Computer Sciences Commons^™

Leveraging Deep Learning Recurrence And Attention Mechanisms For Flood Forecasting And Assessment, Elnaz Heidari

All Dissertations

Predicting how much water will flow in rivers and streams is important for managing floods, water supply, and the environment. Traditionally, government agencies have used complex models, such as the National Water Model (NWM), which simulate how much water moves through landscapes using physical laws and real-world data. However, recent advances in Artificial Intelligence (AI) have enabled new ways to make these predictions. This research explored whether AI-based models could predict river discharge more accurately. These AI models learn patterns from past data instead of relying only on physical rules. To find out how well they work, the AI models …

Towards More Realistic And Practical Graph Backdoor Attacks, Jiawei Chen

Computer Science Theses & Dissertations

Graph Neural Networks (GNNs) have demonstrated remarkable performance on graph-based learning tasks and are increasingly deployed in security-critical applications. However, recent studies have shown that they are highly vulnerable to graph backdoor attacks (GBAs), where adversaries implant malicious triggers to induce targeted misclassification during inference. Despite their effectiveness, existing GBAs are often developed under unrealistic assumptions, such as focusing exclusively on simple homogeneous graphs or assuming the adversary possesses privileged access to target nodes during inference. This dissertation aims to systematically investigate and design graph backdoor attacks under significantly more realistic graph settings and adversarial constraints.

First, we investigate the …

Exploring The Determinants Of User Discontinuance In Ai-Driven Usage-Based Insurance, Wenzhuo Li

Theses and Dissertations in Business Administration

While interest in algorithmic decision-making continues to grow, limited research has examined the post-adoption phase. This study examines how users evaluate their post-adoption experiences with algorithmic decision-making in the context of usage-based insurance (UBI), focusing on how expectation disconfirmation shapes satisfaction and the intention to discontinue use. It explores two key questions: What factors influence users’ discontinuance intention toward AI-based UBI systems? And how do specific algorithmic characteristics alter how users form these post-adoption evaluations? To investigate these questions, this study develops a comprehensive theoretical model that integrates the Expectation Confirmation Model and Reactance Theory, incorporating additional factors such as …

Proxy Interfaces For Enhancing Non-Visual Web Usability, Md Javedul Ferdous

Computer Science Theses & Dissertations

People with blindness or visual impairments (BVI) face significant barriers when navigating the web, even when digital content is technically accessible. These challenges arise not from a lack of access, but from a mismatch between vision-centric user interfaces and the linear, audio-based interaction paradigms of screen readers. Sighted users rely on spatial layout, grouping, and visual cues to interpret structure quickly, while blind users must explore elements sequentially, often without sufficient context. As a result, they expend greater cognitive effort, become disoriented more easily, and struggle with tasks that are usually trivial for sighted users. Although accessibility initiatives have focused …

Modeling The Psychological And Technical Factors Influencing The Use Of Artificial Intelligence Tools Among Non-Native Arabic Learners: A Comparative Study In Egypt, Saudi Arabia, And Jordan., Mohammad Odeh, Alaa Al Din Musa, Ahmed Ragab Ali Ghalish, Montaser Adel Sayed Ahmed

All Works

This study aimed to develop a predictive longitudinal model of the psychological and technical factors influencing the use of artificial intelligence tools among non-native Arabic learners (international students) in three Arab countries: Egypt, the Kingdom of Saudi Arabia, and Jordan. The study adopted an extended Technology Acceptance Model (TAM) incorporating two psychological variables: trust in artificial intelligence and artificial intelligence anxiety. A quantitative longitudinal design with two time waves (T1 and T2) over a full academic semester was employed using Hierarchical Multiple Regression Analysis and PROCESS Macro for mediation. The sample consisted of 812 international students from public universities in …

Automated Testing And Enhancement For Autonomous Driving Systems, Mingfei Cheng

Dissertations and Theses Collection (Open Access)

Autonomous Vehicles (AVs) rely on Autonomous Driving Systems (ADSs) to perceive their surroundings, predict the behavior of traffic participants, plan driving actions, and control vehicle motion in complex traffic environments. As AVs move toward large-scale real-world deployment, ADSs are expected not only to avoid collisions and traffic-rule violations, but also to make robust decisions, cooperate effectively with other AVs, and maintain high-quality driving behavior. However, the open, dynamic, and uncertain nature of driving environments makes the systematic testing and enhancement of ADSs a challenging problem.

