Digital Commons Network^™

Modeling Causal Interactions Across Brain Functional Systems For Population-Specific Disease Analysis, Alissen Moreno

Theses and Dissertations

Functional brain connectivity provides critical insight into neural mechanisms underlying neurodegenerative and affective disorders. Traditional neuroimaging studies rely on undirected or region-specific connectivity measures developed predominantly using racially homogeneous cohorts, limiting fairness and generalizability across diverse populations.

We propose a population-aware framework modeling directed causal interactions across large-scale brain functional subnetworks. Resting-state fMRI data from the HABS-HD cohort were used to construct subject-level causal connectivity matrices via ICA-LiNGAM, aggregated into interpretable system-level hyper-connectomes representing interactions among eleven canonical brain subsystems. These features trained nonlinear models for Alzheimer’s disease stage classification and trait worry prediction.

Results demonstrate that MLP models outperform …

Agentcite: Trustworthy Ai Agents For Information Verification Across Referenced Documents, Eymen Yigit

Master's Theses

This thesis presents AgentCite, a multi-agent framework for automated verification of referenced numerical data in research documents. The framework employs a hybrid design in which LLM-based agents handle document understanding and evidence retrieval, while deterministic components manage structured parsing and value comparison, improving consistency and reproducibility while reducing token consumption and execution time compared to fully agentic approaches.

AgentCite consists of three autonomous agents: a Negotiator, a Main Document Agent, and a Source Documents Agent, coordinated through a fixed tool-call pipeline. The Negotiator orchestrates verification by extracting tabular data from the main document, retrieving evidence from per-source vector stores, and …

Probing Representational Emergence In Large Language Models, Shawn Ismail

Master's Theses

This thesis investigates whether abrupt behavioral gains in large language models under scaling are accompanied by systematic changes in internal representations. It combines a behavioral screen of 65 tasks per family with targeted layerwise probing across eight decoder-only, open-weight model families. Behavioral emergence is defined for each family-task trajectory using an empirical jump detector, with segmented regression retained only as a diagnostic. The representational follow-up analyzes 27 selected MMLU subtasks shared across all families, spanning 37 checkpoints and 216 family-task units.

For each follow-up checkpoint, frozen linear probes are trained on every layer's hidden states to measure how much task-relevant …

Federated Neuromorphic Intelligence: Advancing Robustness, Efficiency, And Continual Adaptation In Edge Environments, Manh V. Nguyen

Dissertations

This dissertation investigates how spiking neural networks (SNNs) can improve federated edge intelligence by advancing three interconnected goals: communication efficiency, adversarial robustness, and continual adaptation. As edge computing deployments expand across Internet of Things (IoT), sensing, and privacy-sensitive applications, conventional federated learning approaches built around artificial neural networks (ANNs) face growing limitations in power consumption, bandwidth demand, and resilience to real-world uncertainty. SNNs offer an alternative computational paradigm based on event-driven, sparse, and temporally structured processing that is naturally suited to constrained edge environments. However, their behavior in practical federated settings remains insufficiently understood.

To address this gap, this dissertation …

A Webcam Eye Tracking Infrastructure For Software Engineering Tasks, Zachary M. Kozak

School of Computing: Dissertations, Theses, and Student Research

Performing eye tracking utilizing commodity webcams has been explored for over a decade, but limited camera quality and sensitivity to head movements have hindered its adoption in research settings. Recent advances in consumer-grade webcams and machine learning methods present an opportunity to improve the accuracy of webcam eye tracking and extend the feasibility of studies beyond controlled laboratory environments.

Current popular webcam eye tracking methods restrict implementations to the browser and rely on continuous user interactions for calibration, limiting the kinds of studies that can be conducted. This thesis presents a feature-based gaze prediction system that incorporates eye geometry and …

Leveraging Code Embeddings To Identify And Address Blind Spots In Benchmark Creation, Charles Moloney

School of Computing: Dissertations, Theses, and Student Research

Formal software verification remains critical for early vulnerability detection, yet benchmarking these tools is costly and often reliant on centralized datasets such as SV-COMP. While such repositories enable standardized evaluation, they introduce risks of overfitting and bias, particularly due to first-party benchmark contributions. To address these limitations, we extend ARG-V, our tool for generating SV-COMP-compatible benchmarks from real-world Java code, with a novel approach of using code embedding techniques to selectively sample from mined code. By leveraging Nomic Embed Code and a cosine-based Minimum Hyperspherical Energy (MHE) objective, we systematically select and transform benchmarks from scraped GitHub code that …

