Computer Sciences Commons^™

Using Machine Learning Models To Improve The Cyber Physical Security Of Drones, Sean Lee, Aviv Segev

Shelby Hall Graduate Research Forum Posters

This research proposes a new manner of implementing machine learning models such that, when applied on a drone, it will be able to accurately identify and maintain the authenticity of the entity sending the control data to the drone. To begin with, the drone will, for a pre-determined amount of signals received per unit time, determine the average signal strength (RSSI) of them and use that average to determine the approximate distance between the drone and the source of those signals. This single data point will be fed into a custom implementation of the SCluStream algorithm (a real-time clustering machine …

Birdie: Natural Language-Driven Table Discovery Using Differentiable Search Index, Yuxiang Guo, Zhonghao Hu, Yuren Mao, Baihua Zheng, Yunjun Gao, Mingwei Zhou

Research Collection School Of Computing and Information Systems

Natural language (NL)-driven table discovery identifies relevant tables from large table repositories based on NL queries. While current deep-learning-based methods using the traditional dense vector search pipeline, i.e., representation-index-search, achieve remarkable accuracy, they face several limitations that impede further performance improvements: (i) the errors accumulated during the table representation and indexing phases affect the subsequent search accuracy; and (ii) insufficient query-table interaction hinders effective semantic alignment, impeding accuracy improvements. In this paper, we propose a novel framework Birdie, using a differentiate search index. It unifies the indexing and search into a single encoder-decoder language model, thus getting rid of error …

Attackg+: Boosting Attack Graph Construction With Large Language Models, Yongheng Zhang, Tingwen Du, Yunshan Ma, Xiang Wang, Yi Xie, Guozheng Yang, Yuliang Lu, Ee‑Chien Chang

Research Collection School Of Computing and Information Systems

Attack graph construction seeks to convert textual cyber threat intelligence (CTI) reports into structuredrepresentations, portraying the evolutionary traces of cyber attacks. Even though previous research hasproposed various methods to construct attack graphs, they generally suffer from limited generalizationcapability to diverse knowledge types as well as requirement of expertise in model design and tuning.Addressing these limitations, we seek to utilize Large Language Models (LLMs), which have achieved enormoussuccess in a broad range of tasks given exceptional capabilities in both language understanding and zeroshot task fulfillment. Thus, we propose a fully automatic LLM-based framework to construct attack graphsnamed: AttacKG+. Our framework consists …

Tla+ For All: Model Checking In A Python Notebook, Konstantin Laufer, George K. Thiruvathukal

Computer Science: Faculty Publications and Other Works

TLA+ is widely recognized for its effectiveness in specifying and verifying concurrent and distributed systems. However, for educators and practitioners, barriers to adoption include installation complexity and tooling setup. In the proposed presentation, we demonstrate a lightweight, easily shareable, and fully reproducible approach to running TLA+ in a Python notebook hosted on Google Colab without requiring new tools or custom Jupyter kernel development. By creating an environment where users can experiment with TLA+ models instantly, we lower these barriers and demonstrate the suitability for education and outreach.

A Causality-Aware Paradigm For Evaluating Creativity Of Multimodal Large Language Models, Zhongzhan Huang, Shanshan Zhong, Pan Zhou, Shanghua Gao, Marink Zitnik, Liang Lin

Research Collection School Of Computing and Information Systems

Recently, numerous benchmarks have been developed to evaluate the logical reasoning abilities of large language models (LLMs). However, assessing the equally important creative capabilities of LLMs is challenging due to the subjective, diverse, and data-scarce nature of creativity, especially in multimodal scenarios. In this paper, we consider the comprehensive pipeline for evaluating the creativity of multimodal LLMs, with a focus on suitable evaluation platforms and methodologies. First, we find the Oogiri game—a creativity-driven task requiring humor, associative thinking, and the ability to produce unexpected responses to text, images, or both. This game aligns well with the input-output structure of modern …

Computing In The Commonwealth: Specialized Education In Computer Science And Information Technology For High School Students In Virginia – An Environmental Scan, Amy Corning, Jonathan D. Becker, Jon Graham, James Carrigan, Keisha Tennessee

ICRE Publications

Over the past two decades, Virginia has invested substantially in STEM education, in part through specialized programs focused on computer science and information technology (CS/IT). This study represents the first effort to identify Virginia’s specialized secondary CS/IT programs and examine them collectively. Findings from the statewide environmental scan indicate that the programs are delivered through a wide variety of institutional structures, including Governor’s STEM Academies, Governor’s Schools, specialty centers, and academies, but most often through Career and Technical Education (CTE) centers. Programs tend to be concentrated in metropolitan areas, and some rural divisions may not be served. The programs provide …