Although scenario-based testing has made substantial progress in discovering safety-critical violations, several important limitations remain. …

Practical On-Device Intelligence For Resource-Constrained Embedded And Wearable Devices, Xiao Ma

Dissertations and Theses Collection (Open Access)

Embedded and wearable devices increasingly rely on deep neural networks to support intelligent sensing applications directly on the device. However, building practical on-device intelligence remains challenging throughout the deployment lifecycle. Before deployment, models must remain accurate despite severe memory, computation, and energy budgets, and a single device often needs to support multiple sensing applications without deploying a separate model for each application. After deployment, the device continues to operate in changing real-world environments, where shifts in data distribution can degrade the model’s performance over time, so the model must be able to adapt to such shifts efficiently.

The first challenge …

An Open-Source Evaluation Framework For Risc-V Co-Design-Based Decimal Arithmetic, Riaz Ul Haque Mian, Michiko Inoue

Research outputs 2022 to 2026

Hardware–software co-design is a balanced strategy for computationally intensive algorithms such as decimal computing. It can provide several Pareto points for the development of embedded systems in terms of hardware cost and performance. In this study, we propose an efficient and accurate evaluation framework for decimal computing. The framework was designed and developed for hardware–software co-design decimal arithmetic using the RISC-V ecosystem. New binary and decimal-oriented instructions supported by an accelerator were developed. The framework can perform cycle-accurate analysis for performance and assess hardware overhead for co-design-based decimal arithmetic. Unlike previous studies that focused primarily on implementing and evaluating individual …

Approximation And Learning-Based Algorithms For Influence Maximization In Multilayer Social Networks, Xueqin Chang, Ruize Liu, Qing Liu, Baihua Zheng, Yunjun Gao

Research Collection School Of Computing and Information Systems

Motivated by the observation that users in the real world often engage across multiple social networks simultaneously, we study the problem of influence maximization in multilayer social networks (Mlim), aiming to select a small set of nodes that maximizes the total influence spread across all layers. To this end, we introduce a hybrid propagation model that jointly captures layer-specific diffusion dynamics and probabilistic cross-layer propagation. Based on this model, we formally define the Mlim problem and establish its NP-hardness, monotonicity, and submodularity. To address the Mlim problem, we first propose a greedy baseline Mlim-Greedy, which achieves a (1-1/e) approximation. Since …

Hvi-Cidnet+: Beyond Extreme Darkness For Low-Light Image Enhancement, Kangbiao Shi, Xiaowen Ma, Yixu Feng, Tao Hu, Peng Wu, Guansong Pang, Qingsen Yan

Research Collection School Of Computing and Information Systems

Low-Light Image Enhancement (LLIE) aims to recover visually pleasing content and details from degraded low-light images. However, existing RGB-based methods often suffer from color bias and brightness artifacts due to inherent high color sensitivity. Although the HSV color space can decouple brightness and color, it introduces noticeable red and black noise artifacts. To address these challenges, we adopt the Horizontal/Vertical-Intensity (HVI) color space for LLIE, which is defined by the HV color map and learnable intensity. The former enforces small distances for red coordinates to alleviate red noise artifacts, while the latter adaptively compresses low-light regions to suppress black noise …

Audeter: A Large-Scale Dataset For Deepfake Audio Detection In Open Worlds, Qizhou Wang, Hanxun Huang, Guansong Pang, Sarah Erfani, Christopher Leckie