Generalizable Adaptation For Vision-Language Models, Niloufar Alipour Talemi

All Dissertations

Vision-Language Models (VLMs) and Multimodal Large Language Models (MLLMs) have recently emerged as powerful frameworks for learning joint representations across visual and textual modalities. These models enable a wide range of applications, including visual recognition, multimodal reasoning, and visual question answering. However, adapting large pre-trained VLMs to downstream tasks while preserving their strong generalization ability remains a significant challenge, particularly under domain shifts or limited supervision. This dissertation focuses on developing methods for generalizable adaptation of VLMs, aiming to improve robustness, efficiency, and applicability across diverse tasks and environments.

First, this work introduces novel prompt learning strategies for adapting CLIP-style …

Learning Global Context For Sparse Activity Recognition In Lengthy Recordings With Limited Dataset Size, Zeyu Tang

All Dissertations

This dissertation describes methods to analyze lengthy recordings of data in order to detect sparsely occurring activities. The narrative below describes the progression of research that led to the development of these methods and their generalization into a unified framework. My research started with designing models for dietary monitoring, including detecting meals from day-long recordings and detecting intake gestures from meal-length recordings. Both tasks share some common characteristics: (a) the target event takes only a small portion of data recordings, and (b) there is global context within full-length data recordings that can help a model make better decisions. After finishing …

Towards Generalizable Representation Learning Across Domains, Hossein Kashiani

All Dissertations

Despite remarkable progress in deep learning, a major challenge remains: machine learning models often struggle to generalize to unseen domains under distribution shift. In real-world settings, data often differ from training conditions due to changes in lighting, sensor type, image resolution, and style. These differences can significantly degrade performance, highlighting the need for representations that are both robust and generalizable. This thesis addresses this challenge by developing a set of frameworks for generalization across domains in anomaly detection, deepfake detection, and vision-language image recognition. For anomaly detection, this thesis introduces ROADS, a robust prompt-driven framework for multi-class unified anomaly detection. …

Conditioning Hierarchical Diffusion Transformers On Rf Circuit Parameters, Ethan Morton

McKelvey School of Engineering Graduate Student Theses & Dissertations

As modern ML techniques have become increasingly advanced, they have begun to be integrated into wireless RF systems for classification, identification, and spectrum management. Deep Neural Networks (DNNs) enable RF system operators and designers to design more flexible systems with greater robustness to errors and attacks. However, neural networks require significant amounts of properly annotated data to train. Current data labeling methods lack the ability to obtain reliable true labels for circuit properties such as carrier frequency offset (CFO), power amplifier (PA) non-linearity, and in-phase/quadrature (IQ) imbalance. This thesis investigates the efficacy of a novel architecture, RF-Diffusion, for generating high-quality …

The Quality Assurance Machine – A Software Quality Assurance Architecture For Ml-Enabled Systems, Shane E. Downing

All-Inclusive List of Electronic Theses and Dissertations

This dissertation evaluates whether a reusable assurance architecture, the Quality Assurance Machine (QAM), can provide effective product and process quality assurance for ML-enabled software platforms. The QAM is a system-level SQA architecture that turns plans and policies into versioned configurations, executes them in controlled environments, and produces preserved run evidence that supports traceability, auditability, and controlled change. The study follows Design Science Research and evaluates the instantiated artifact using eight assurance requirements (AR1–AR8) synthesized from standards-based guidance, including IEEE 730 and ISO/IEC/IEEE 15026. A four-year longitudinal evaluation combines two methods. First, operational evidence from routine regression and release-validation runs, defect …

Analysis Of Volumetric Reconstruction Methods In Archaeology, Cade O'Fallon

All-Inclusive List of Electronic Theses and Dissertations

The use of Structure from Motion (SfM) photogrammetry in archaeological projects is entering a period of transition; a method of producing 3D data that is traditionally embraced as tool for documentation is being explored for its analytic potential. One such way SfM photogrammetry can be used analytically is through the calculation of volumes using photogrammetric data. The tools exist for archaeologists to be able to create and quantify volumetric models; however, the discourse on these methods is still so new there is no consensus on the best method for conducting volumetric work. Different methods of creating and isolating volumetric space …

Market Reactions To Deceptive Language In Fake News: Implications From Language Expectancy Theory And Transfer Learning, Ka Chung Ng, Ping Fan Ke, Ping Fan, Mike So, Tam, Kar Yan

