads. Tasks will involve recruiting people into a laboratory setting where they will use the browser extension, interviewing them about their experience, and manually extracting themes from the …
Approximating The Maximum Weighted Independent Set Problem Empirically, Sue Sue
Approximating The Maximum Weighted Independent Set Problem Empirically, Sue Sue
College of Engineering Summer Undergraduate Research Program
In this project we investigate approximation algorithms for the maximum weighted independent set (MWIS) problem in random graphs that approximate real-world graphs, such as social networks. The problem involves finding a large collection of nodes in a network (vertices in a graph) such that no two nodes are directly connected to one another. Applications of the MWIS problem are broad and include clique-finding algorithms as well as the use of large independent sets in distributed algorithms. We build on prior work by the mentor with a SURP 2024 and senior project, in which preliminary findings suggested that a standard greedy …
Building Pathways To Computer Science Careers For Latinx Students Through Multilingual Collaborative Block-Based Programming, Valerie Ponce, Priscilla Garcia
Building Pathways To Computer Science Careers For Latinx Students Through Multilingual Collaborative Block-Based Programming, Valerie Ponce, Priscilla Garcia
College of Engineering Summer Undergraduate Research Program
The underrepresentation of Latinx students in computer science highlights the need for innovative and inclusive educational approaches. This project addresses challenges such as limited access to educational resources and the demand for multilingual learning tools by developing a co-located, collaborative, game-based programming environment. Designed for use on phones, tablets, and laptops, this tool supports English, Spanish, and Mixtec, facilitating broader engagement. By promoting peer collaboration and interactive learning, our approach challenges traditional notions of solitary programming and reinforces the idea that expertise is shared, fostering an inclusive and equitable learning environment.
Mastering Undergraduate Algorithms: Improving Problem-Solving Skills And Fluency Through Scaffolding Learning Modules, Anissa Soungpanya
Mastering Undergraduate Algorithms: Improving Problem-Solving Skills And Fluency Through Scaffolding Learning Modules, Anissa Soungpanya
College of Engineering Summer Undergraduate Research Program
The primary objective of the undergraduate algorithms course is to equip students with the ability to design and analyze algorithms, prove theorems about computation, and effectively communicate these algorithms and proofs to a human audience. In addition, the course aims to help students foster their fluency in the process of formulating and solving computational problems. Scaffolding exercises and activities that focus on these aspects could serve as useful learning tools in providing targeted feedback and helping students develop their confidence and fluency. To address the challenges that students encounter when solving algorithmic problems -- particularly in regard to problem decomposition …
Augmented Reality Application For Real-Time Coastal Data Visualization, Nithyasri Palanisamy
Augmented Reality Application For Real-Time Coastal Data Visualization, Nithyasri Palanisamy
College of Engineering Summer Undergraduate Research Program
This project aims to develop an Augmented Reality (AR) application that overlays real-time coastal environmental data onto physical landscapes when viewed through AR devices such as smartphones and mixed reality headsets. By integrating data from machine learning models, computer vision-based event detection, coastal sensors, and geospatial mapping technologies, the application will provide users with an immersive and interactive experience, enhancing their understanding of coastal dynamics and environmental changes. The application will focus on observing coastal phenomena such as rip currents, tracking endangered coastal species and marine mammals, monitoring crowd levels on beaches, etc. Data sources will include NOAA's National Data …
Machine Unlearning: The Right To Be Forgotten, Colin Ngo
Machine Unlearning: The Right To Be Forgotten, Colin Ngo
College of Engineering Summer Undergraduate Research Program
The objective of this SURP proposal is to investigate machine unlearning as a viable approach to support the right to be forgotten in artificial intelligence (AI) systems, many of which rely heavily on personal data. The capability to selectively remove user-specific information upon request—without necessitating full model retraining—is critical for safeguarding individual privacy and enhancing computational and energy efficiency. This project will undertake a systematic review of state-of-the-art unlearning techniques, evaluate their performance using standard benchmark datasets, and assess their feasibility in real-world applications. In addition, the project will provide participating students with practical experience in implementing and analyzing machine …
Relational Algebra Interpreter, Sydney Lynch
Relational Algebra Interpreter, Sydney Lynch
College of Engineering Summer Undergraduate Research Program
We would like to build a compiler for relational algebra that converts it to SQL. This compiler will be used in database labs to give the students hands-on experience to write relational algebra code. Current relational algebra compilers that are open source are not very good and are hard for the students to use.