Research Collection School Of Computing and Information Systems

Speech synthesis systems can now produce highly realistic vocalisations that pose significant authenticity challenges. Despite substantial progress in deepfake detection models, their real-world effectiveness is often undermined by evolving distribution shifts between training and test data, driven by the complexity of human speech and the rapid evolution of synthesis systems. Existing datasets suffer from limited real speech diversity, insufficient coverage of recent synthesis systems, and heterogeneous mixtures of deepfake sources, which hinder systematic evaluation and open-world model training. To address these issues, we introduce AUDETER (AUdio DEepfake TEst Range), a large-scale and highly diverse deepfake audio dataset comprising over 4,500 …

Left: Learnable Fusion Of Tri-View Tokens For Unsupervised Time Series Anomaly Detection, Dezheng Wang, Tong Chen, Guansong Pang, Congyan Chen, Shihua Li, Hongzhi Yin

Research Collection School Of Computing and Information Systems

As a fundamental data mining task, unsupervised time series anomaly detection (TSAD) aims to build a model for identifying abnormal timestamps without assuming the availability of annotations. A key challenge in unsupervised TSAD is that many anomalies are too subtle to exhibit detectable deviation in any single view (e.g., time domain), and instead manifest as inconsistencies across multiple views like time, frequency, and a mixture of resolutions. However, most cross-view methods rely on feature or score fusion and do not enforce analysis–synthesis consistency, meaning the frequency branch is not required to reconstruct the time signal through an inverse transform, and …

Parameterized Approximation Schemes For Fair Clustering In Doubling Metrics, Xiaoliang Wu, Ting Liang, Zhize Li, Qilong Feng

Research Collection School Of Computing and Information Systems

Fair clustering has garnered considerable attention, with various fairness notions proposed to ensure equitable representation across demographic groups. In this paper, we focus on the k-center problem in bounded doubling metrics under two popular fairness requirements: group fairness and data summarization fairness, referred to Group Fair k-Center (Gf-k-Cen) and Data Summarization Fair k-Center (Dsf-k-Cen), respectively. Both fairness notions extend classical clustering formulation by associating each data point with a demographic label. Motivated by recent advances in parameterized approximation results for fair clustering, we investigate whether these problems admit Fixed-Parameter Tractable (FPT) approximation schemes in bounded doubling metrics. The previous algorithms …

Understanding The Correlation Between Prediction Performance And Trust In Ai Through Scenario-Based Tasks, Likhitha Kammara

Theses and Dissertations

Trust in artificial intelligence is commonly assessed through self-reported scales or behavioral reliance, yet behavioral reliance is retrospective and can only be observed after a decision has already been made. This thesis examines whether prediction accuracy — a user's ability to predict what an AI system will recommend before its output is revealed — can serve as a prospective correlate of trust in the same empirical sense as behavioral reliance. The study was conducted in two phases using scenario-based AI decision tasks across disaster response, healthcare, and infrastructure restoration contexts, employing a between-group design in which participants either predicted AI …

Lessons Learned From The Adrenalin Load Disaggregation Challenge, András Balázs Tolnai, Zheng Ma, Igor Sartori, Clayton Miller, Stephen White, Matt Amos, Gustaf Bengtsson, Akram Hameed, Nørregaard Bo Jørgensen

Research Collection College of Integrative Studies

Crowdsourced data science competitions have emerged as a powerful mechanism for advancing research in energy informatics, offering scalable pathways for developing machine learning solutions that enhance energy efficiency and smart building operations. The ADRENALIN Load Disaggregation Challenge addressed a central problem in energy analytics—non-intrusive load monitoring (NILM) of heating and cooling loads in commercial buildings—while emphasizing the importance of model generalization across different buildings. This paper presents a comprehensive reflection on the lessons learned from organizing and executing the ADRENALIN competition, including technical insights, organizational challenges, and recommendations for future energy data challenges. In addition to the ADRENALIN case, a …