Towards Smart Farming: Image-Based Crop Health Assessment And Disease Diagnosis Using Deep Learning Techniques, Kristina Botova

Master's Theses or Doctor of Nursing Practice

Accurate crop monitoring is essential for optimizing agricultural productivity and ensuring food security. This study presents a comprehensive deep learning framework for image crop type recognition, health status prediction, and disease detection using multiple Convolutional Neural Network (CNN) models. The proposed approach uses open-source datasets consisting of five crop types (apple, corn, grape, potato, tomato), varying health conditions, and common diseases. By deploying specialized CNN architecture focused on each task, the system achieves a high accuracy of 99.25% in classifying crop types, identifying health status, and detecting specific diseases. Compared to a single CNN model, the use of the proposed …

Digital Platform Transitions In The Finance Industry: Three Essays, Cheryll-Ann Wilson

2025

This three-paper dissertation is motivated by an emerging dichotomy in the financial sector: an increasing use of an open-source digital platform—the Python platform—in an industry that historically has been wedded to proprietary systems.

Chapter 1 is a qualitative pilot study to ascertain which factors are likely to motivate investment professionals to select Python versus other tools and/or technologies. I find that efficiency and access to industry-specific libraries—notably Pandas and NumPy—are significant motivators in their selection of Python over Excel. Chapters 2 and 3 examine the issues through a sequential, exploratory mixed methods approach.

Chapter 2—the qualitative field study—investigates how and …

Ultrasonic Sensor-Based Sound Synthesis Using Raspberry Pi Pico W, Niraj Jaishwal

Williams Honors College, Honors Research Projects

At the intersection of Human Computer Interaction and digital art, this project transforms simple motion into musical expression. It explores an interactive real-time sound synthesis system using ultrasonic sensors to generate continuous audio. The objective is to design a system that maps physical distances into musical parameters such as pitch and amplitude, which will create a responsive audio environment. Two ultrasonic sensors are used in combination with the Raspberry Pi Pico W microcontroller running CircuitPython and Adafruit Audio Hat for real-time sound output. One sensor controls the pitch of the generated tone, while the other controls volume. This enables expressive …

Finding Antipatterns Across Languages With Abstract Syntax Trees, Daniel T. Masker

Dissertations, Master's Theses and Master's Reports

Finding antipatterns in student code is a difficult task that is useful for helping beginner programmers. Antipatterns are common mistakes that students make while writing code. Code critiquers are tools that find antipatterns and provide rich, immediate feedback to students, even when professors aren’t available. WebTA is a code critiquer that finds antipatterns using regular expressions (regex), error messages, and language-specific abstract syntax trees (ASTs). Each of these tools has obstacles to antipattern searching that are difficult to overcome. Regex is without context, limiting the patterns it can recognize. Additionally, even experienced users have difficulty reading and debugging regex. Error …

Relational Database Schema To Support Research Profiling Studies, Natural Language Processing, And Bibliometric Analysis, Darnelle Melvin

Library Faculty Research

In this paper, a relational database schema is introduced that supports rapid prototyping, data preprocessing, and warehousing tasks associated with research profiling studies, natural language processing, and bibliometric analysis. Python scripts are leveraged for the seamless retrieval and processing of data from Semantic Scholar. This schema is tailored to efficiently analyze entities such as authors, their scientific papers, referenced papers, and cited papers. Adhering to the relational model, this schema offers a standardized approach to data storage and detailed information retrieval for scientific papers. Enhancing knowledge discovery in scientific databases, this schema provides researchers with a powerful platform for robust …

Bytes, Banter, And The Bible: An Interdisciplinary Account Of Objective Meaning, Cameron Bonin

Senior Honors Theses

The claim that the Bible has objective meaning is contested in a postmodern world. This claim can be more persuasively defended when it is addressed by insights from multiple disciplines. In particular, the field of computer science is apt to illuminate the concept of meaning through its reflection on the nature of languages and its concern with the accurate transmission of information. By synthesizing insights from the field of computer science, such as that of Claude Shannon, with Nicholas Wolterstorff’s use of speech-act theory, the concept of meaning can be understood more clearly. Consequently, this synthesis assists in answering questions …

Individual And Collective Properties Of Tunable Photochemical Belousov-Zhabotinsky Micro-Reactors, Kudakwashe Benedict Shumba

