Digital Commons Network^™

Pciafl: Personalized And Class Imbalance-Aware Federated Learning For Driver Behavior Classification, Osho Osho, Shubh Garg, Suchetana Chakraborty, Sajal K. Das

Computer Science Faculty Research & Creative Works

Automated understanding of driver behavior from vehicular kinematics is vital for safety-aware intelligent transportation systems. However, centralized cloud processing suffers from latency, scalability, and privacy issues. Federated Learning (FL) provides a decentralized alternative but faces two major challenges: (i) non-IID client data due to heterogeneous driving styles and sensors, and (ii) severe class imbalance, as risky behaviors are inherently rare. In this work, we propose a personalized FL framework that uses a shared CNN-LSTM backbone with client-adaptive classifiers and incorporates a cost-sensitive loss to address behavior skew. Evaluated on the UAH-DriveSet dataset, our method achieves 92.60% accuracy and 91.68% macro-F1, …

Rescue: Routing Under Evolving Stochastic Congestion And Uncertain Spread In Wildfire Emergencies, Sowjanya Tammali, Arindam Khanda, Anurag Satpathy, S. M. Shovan, Sajal K. Das

Computer Science Faculty Research & Creative Works

Wildfires cause unpredictable spread and panic-driven congestion, posing severe challenges to evacuation planning. We present RESCUE (Routing under Evolving Stochastic Congestion and Uncertain Spread in Wildfire Emergencies), a dynamic, risk-aware framework that models the road network as a time-varying weighted graph. RESCUE operates in two stages: (i) a preprocessing phase integrating fire forecasts, traffic density, and distance to assign edge weights, and (ii) a real-time routing phase that adaptively updates paths using a multi-granular strategy distinguishing macro-level disruptions (e.g., rapid spread) from micro-level changes (e.g., local congestion). Two stochastic edge-cost functions are introduced: the Edge-Fire Risk Function (EFRF), estimating road …

A Visualization-Supported, Hierarchical, Action-Learning Model For Driving Behavior In A V2x Environment, Xuantong Wang, Jing Li, Jecca Bowen

Geography and the Environment: Faculty Scholarship

Understanding human driving decisions is crucial for intelligent transportation research. Most existing studies focus on individual vehicles in limited contexts, which restricts broader applicability of results. Leveraging Vehicle-to-Everything (V2X) infrastructure, this study introduces a machine learning framework to model driving actions and detect outliers across diverse environments. This approach features a semantically enabled clustering method that groups similar driving behaviors based on speed and actions. It also adds a time-series learning model to identify typical driving behaviors across various contexts, thereby enabling detection of abnormal driving actions. A suite of visual tools has been developed to help interpret driving patterns, …

Universal Sound Separation: Distance-Aware Mixture Simulation, Co-Occurrence Conditioning, And Chain-Of-Inference, Wonjun Park

Computer Science and Engineering Theses - Archive

Universal Sound Separation (USS) -- the task of disentangling arbitrary sound sources from a single-channel acoustic mixture -- remains an open challenge due to the ill-posed nature of the problem and the distributional gap between synthetic training data and real-world recordings. This thesis addresses three distinct bottlenecks in the USS pipeline: training data realism, inference strategy, and conditioning richness. We first present two knowledge-guided approaches to sound source separation. The first is a distance-aware mixing strategy that leverages Large Language Models (LLMs) to assign plausible loudness relationships between audio sources during training data synthesis. By querying an LLM about the …

A. Vs. I In Ai: Is There A Threshold To "Engineered" Intelligence?, Joshit Mohanty

Engineering Management & Systems Engineering Faculty Publications

Despite artificial intelligence reshaping the world, its development generates uncertainties regarding future capabilities. AI simultaneously exists as an artifact of engineering design and as autonomous intelligence, creating an observer-participant feedback loop. This paper proposes that embodied AI faces a bandwidth-limited intelligence threshold T_h that it arises from B = min(C_sens,C_Act). However, Shannon capacity measures bits while intelligence operates on concepts, necessitating a dual-channel model separating physical bandwidth B_io from representational capacity B_rep. Intelligence emerges as multi-dimensional rather than scalar, with components exhibiting different bandwidth dependencies. Surpassing T_h requires either new sensing methods expanding B, enhanced representational frameworks, or reconceptualization within …