Hand-Tracking And Extended Reality Interfa, Alexander Bloomer, Alberto Cornejo
Hand-Tracking And Extended Reality Interfa, Alexander Bloomer, Alberto Cornejo
College of Engineering Summer Undergraduate Research Program
This project explores the use of Extended Reality (XR) technologies to enhance human- robot interaction in industrial contexts. Building upon prior research in affective and cognitive state recognition during human-cobot collaboration, this study investigates how natural hand and head gestures, captured through Meta Quest passthrough mode, can be used to communicate human intent to a Universal Robotics e-Series collaborative robot. The XR system provides users with an immersive, real-world visual interface while tracking motion and position in real time. The captured gestures are interpreted through a custom software pipeline that integrates machine learning models and rule-based logic to trigger adaptive …
Ai Fact-Checking Claims In Videos, Jake Altieri
Ai Fact-Checking Claims In Videos, Jake Altieri
College of Engineering Summer Undergraduate Research Program
This project investigates the use of acoustic signals captured during Fused Deposition Modeling (FDM) 3D printing to predict part quality and detect process anomalies. Traditional quality monitoring in FDM often relies on visual inspection or post-process evaluation, which can be slow and inconsistent. This research explores a low-cost, non-contact alternative using microphones and accelerometers to capture real-time audio and vibration signatures of the printing process. By applying signal processing and machine learning techniques to these acoustic signals, the project aims to classify part quality and identify defects such as under-extrusion, layer misalignment, or nozzle clogging. The outcomes have potential applications …
Deterministic Motion Planning For Highly Articulated Multi-Link Robots, Matthew Flynn
Deterministic Motion Planning For Highly Articulated Multi-Link Robots, Matthew Flynn
College of Engineering Summer Undergraduate Research Program
Slender, multi-link, highly articulated, and extensible robots designed for minimally invasive surgeries have the potential to significantly transform the performance of common medical procedures. These advanced robots can reduce uncertainties and risks associated with surgeries, leading to shorter patient recovery times, accelerated healing, and minimized scarring. Made possible by their numerous mechanical linkages and concentric mechanisms, these multi-link articulated robots can navigate along non-linear paths, a capability that traditional straight probes lack. This flexibility allows surgeons to perform minimally invasive procedures on clinically significant targets that were previously difficult or impossible to access while avoiding vital anatomical structures. Beyond their …
Math+Cs Integrated Curriculum For K-12 Computer Science Education, Amogh Arora
Math+Cs Integrated Curriculum For K-12 Computer Science Education, Amogh Arora
College of Engineering Summer Undergraduate Research Program
This is a proposal for an activity to initiate an effort to create a series of X+CS integrated curricula for learning Computer Science (CS) in K-12. As a start, we examine Mathematics and CS standards, to find the cross-cutting concepts between the two fields. By leveraging these concepts, we bring to the foreground the ways CS can be used in the mathematical context. The goal for this research is to create a 15-week teacher training curriculum that will expose teachers to the CS concepts of Abstraction, Data Representation, Problem Comprehension and Decomposition, Control Structures, Functions and Generalization. Historically, Mathematics and …
Analysis Of Student Inclusivity In Computing Education: Eeg-Based Prediction Of Student Belonging, Alec Odell
Analysis Of Student Inclusivity In Computing Education: Eeg-Based Prediction Of Student Belonging, Alec Odell
College of Engineering Summer Undergraduate Research Program
This project focuses on the use of Natural Language Processing (NLP) techniques to analyze text stimuli used in cognitive research. Specifically, the project involves analyzing text that presents different types of mindsets, such as growth and fixed mindsets, to understand their impact on cognitive state. Students will apply various NLP methods, such as tokenization, text classification, and sentiment analysis, to analyze the language used in different types of mindset stimuli. The goal is to understand how text-based stimuli can influence cognitive responses and to extract meaningful features from the text that can be used to predict outcomes like engagement or …