Research Collection School Of Computing and Information Systems

The advent of generative artificial intelligence (AI) has heightened the proliferation of fake news. A key challenge is the limited real-world data to investigate the societal impact of fake news produced by generative AI. In this paper, we examine stock market reactions to financial news articles that exhibit stylometric similarity to human-crafted and AI-crafted fake financial news. Grounded in language expectancy theory, we employ a style-based transfer learning model, pre-trained to recognizing deceptive language employed in various types of fake news intricacies. We then apply this model to a comprehensive dataset of financial news, assigning a “veracity style score” to …

Enhancing Traffic Safety Through Ai-Driven, Privacy-Preserving, And Secure Impaired Driving Detection Systems, Razan Alsulieman

Dissertations

Drunk driving remains a major threat to road safety worldwide, contributing significantly to traffic injuries and fatalities each year. Traditional detection approaches are largely reactive and vehicle-centric, relying on in-vehicle sensors, breathalyzers, or post-incident enforcement. These methods often depend on driver cooperation, intrusive hardware installations, or limited monitoring environments, restricting their scalability and effectiveness in large transportation systems. At the same time, modern cities increasingly deploy roadside cameras, surveillance networks, and drone- based monitoring systems, creating new opportunities for proactive intoxication detection at the infrastructure level. However, leveraging such external monitoring introduces challenges related to secure data collection, reliable AI-based …

A Survey Of Privacy-Preserving Federated Learning For Intrusion Detection Systems, Thomas Bunko, Michael N. Johnstone, Wencheng Yang, Ben A. Scott

Research outputs 2022 to 2026

Intrusion detection systems (IDS) monitor and detect malicious activity and unauthorized access that may compromise systems. Traditional IDS approaches send data to a central server for analysis, raising privacy concerns as data owners lose control over security. Federated Learning (FL) offers a privacy-preserving alternative by allowing local devices to process their data and generate models without sharing raw data. These local models are aggregated centrally to form a comprehensive model with performance comparable to centralized systems. This paper reviews FL-based IDS research, and is the first review paper to focus on privacy-preserving techniques collectively known as privacy-preserving Federated Learning (PPFL) …

Mease: Multi-Agent Episodic Action Sequence Explanation, Phyo Wai Khaing, Minghong Geng, Shubham Pateria, Budhitama Subagdja, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

Multi-agent reinforcement learning (MARL) achieves remarkable performance in complex coordination tasks, yet interpreting the emergent behaviors of trained agents remains a fundamental challenge. Most current explainability methods focus on individual agent decisions, overlooking the critical interplay of joint strategiesand temporal coordination patterns that define successful multi-agent policies. We present MEASE (Multi-agent Episodic Action Sequence Explanation), a novel explainable MARL (XMARL) framework that explains trained MARL policies as human-interpretable emergent cooperative joint behaviors. MEASE employs a cognition-inspired episodic memory model to learn spatio-temporal multi-agent interaction patterns, coupled with abstraction algorithms that identify significant cooperative agent behaviors. We evaluate MEASE on diverse …

Smart-Charge: Stable Matching Algorithm For Electric Vehicle Charging In Subscription-Based Models, Arindam Khanda, Anurag Satpathy, Sajal K. Das

Computer Science Faculty Research & Creative Works

The transition from internal combustion engine (ICE) to electric vehicles (EVs) introduces several challenges, including limited charging infrastructure, unpredictable charging wait times, and inefficient selection of charging points (CPs). To address these issues, we propose SMART-CHARGE, a framework that efficiently assigns EVs to CPs through an edge-level coordination mechanism within each service region, enforced by roadside units (RSUs). Operating under a novel subscription-based charging model, SMART-CHARGE enforces predefined charging time limits via service-level agreements (SLAs). The EV-CP assignment problem is formulated as a one-to-many matching game that captures EV user preferences. To construct bounded yet efficient EV coalitions at each …

Safepass: Efficient Emergency Vehicle Passage With Minimal Disruption To Traffic Flow, Osho Osho, Suchetana Chakraborty, Sajal K. Das

Computer Science Faculty Research & Creative Works

Emergency vehicle passage in congested urban networks poses a dual challenge: ensuring rapid response while minimizing disruption to surrounding traffic. This study addresses this challenge in the context of Connected Autonomous Emergency Vehicles (CA-EVs), proposing SafePass , a lightweight distributed framework for seamless CA-EV passage through decentralized, cooperative maneuvering of surrounding Connected Autonomous Non-Emergency Vehicles (CA-NEVs). At its core, SafePass employs the Target Lane Potential (TLP), a novel utility-based metric combining lane-choice utility with probabilistic gap acceptance, augmented by a cascade-aware penalty that suppresses upstream shockwaves triggered by gap-creation maneuvers. Evaluated in Simulation of Urban Mobility (SUMO) using synthetic traffic …