Graduate Theses, Dissertations, and Problem Reports (ETD)

Cell-like model chemical systems are powerful tools that can be used to explore the role of intercellular coupling on population level behaviors in communities of biological cells. Firstly, we present a new method for fabricating such micro-reactors using the photosensitive Belousov–Zhabotinsky (BZ) reaction system employed in silica microparticles. These BZ micro-reactors have a tunable response to photochemical coupling, varying from a fully excitatory response to a fully inhibitory response. Their response can be tuned through variations in either the reactive mixture or, on an individual micro-reactor level, by changes in the synthesis temperature used during the fabrication of the silica …

Financial Named Entity Recognition: How Far Can Llm Go?, Yi-Te Lu, Yintong Huo

Research Collection School Of Computing and Information Systems

The surge of large language models (LLMs) has revolutionized the extraction and analysis of crucial information from a growing volume of financial statements, announcements, and business news. Recognition for named entities to construct structured data poses a significant challenge in analyzing financial documents and is a foundational task for intelligent financial analytics. However, how effective are these generic LLMs and their performance under various prompts are yet need a better understanding. To fill in the blank, we present a systematic evaluation of state-of-the-art LLMs and prompting methods in the financial Named Entity Recognition (NER) problem. Specifically, our experimental results highlight …

Calculation And Statistical Analysis Of Wins Above Replacement, Joshua Taylor

Departmental Honors & Graduate Capstone Projects

The Wins Above Replacement (WAR) statistic in Major League Baseball is a prominent metric used to estimate player value by quantifying all aspects of play in terms of wins added to a baseball team. We will use R to calculate WAR for all players from 1871 to 2012 and use data from those years to construct multivariate predictive models to attempt to estimate WAR for players from 2013 to 2024. We find strong correlations between predicted and actual WAR values for most models, with the exception of the polynomial predictive model for non-qualified pitchers.

Towards Robust, Secure, And Privacy-Aware Large Language Models Of Code, Zhou Yang

Dissertations and Theses Collection (Open Access)

The field of software engineering has witnessed a surge in large language models specifically tailored to understand and process code, which we call large language models for code (LLM4Code). The increasing popularity of LLM4Code is inseparable from three key factors: the availability of extensive datasets compiled from diverse data sources, the advancements in deep learning algorithms and computational power that facilitate the training of these powerful models, and the active engagement and collaboration within the research community fostering innovation and the rapid exchange of ideas and methodologies. As evidenced by a series of studies, LLM4Code has been experiencing rapid development …

Revisiting Masked Auto-Encoders For Ecg-Language Representation Learning, Hung Manh Pham, Aaqib Saeed, Dong Ma

Research Collection School Of Computing and Information Systems

We propose C-MELT, a novel framework for multimodal self-supervised learning of Electrocardiogram (ECG) and text encoders. C-MELT pre-trains a contrastive-enhanced masked auto-encoder architecture using ECG-text paired data. It exploits the generative strengths with improved discriminative capabilities to enable robust cross-modal alignment. This is accomplished through a carefully designed model, loss functions, and a novel negative sampling strategy. Our preliminary experiments demonstrate significant performance improvements with up to 12% in downstream cardiac arrhythmia classification and patient identification tasks. Our findings demonstrate C-MELT's capacity to extract rich, clinically relevant features from ECG-text pairs, paving the way for more accurate and efficient cardiac …

Divlog: Log Parsing With Prompt Enhanced In-Context Learning, Junjielong Xu, Ruichun Yang, Yintong Huo, Chengyu Zhang, Pinjia He

Research Collection School Of Computing and Information Systems

Log parsing, which involves log template extraction from semistructured logs to produce structured logs, is the first and the most critical step in automated log analysis. However, current log parsers suffer from limited effectiveness for two reasons. First, traditional data-driven log parsers solely rely on heuristics or handcrafted features designed by domain experts, which may not consistently perform well on logs from diverse systems. Second, existing supervised log parsers require model tuning, which is often limited to fixed training samples and causes sub-optimal performance across the entire log source. To address this limitation, we propose DivLog, an effective log parsing …

Reevo: Large Language Models As Hyper-Heuristics With Reflective Evolution, Haoran Ye, Jiarui Wang, Zhiguang Cao, Federico Berto, Chuanbo Hua, Haeyeon Kim, Jinkyoo Park, Guojie Song