Analyzing Privacy And Usability Tradeoffs In Multi-Party Relay Systems, Jess Alencaster, Leticia Leon-Rodriguez
Analyzing Privacy And Usability Tradeoffs In Multi-Party Relay Systems, Jess Alencaster, Leticia Leon-Rodriguez
College of Engineering Summer Undergraduate Research Program
Nearly everything we do on the Internet leaves a trace, and in recent decades the value of user data has proven to be highly profitable and become a fundamental business strategy of the Internet. The only recourse users have in this situation is seeking increased privacy, yet privacy is uniquely challenging on the Internet because we inherently rely on others (e.g., ISPs, content providers, CDNs) to carry and serve our traffic. Recent systems have sought to enhance user privacy without sacrificing performance by adopting Multi-Party Relay (MPR) architectures, including Apple's iCloud Private Relay. These architectures mask user IP addresses by …
Enhancing Non-Player Character Dialogue In Video Gages: An Evaluation Of Large Language Model-Generated Responses, Lam P. Quach
Enhancing Non-Player Character Dialogue In Video Gages: An Evaluation Of Large Language Model-Generated Responses, Lam P. Quach
Master's Theses
As video games increasingly emphasize narrative depth and player immersion, the quality of Non-Player Character (NPC) dialogue has become crucial for creating engaging gaming experiences. This thesis investigates the potential of Large Language Models (LLMs) to generate high-quality NPC dialogue by comprehensively evaluating four state-of-the-art models: Gemma 3 27B, Mistral 7B, QWEN 2.5, and LLAMA 3.1. The study employs a mixed-methods approach, combining human evaluation (N=50 participants) with AI-based assessment across five key benchmarks: coherence, personality expression, engagement, style/tone appropriateness, and overall quality. Participants evaluated 32 dialogue samples (8 per model) generated for a fantasy game context featuring two distinct …
Simulated Live Studio Audience, Theodore David Shellenberger
Simulated Live Studio Audience, Theodore David Shellenberger
Computer Engineering
The Simulated Live Studio Audience is a Python based application that utilizes Vosk, Roboflow, and Llama 3.2 to provide a user with auditory feedback based upon both visual and audible input from their device's microphone and camera. This system functions with a custom trained computer vision model to detect a specified object and when individuals walk in and out of the camera frame, outputting sitcom style simulated crowd reaction sounds accordingly. The simulated studio audience program also takes in vocal input from users, converts it to text, and, using a large language model, analyzes it for content that can be …
Analyzing Player Difficulty Perception In Platformers Through Procedural Level Generation, Sasank Madineni
Analyzing Player Difficulty Perception In Platformers Through Procedural Level Generation, Sasank Madineni
Master's Theses
Games utilizing Procedural Level Generation (PLG), such as Roguelikes, are becoming increasingly popular in today's gaming sphere. In games employing PLG, levels are generated randomly or pseudo-randomly, and aim to retain player attention through variance in levels between playthroughs. However, when generating levels with variance in structure and design, player enjoyment is often a mixed bag. With low enjoyment, player retention for these games can dwindle. This study explores the efficacy of real-time difficulty adjustment in procedurally generated platformers, as a method for maintaining stable player enjoyment without causing frustration. This thesis focuses on creating a short user experience, MIMEVA, …
Deeppanorf: Deep Prior For Neural 3d Reconstruction From Sparse Panoramas, Edward Du
Deeppanorf: Deep Prior For Neural 3d Reconstruction From Sparse Panoramas, Edward Du
Master's Theses
Advances in neural field representations have led to a significant improvement in view synthesis quality. However, many current novel view synthesis methods rely on a dense set of input views, which can be impractical and inefficient in real-world applications. We propose DeepPanoRF, a novel method for 360◦ scene reconstruction from a sparse set of input equirectangular panoramas. Built upon K-Planes, a radiance field representation that encodes explicit features on orthogonal feature planes, our method does not directly learn feature grids. Instead, we parameterize the feature grids to enable sparse view reconstruction without pretraining or additional regularization. We implement a custom …