Quantitative Bounds On Resource Usage Of Probabilistic Programs, Krishnendu Chatterjee, Amir Kafshdar Goharshady, Tobias Meggendorfer, Dorde Zikelic

Research Collection School Of Computing and Information Systems

Cost analysis, also known as resource usage analysis, is the task of finding bounds on the total cost of a program and is a well-studied problem in static analysis. In this work, we consider two classical quantitative problems in cost analysis for probabilistic programs. The first problem is to find a bound on the expected total cost of the program. This is a natural measure for the resource usage of the program and can also be directly applied to average-case runtime analysis. The second problem asks for a tail bound, i.e. ‍given a threshold t the goal is to find …

Collaborative Practices And Tool Utilization In Software Development Projects: A Student Perspective, Yi Meng Lau, Muhammad Syahmi Bin Abbas, Lingxiao Jiang

Research Collection School Of Computing and Information Systems

Software development is a collaborative activity that depends on effective teamwork, shared understanding, and coordinated use of development practices and tools. While these aspects are well studied in professional environments, they are less frequently examined within software engineering education. This study investigates how students collaborate in group projects, focusing on collaborative practices, tool usage, and their perceptions of software quality. We conducted a quantitative post-project survey with 143 second-year undergraduate students enrolled in a software development course. The results show that students actively share information and often establish team norms to support coordination and collaboration. However, students face challenges in …

Causality-Driven Test Case Minimisation For Cyber-Physical Systems, Michael Foster, Christopher M. Poskitt, Nicholas R. Latimer, Neil Walkinshaw, Richard Somers, Robert M. Hierons

Research Collection School Of Computing and Information Systems

Cyber-physical systems allow digital control systems to interact with the physical world using sensors and actuators. They are increasingly being used to automate critical infrastructure, where software faults can have dire consequences. Due to the complex nature and unpredictability of these systems, their resilience is often tested using a technique called fuzzing, which generates quasi-random sequences of sensor and actuator manipulations with the goal of forcing a system into unsafe states. However, there is currently no way of determining which manipulations of a test case cause a failure without systematically removing each one and re-running the test, which can be …

Natural Adversaries: Fuzzing Autonomous Vehicles With Realistic Roadside Object Placements, Yang Sun, Haoyu Wang, Christopher M. Poskitt, Jun Sun

Research Collection School Of Computing and Information Systems

The emergence of Autonomous Vehicles (AVs) has spurred research into testing the resilience of their perception systems, i.e., ensuring that they are not susceptible to critical misjudgements. It is important that these systems are tested not only with respect to other vehicles on the road, but also with respect to objects placed on the roadside. Trash bins, billboards, and greenery are examples of such objects, typically positioned according to guidelines developed for the human visual system, which may not align perfectly with the needs of AVs. Existing tests, however, usually focus on adversarial objects with conspicuous shapes or patches, which …

Enhancing Action And Ingredient Modeling For Semantically Grounded Recipe Generation, Guoshan Liu, Bin Zhu, Yian Li, Jingjing Chen, Chong-Wah Ngo, Yu-Gang Jiang

Research Collection School Of Computing and Information Systems

Recent advances in Multimodal Large Language Models (MLMMs) have enabled recipe generation from food images, yet outputs often contain semantically incorrect actions or ingredients despite high lexical scores (e.g., BLEU, ROUGE). To address this gap, we propose a semantically grounded framework that predicts and validates actions and ingredients as internal context for instruction generation. Our two-stage pipeline combines supervised fine-tuning (SFT) with reinforcement fine-tuning (RFT): SFT builds foundational accuracy using an Action-Reasoning dataset and ingredient corpus, while RFT employs frequency-aware rewards to improve long-tail action prediction and ingredient generalization. A Semantic Confidence Scoring and Rectification (SCSR) module further filters and …

A Study Of Visualized Diagnostics In Early Stage Digital Twin Implementation Of An Industrial Control System, Michael R. Kinzel

All-Inclusive List of Electronic Theses and Dissertations

Industrial Control Systems (ICS) are used for process control in almost all industries. An ICS combines Operational Technologies (OT) with Information Technologies (IT) to allow human supervision of a process through surveillance of process variables and manipulation of controlling elements such as valves to maintain stable process conditions. ICSs have been in-service for several decades and may remain operational past their technological service life. Organizational personnel interact with the ICS through visual displays that both indicate the process variables and also the controlling elements. The Human Machine Interface (HMI) allows visibility of the process and the ability to manipulate controlling …