Differential Effects Of Generative Artificial Intelligence On Formative And Summative Assessment Performance: A Quasi-Experimental Longitudinal Study, Md Istiak Morsalin

Master's Theses

Generative artificial intelligence has unsettled a core assumption of course assessment: that scores on unsupervised work reflect what students can do unassisted. This study tests whether the widespread availability of ChatGPT altered student performance differently on formative versus summative assessments in Business Analytics and Foundations, a required undergraduate quantitative-methods course taught by one instructor across nine cohorts. In a quasi-experimental longitudinal design, the Fall~2022 cohort ($n = 90$), the last to finish before ChatGPT's public release, serves as a control against eight post-ChatGPT cohorts spanning Spring~2023 through Summer~2025 ($N = 646$). Outcomes were drawn from McGraw-Hill Connect records using matched …

Task-Aligned Haze Removal With Semantic-Aware Fusion And Contrast Self-Correction, Jinbin Wang, Aiping Yang, Guosong Jiang, Wenlong Yu, Dongwei Ren, Qinghua Hu

Research Collection School Of Computing and Information Systems

Adverse haze conditions introduce complex degradations that obscure scene details and distort structural cues critical for object detection, posing persistent challenges for vision‐based sensing systems. Although existing haze removal methods have achieved notable improvements in visual clarity, their optimisation objectives are often misaligned with downstream detection requirements, leading to limited detection performance in real‐world scenarios. To address this issue, this work proposes a task‐aligned weakly supervised haze removal framework, termed Dehaze4Detection, which explicitly aligns low‐level restoration with high‐level detection objectives. The framework incorporates a Semantic‐Aware Multi‐Scale Fusion Module (SMFM) that embeds pixel‐level semantic knowledge into the dehazing process, enabling selective …

Corruption Is Futile: Hardware-Assisted Multi-User Searchable Encryption, Feng Li, Chengyan Ma, Xiaoguo Li, Pengfei Wu, Lisha Yao, Jianting Ning, Guomin Yang, Jianfeng Ma, Deng, Robert H.

Research Collection School Of Computing and Information Systems

Searchable encryption enables writers to upload encrypted data to an untrusted cloud server, while allowing authorized readers to perform keyword searches over the encrypted content without compromising data privacy. The multi writer/multi-reader (M/M) setting better reflects real-world de ployment requirements because it aligns with the collaborative nature of many modern applications, but introduces substantial challenges in both efficiency and security. The state-of-the art scheme, delegatable searchable encryption (DSE), achieves optimal search time and forward privacy in the M/M setting. Nevertheless, DSE provides only limited security guarantees: search tokens generated by readers reveal the update count of queried keywords, and the …

Medical Firms’ Online Q&A Interactions: Effect Of Language Style On Investor Engagement, Runyu Wang, Keng Siau, Zili Zhang

Research Collection School Of Computing and Information Systems

PurposeThis study aims to investigate how language styles used by medical firms on digital question and answer (Q&A) platforms influence investor engagement. It examines the linguistic characteristics of managerial responses and compares their effects across industries, with a focus on the distinctive demands of medical communication.Design/methodology/approachWe analyze a panel dataset of 1,223 firm-month observations, constructed from 13,549 individual responses provided by 70 medical firms on a major Chinese web-based firm-investor Q&A platform over a 24-month period (2020–2021). Content analysis is used to assess linguistic features, such as first-person usage, uncertainty, understandability and concreteness. A two-way fixed effects model with clustered …

Interpretable Sparse Modeling Of Longitudinal Signals Via Critical-Range Rectification And Anytime Rule Compression, Jason Orender

Computer Science Theses & Dissertations

High-dimensional longitudinal data arise in clinical monitoring, industrial control systems, and other sensor-driven domains where outcomes are often governed by threshold-and-lag behavior. Traditional longitudinal workflows frequently depend on expert guessing to nominate candidate variables, lag windows, and threshold hypotheses, followed by repeated hypothesis testing over a limited set of manually specified relationships. While such approaches can be useful in narrow settings, they are often less robust in high-dimensional regimes because important interactions may be missed, multicollinearity can destabilize inference, and the resulting process can be labor-intensive and difficult to scale. This dissertation develops an end-to-end framework for interpretable sparse longitudinal …