Optimizing Resume Authenticity And Ats Compatibility With Llm Feedback Integration, Katie He, Justin Lau
Optimizing Resume Authenticity And Ats Compatibility With Llm Feedback Integration, Katie He, Justin Lau
College of Engineering Summer Undergraduate Research Program
Resume generation using Large Language Models (LLMs) like ChatGPT is becoming increasingly popular for automating the creation of customized resumes, but significant user modification is often required before submission. Common issues include poor alignment with job descriptions, inflated qualifications, and lack of authenticity, which undermine the effectiveness of LLM-generated resumes. This project addresses these challenges by integrating feedback from Applicant Tracking Systems (ATS) to guide LLMs in producing resumes that accurately reflect an applicant’s qualifications and better align with job-specific requirements. By optimizing the model's output through ATS feedback, the project aims to create more authentic, tailored, and ATS-compatible resumes, …
Enhancing Semantic Search With Human-Crafted Knowledge In Sentence Embeddings, Zachary Weinfeld
Enhancing Semantic Search With Human-Crafted Knowledge In Sentence Embeddings, Zachary Weinfeld
College of Engineering Summer Undergraduate Research Program
Semantic search plays a critical role in many domains, with numerous algorithms developed to address it. A common approach involves using sentence transformers to generate embeddings for both search queries and documents, allowing for the comparison of their vectors. While many different embedding models are widely used, our approach integrates these models with human-crafted knowledge in a novel way, resulting in an improvement in the Mean Average Precision (MAP) scores. Traditional embeddings often rely heavily on the specific words used in a query or document. Our technique mitigates this dependency by refining the vectors to capture the overall semantic meaning, …
Advanced Grasping Sensor Technologies For Autonomous Robotic Apple Harvesting Using Tactile Data And Cnns, Chris Bae
College of Engineering Summer Undergraduate Research Program
This research investigates how to achieve an optimal grasp of an apple using a four-finger soft robotic grasper equipped with force-resistive sensors. Specifically, we sought to determine whether a convolutional neural network (CNN) could accurately classify the grasper's state and recommend adjustments ("in," "out," or "good" grasp) based on tactile data from the sensors. Spatiotemporal tactile images were developed from the sensors and fed into our CNN, achieving near 100% accuracy on unseen test data. This work suggests that CNN-based processing of tactile images can be a powerful tool for real-time control of soft robotic grippers.
Ai Integration For Intellisar, Eric Lee
Ai Integration For Intellisar, Eric Lee
College of Engineering Summer Undergraduate Research Program
IntelliSAR aims to integrate AI techniques into Search and Rescue (SAR) operations, building on the foundation laid by previous SURP initiatives. IntelliSAR’s core elements include a front-end for SAR forms, a comprehensive command center dashboard, and AI-driven components designed to enhance SAR decision-making. During summer, our efforts focused on streamlining the user interface by integrating various machine learning models into a unified, interactive dashboard. Our models predict critical factors such as missing persons’ behavior, potential locations, and resource requirements, with the goal of optimizing response times and improving the effectiveness of SAR teams.
Deep-Learning Based Microstructure Reconstruction And Generation, Cameron J. Maloney, Lucas Taliaferro
Deep-Learning Based Microstructure Reconstruction And Generation, Cameron J. Maloney, Lucas Taliaferro
College of Engineering Summer Undergraduate Research Program
Characterizing the microstructural behavior of materials is crucial for understanding their properties and performance. Traditional imaging methods, such as optical microscopy and electron microscopy, are effective but costly and time-consuming. Computational approaches can reduce costs and time while expanding the accessibility of microstructural analysis through the generation of new microstructure images. Traditional computational approaches, namely descriptor-based approaches, are slow but effective in low-data scenarios. Modern approaches use machine learning (ML), which is faster but often requires a lot of data to approach the performance of descriptor-based methods. This research leverages a special data-efficient Generative Adversarial Network (GAN) architecture to artificially …