Research Collection School Of Computing and Information Systems

The omnipresence of NP-hard combinatorial optimization problems (COPs) compels domain experts to engage in trial-and-error heuristic design process. The long-standing endeavor of design automation has gained new momentum with the rise of large language models (LLMs). This paper introduces Language Hyper-Heuristics (LHHs), an emerging variant of Hyper-Heuristics that leverages LLMs for heuristic generation, featuring minimal manual intervention and open-ended heuristic spaces. To empower LHHs, we present Reflective Evolution (ReEvo), a generic searching framework that emulates the reflective design approach of human experts while far surpassing human capabilities with its scalable LLM inference, Internet-scale domain knowledge, and powerful evolutionary search. Evaluations …

Elevating Automated Software Maintenance Tasks With Large Language Models, Xin Zhou

Dissertations and Theses Collection (Open Access)

Software engineering involves many tasks across different phases such as requirements, design, implementation, testing, and maintenance. Among them, software maintenance is a crucial phase, typically accounting for more than half of the software life cycle's duration.
To boost developer productivity, in recent years, numerous research endeavors in software engineering have sought to automate certain software maintenance tasks through the application of machine learning techniques.
Since 2020, the emergence of advanced Large Language Models (LLMs) of code has opened new avenues for enhancing automated solutions in software maintenance.
This dissertation presents a series of works aimed at advancing automated solutions for …

Mm‑Forecast: A Multimodal Approach To Temporal Event Forecasting With Large Language Models, Haoxuan Li, Zhengmao Yang, Yunshan Ma, Yi Bin, Yang Yang, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

We study an emerging and intriguing problem of multimodal temporal event forecasting with large language models. Compared to using text or graph modalities, the investigation of utilizing images for temporal event forecasting has not been fully explored, especially in the era of large language models (LLMs). To bridge this gap, we are particularly interested in two key questions of: 1) why images will help in temporal event forecasting, and 2) how to integrate images into the LLM-based forecasting framework. To answer these research questions, we propose to identify two essential functions that images play in the scenario of temporal event …

Review Of Current Trends In Information Technology Concerning Phonetic Similarity”, Zaid Rajih Mohammed, Ahmed H. Aliwy

Al-Bahir

With the increasing availability of textual information in various languages via the Internet in homes and companies through Internet and intranet services, there is an urgent need for the technologies and tools necessary to process this information, phonetic representation, and voice interaction. For example voice to voice machine translation need to phonetic mapping and similarity among the languages especially for names and foreign words. This one example of the importance of phonetic mapping and similarity. This article aims to describe, in detail, the recent surge in interest and advancements in phonetic similarity (PS), phonetic representation, and phonetic mapping researches. PS …

Wip: An Engaging Undergraduate Intro To Model Checking In Software Engineering Using Tla+, Konstantin Laufer, Gunda Mertin, George K. Thiruvathukal

Computer Science: Faculty Publications and Other Works

Background: In this Innovative Practice Work in Progress, we present our initial efforts to integrate formal methods, with a focus on model-checking specifications written in Temporal Logic of Actions (TLA⁺), into computer science education, targeting undergraduate juniors/seniors and graduate students. Many safety-critical systems and services crucially depend on correct and reliable behavior. Formal methods can play a key role in ensuring correct and safe system behavior, yet remain underutilized in educational and industry contexts.

Aims: We aim to (1) qualitatively assess the state of formal methods in computer science programs, (2) construct level-appropriate examples that could be included …

Interoperability In Deep Learning: A User Survey And Failure Analysis Of Onnx Model Converters, Purvish Jajal, Wenxin Jiang, Arav Tewari, Erik Kocinare, Joseph Woo, Anusha Sarraf, Yung-Hsiang Lu, George Thiruvathukal, James C. Davis

Computer Science: Faculty Publications and Other Works

Software engineers develop, fine-tune, and deploy deep learning (DL) models using a variety of development frameworks and runtime environments. DL model converters move models between frameworks and to runtime environments. Conversion errors compromise model quality and disrupt deployment. However, the failure characteristics of DL model converters are unknown, adding risk when using DL interoperability technologies. This paper analyzes failures in DL model converters. We survey software engineers about DL interoperability tools, use cases, and pain points (N=92). Then, we characterize failures in model converters associated with the main interoperability tool, ONNX (N=200 issues in PyTorch and TensorFlow). Finally, we formulate …

Recasting The Mould – Librarianship Of The Future: Leveraging Automation, Apis, And Ai, Samantha Seah