Ai Institute Summer Camp Webinar Summary, Dora Nguyen

Paul English Applied Artificial Intelligence (AI) Institute Publications

This report summarizes the AI Institute Summer Camp informational webinar hosted by the Paul English Applied Artificial Intelligence Institute (PEAAII) at the University of Massachusetts Boston. The webinar introduced the structure, curriculum, learning objectives, and student outcomes associated with the 2026 AI Institute Summer Camp. In addition to summarizing the webinar content, this report analyzes participant questions, engagement trends, and areas of audience interest. Findings indicate strong interest in coding accessibility, mentorship opportunities, student outcomes, research experiences, and program flexibility. The report also identifies opportunities for improving future webinar delivery, including expanded eligibility guidance, pre-camp learning resources, enhanced presentation of …

Moodify: A Mood-Based Music Recommendation System, Meghana Kagitha

Theses and Dissertations

Music has long been recognised as a powerful tool for emotional regulation, yet existing music streaming platforms often fail to align song recommendations with a user's current emotional state. Moodify is a mood-based music recommendation system designed to bridge this gap by delivering personalised playlists that reflect how a user feels in real time.

This project presents the design, development, and evaluation of Moodify, a mobile application that leverages the Circumplex Model of Emotion to capture user mood through an intuitive two-dimensional valence-arousal interface. Rather than relying on text input or manual search, users plot their emotional state directly onto …

Adaptive Artificial Potential Field Guidance And Control For Autonomous Docking With Uncooperative And Unknown Spacecraft, Steven Holmberg

Theses and Dissertations

The increasing demand for on-orbit servicing (OOS), active debris removal (ADR), and space domain awareness (SDA) missions has increased the need for autonomous spacecraft rendezvous and proximity operations (RPO) with uncooperative and unknown targets. Traditional guidance and control methods are typically designed for cooperative systems with known geometry and state information. This work builds on previous research to develop and evaluate an artificial potential field (APF)-based control framework capable of autonomous operation with minimal prior target knowledge and applicability to both relatively static and tumbling spacecraft.

The proposed APF formulation incorporates established safety constructs from cooperative docking systems, including an …

Adversarial Heterogeneous Agent Learning For Robotic Systems: A Framework For Coordinated Competitive Behaviors, Christopher T. Allred

All Graduate Theses and Dissertations, Fall 2023 to Present

Autonomous robot teams must move reliably, explain their actions, and work together—even in changing or adversarial settings. We present a structured, three-stage pathway that builds coordinated team behavior from strong single-robot skills. First, we develop robust legged-robot locomotion and interpretability using only internal actuator signals. From these proprioceptive cues, robots learn to classify terrain and predict short-term power use, enabling energy-aware movement without external sensors. We further analyze learned behaviors with motif discovery to reveal recurring sensor–action patterns, which clarify how agility emerges and guide reward design. Second, we compose these skills into heterogeneous teamwork using centralized training with decentralized …

Counterfactual Explanations For Time Series Through Local Pattern Mining And Generative Models, Omar Bahri

All Graduate Theses and Dissertations, Fall 2023 to Present

Machine learning systems increasingly make decisions that affect people’s lives, from medical diagnoses to loan approvals. When these systems analyze time series data—sequences of measurements collected over time, such as heart rhythms or sensor readings—users need to understand why a particular prediction was made. Counterfactual explanations address this need by answering “what-if” questions: what would need to change in the input for the system to make a different prediction? 

This dissertation develops methods for generating counterfactual explanations specifically designed for time series data. Time series often contain distinctive local patterns—short subsequences that distinguish one class from another. For example, a …

Advancing Context-Aware Detection Of Socially Harmful Discourse Using Transformer-Based Models, Santosh Chapagain

All Graduate Theses and Dissertations, Fall 2023 to Present

Social media platforms are a central part of modern communication, shaping how people share ideas, build communities, and discuss social issues. While these spaces can support connection and self expression, they also enable the spread of harmful language such as hate speech. At the same time, social media is an important place where members of marginalized communities, including sexual and gender minorities, express stress, discrimination, and emotional challenges in ways that are often indirect and context dependent.

This research examines whether modern artificial intelligence systems can better identify harmful language and expressions of minority stress in online posts. The study …