Convergence Theory For Deep And Multi-Grade Neural Architectures, Lei Huang

Mathematics & Statistics Theses & Dissertations

This dissertation studies two complementary notions of convergence arising in modern neural network models: the convergence of recursively constructed neural network architectures and the convergence of optimization algorithms used for training neural-network-based image restoration models. The first part develops a convergence theory for deep neural networks (DNNs) viewed as recursively generated sequences of functions. Within an Lp framework motivated by statistical learning, sufficient conditions are established under which increasing-depth neural network sequences converge to well-defined limiting functions. The analysis covers both bounded-width and unbounded-width architectures, establishes explicit convergence rates, and motivates a network initialization strategy derived from the convergence conditions. …

Sem-Pdpl: Semantic Exposure Graphs For Privacy-Law-Informed Risk Assessment Of Public Social-Media Data, Heba Ismail

All Works

Public social-media content often contains self-disclosed personal attributes that appear low-risk in isolation but become privacy-relevant when linked across posts, platform accounts, or user-level traces. Existing research has advanced privacy-sensitive content detection, de-anonymization analysis, social-media research ethics, and privacy-compliance workflows; however, limited work operationalizes how personal-data disclosures combine structurally and how these structures can be translated into auditable governance actions. This paper proposes SEM-PDPL, a computational, privacy-law-informed risk-assessment framework for modeling public social-media exposure as semantic exposure graphs and mapping graph patterns to controls aligned with the United Arab Emirates Personal Data Protection Law (PDPL) and compatible with GDPR principles. …

Herd: A Policy-Driven Elastic Resource Distribution Framework For Hpc Deep Learning, Alejandro Guerrero Rodriguez

Open Access Theses & Dissertations

Modern deep learning workloads increasingly rely on distributed computation, and High Performance Computing systems can provide the necessary resources through large GPU allocations across interconnected nodes. Despite this, most distributed training frameworks operate under static resource assignments once a job is deployed. Research on NERSC Perlmutter has shown that 50% of GPU-enabled jobs use 25% or less of available GPU memory, and elastic training can reduce this underutilization by dynamically adjusting active workers. However, existing elastic systems have been developed mainly for cloud environments where fault tolerance and cost optimization are the primary concerns. Applying elastic training to HPC environments …

Learning To Unlearn: Unlearning And Meta-Unlearning For Continually Adapting Cybersecurity Threat Detectors, Daniel Lucio

Open Access Theses & Dissertations

Machine learning (ML) models deployed in non-stationary environments must continually adapt to evolving data distributions. This challenge is particularly critical in cybersecurity, where malware, intrusion techniques, and adversarial behaviors evolve over time. Continual learning primarily enables incorporating new knowledge while preserving prior knowledge, however, indiscriminately retaining obsolete and harmful information can hinder future adaptation and consume limited model capacity. We argue that effective adaptation should not only acquire new knowledge, but also selectively discard obsolete and less useful historical knowledge before learning from a new distribution. In this work, we propose a meta-learning framework that learns what to forget to …

Unsupervised Learning For Minimum Error Adaptive Sampling Of Atmospheric Vertical Temperature Profiles, Alejandro Medina

Open Access Theses & Dissertations

Uncrewed aerial systems (UAS) collect atmospheric data on fixed schedules, and endurance limits make blind searching costly. This thesis develops an unsupervised representation that summarizes a multi-decade radiosonde archive into a compact library of atmospheric states, giving a UAS an expectation of the column before it flies. The method standardizes both axes of a profile against the sounding's own surface conditions, which makes the representation independent of season and of station elevation. Applied to 27,270 soundings from Norman, Oklahoma, over the lowest 1.5 km of the atmosphere, 12 representative profiles reconstruct the record to within 1.0 °C of mean absolute …