Research Collection Library

With leaps in artificial intelligence made in recent years redefining the information landscape and introducing new means of information production, librarianship also must evolve to include new literacies. One way librarians can equip and empower ourselves is by understanding the building blocks of how machines and automation work. Perhaps more important than learning specific programming languages, learning computational thinking provides us with more ways to spot and evaluate problems and devise solutions without extensive coding knowledge. My presentation will take the improvement of membership processing as an example using Power Automate, a low-code Microsoft tool mimicking block programming. The tool …

Sound And Complete Witnesses For Template-Based Verification Of Ltl Properties On Polynomial Programs, Krishnendu Chatterjee, Amir Goharshady, Ehsan Goharshady, Mehrdad Karrabi, Dorde Zikelic

Research Collection School Of Computing and Information Systems

We study the classical problem of verifying programs with respect to formal specifications given in the linear temporal logic (LTL). We first present novel sound and complete witnesses for LTL verification over imperative programs. Our witnesses are applicable to both verification (proving) and refutation (finding bugs) settings. We then consider LTL formulas in which atomic propositions can be polynomial constraints and turn our focus to polynomial arithmetic programs, i.e. programs in which every assignment and guard consists only of polynomial expressions. For this setting, we provide an efficient algorithm to automatically synthesize such LTL witnesses. Our synthesis procedure is both …

Self-Chats From Large Language Models Make Small Emotional Support Chatbot Better, Zhonghua Zheng, Lizi Liao, Yang Deng, Libo Qin, Liqiang Nie

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) have shown strong generalization abilities to excel in various tasks, including emotion support conversations. However, deploying such LLMs like GPT-3 (175B parameters) is resource-intensive and challenging at scale. In this study, we utilize LLMs as “Counseling Teacher” to enhance smaller models’ emotion support response abilities, significantly reducing the necessity of scaling up model size. To this end, we first introduce an iterative expansion framework, aiming to prompt the large teacher model to curate an expansive emotion support dialogue dataset. This curated dataset, termed ExTES, encompasses a broad spectrum of scenarios and is crafted with meticulous strategies …

Clamber: A Benchmark Of Identifying And Clarifying Ambiguous Information Needs In Large Language Models, Tong Zhang, Peixin Qin, Yang Deng, Chen Huang, Wenqiang Lei, Junhong Liu, Dingnan Jin, Hongru Liang, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Large language models (LLMs) are increasingly used to meet user information needs, but their effectiveness in dealing with user queries that contain various types of ambiguity remains unknown, ultimately risking user trust and satisfaction. To this end, we introduce CLAMBER, a benchmark for evaluating LLMs using a well-organized taxonomy. Building upon the taxonomy, we construct 12K high-quality data to assess the strengths, weaknesses, and potential risks of various off-the-shelf LLMs.Our findings indicate the limited practical utility of current LLMs in identifying and clarifying ambiguous user queries, even enhanced by chain-of-thought (CoT) and few-shot prompting. These techniques may result in overconfidence …

Larp: Language Audio Relational Pre‑Training For Cold‑Start Playlist Continuation, Rebecca Salganik, Xiaohao Liu, Yunshan Ma, Jian Kang, Tat‑Seng Chua

Research Collection School Of Computing and Information Systems

As online music consumption increasingly shifts towards playlist-based listening, the task of playlist continuation, in which an algorithm suggests songs to extend a playlist in a personalized and musically cohesive manner, has become vital to the success of music streaming services. Currently, many existing playlist continuation approaches rely on collaborative filtering methods to perform their recommendations. However, such methods will struggle to recommend songs that lack interaction data, an issue known as the cold-start problem. Current approaches to this challenge design complex mechanisms for extracting relational signals from sparse collaborative signals and integrating them into content representations. However, these approaches …

Reinforcement Tuning For Detecting Stances And Debunking Rumors Jointly With Large Language Models, Ruichao Yang, Wei Gao, Jing Ma, Hongzhan Ling, Bo Wang

Research Collection School Of Computing and Information Systems

Learning multi-task models for jointly detecting stance and verifying rumors poses challenges due to the need for training data of stance at post level and rumor veracity at claim level, which are difficult to obtain. To address this issue, we leverage large language models (LLMs) as the foundation annotators for the joint stance detection (SD) and rumor verification (RV) tasks, dubbed as JSDRV. We introduce a novel reinforcement tuning framework to enhance the joint predictive capabilities of LLM-based SD and RV components. Specifically, we devise a policy for selecting LLM-annotated data at the two levels, employing a hybrid reward mechanism …