Integrated Framework For Tsn-Enabled Ot Networks And Scalable Edge Computing To Enable Real-Time Feedback Loop, Taposh Kumer Sarker

Open Access Theses & Dissertations

The advent of Industry 5.0 envisions smart manufacturing characterized by human centricity, sustainability, and systemic resilience. Realizing this vision requires the seamless convergence of Information Technology (IT) and Operational Technology (OT) networks. However, integrating massive, stochastic IT edge computing workloads with deterministic physical control loops introduces severe architectural friction, inherently threatening the safety guarantees required by industrial machinery. To resolve this fundamental incompatibility, this dissertation proposes the Edge-Augmented Real-Time Industrial Control System (EA-RICS).

EA-RICS is a comprehensive, multi-layered architecture designed to dismantle systemic bottlenecks across the physical data plane, the centralized control plane, and the edge operating system. First, the …

Spring Ai 2026 Workshop And Speaker Series Report, Gregory Blike, Hannah (Nyingi) Brown, Dora (Dawn) Nguyen, Rami Huu Nguyen, Ajanee Igharo, Frayni Calderon, Moumita Saha, Chengjie Zheng

Paul English Applied Artificial Intelligence (AI) Institute Publications

The AI Workshop and Speaker Series was organized by the Student Advisory Council of the Paul English Applied Artificial Intelligence Institute at the University of Massachusetts Boston with the guidance of Distinguished Professor of Computer Science Wei Ding to create a practical and student-centered AI learning space. The Spring 2026 series included workshops on LinkedIn Optimization, Data Mining, GitHub, Prompt Engineering, Machine Learning of Structured Data, and Applied LLMs with Responsible AI Use in Research, while the broader speaker series introduced students to AI career development, generative AI and LLMs for cybersecurity, transportation security, political sciences, and AI in biomedicine. …

A Simulation Assessment Of The 'Law Of One Price', Caleb Wilkins

Computational and Data Sciences (MS) Theses

The ‘law of one price’ is an appealing notion regarding pricing of tradeable commodities that are priced in different currencies. It states that the prices of the same good in different markets should be equal after adjustment for exchange rates and that equality should persist through exchange rate fluctuations.

My research simulates the market conditions that should precipitate the ‘law of one price.’ Data was obtained from the simulated trade between algorithmic artificial intelligence agents that operated under induced boundedly rational market behaviors. Trade took place in two initially separate markets, a high-price market with a higher equilibrium price and …

Causal Discovery Methods For Single Cell Rna-Seq Data, Melanie Lambert

All Dissertations

The advancement of single cell RNA sequencing (scRNA-seq) has enabled the study of causal relationships between genes at single cell resolution. Although many causal discovery methods have been applied to scRNA-seq perturbation data, they are not well-suited to capture the characteristics of scRNA-seq data. The overall goal of this dissertation is to enhance researchers' ability to gain insight into genetic relationships.

The scRNA-seq data is high-dimensional, typically containing thousands of genes, and is sparse and zero-inflated due to dropout events, as well as noisy and subject to biological variability. Traditional causal discovery methods, such as constraint or score-based approaches, do …

Theory-Informed Generative Agents For Human Behavioral Modeling In Disasters, Liming Lu

All Dissertations

This dissertation develops a theory-informed generative-agent framework for modeling human behavioral decisions in disasters. Existing flood and disaster preparedness models often emphasize physical hazards, infrastructure exposure, or statistical correlations, but they struggle to capture the heterogeneous and evolving choices households make. This limitation is especially important for climate-related hazards, where future damage depends not only on changes in rainfall, inundation, and urban development, but also on decentralized protective actions such as house elevation, flood insurance, evacuation, and early preparedness. The dissertation integrates two empirical studies: a flood-risk study in Charleston, South Carolina, and a household disaster-preparedness study across hurricane contexts. …