An Examination Of Ethics When Using Chatgpt, Blake V. Ailes

CCAC Theses and Dissertations

With the general population’s recent and dramatic increase in the frequency of ChatGPT and other similar Artificial Intelligence Generated Content (AIGC) usage throughout various industries, gray areas are becoming more prominent regarding whether ChatGPT is considered to be ethical or unethical in certain situations. Examples of unethical use of ChatGPT include plagiarism, the use of inaccurate information in drawing conclusions, and the creation of malicious code that negatively impacts various companies. Not all of these ethical concerns are necessarily the fault of the user or the AIGC. To date, peer-reviewed research on the ethical usage of ChatGPT is limited, primarily …

Digital Redlining In The Smart City: Artificial Intelligence, Housing Law, And Structural Urban Inequality, Spurthi Nrusimhadevara

Undergraduate Scholarship and Creative Works

Artificial intelligence is increasingly used in urban housing systems, where it shapes decisions about tenant screening, rent pricing, lending, zoning, and neighborhood investment. Although these tools are often promoted as efficient and impartial, they frequently rely on historical data that reflect racial, economic, and spatial inequality. As a result, AI systems can reproduce discriminatory outcomes even when protected characteristics are not directly used. This paper examines digital redlining in the smart city and argues that algorithmic housing tools mirror long standing structural inequities that raise significant concerns under fair housing and civil rights law. It evaluates how automated screening, predictive …

Deep Learning For Eeg-Based Emotion Recognition With Temporal And Spectral Interpretability, Shruti Rameshbhai Shingala

Selected Full-Text Master Theses 2021-

Electroencephalography (EEG)-based emotion recognition has emerged as a critical component of affective computing and clinical neuroscience. Existing approaches to this problem primarily reduce the multi-dimensional EEG time series to a single averaged feature vector, thereby discarding the temporal structure of the emotional response. The present work addresses three identified gaps in the literature: the absence of temporal interpretability, the uniform use of frequency bands, and the use of single-scale temporal feature extraction. A deep learning architecture, MST-Mamba-Asym, is proposed, comprising four components: Asymmetry Attention, which encodes hemispheric asymmetry by computing signed left–right channel differences, FreqBandAttention, which learns differential weights across …

Large Language Model Communication And Data Transfer Across A Simulated Telephone Line, Jared Reyes

Dissertations and Theses

This thesis presents a proof-of-concept communication system in which two local large language model endpoints communicate across a simulated analog telephone line using legacy USB modems. The project combines modem voice mode, modem data mode, local speech processing, and structured machine messaging into a single staged session. During the voice phase, one endpoint places a call, the other answers, speech generated by a locally hosted LLaMA-family model is synthesized with Piper, transmitted through the modem voice path, captured on the remote side, and transcribed with Faster-Whisper to drive the next response. After the voice exchange, the system transitions to a …

Ai For Life Sciences: From Geometric Protein Modeling To Multimodal Drug Design, Feng Jiang

Computer Science and Engineering Dissertations

Predicting biomolecular interactions, from immune recognition to drug–target binding, is a central problem in the life sciences and computational drug discovery. Deep learning has advanced this area, yet three challenges persist: the topology of large, highly imbalanced interaction networks; structural noise in computationally predicted protein models; and the integration of multimodal information such as functional text and taxonomic annotations. This dissertation develops a coherent set of models spanning immune complex prediction and small-molecule drug design: graph learning that addresses network topology and severe class imbalance; a noise-tolerant method that fuses predicted structures with evolutionary sequence features; and multimodal representation learning …

Ransomware As Organization: A Comparative Analysis Of Corporate And Criminal Structures In Conti, George Urling

Theses, Dissertations and Capstones

Cybercriminal groups continue to pose major threats to global cybersecurity. One of the most common types of cybercriminal groups are, “Ransomware-as-a-Service (RaaS)" groups, who create and sell ransomware. While research is conducted into the development of ransomware, there is limited reporting on the organizational structure and habits of RaaS groups. In 2022, prominent RaaS group Conti had their chat logs leaked, with the logs ranging from 2020 to 2022. This study seeks to provide a deeper understanding of RaaS group structures by utilizing the Conti leaked logs as a case study. The study, entitled “Ransomware as Organization: A Comparative Analysis …

Towards Multimodal Guideline-Aligned Agentic Systems, Wenliang Zhong

Computer Science and Engineering Dissertations - Archive

I present my work on building multimodal guideline-aligned agentic systems designed to enable AI agents to solve complex real-world tasks. My research addresses two critical perspectives: (1) Instruction-Aware Embedding Models for flexible and universal embedding tasks, and (2) Guideline-Driven LLM Agents that leverage domain-specific guidelines to perform expert-level tasks. These components address embedding and generation tasks, respectively, and lay the foundation for a hybrid agent capable of tackling challenging real-world applications.

From the embedding perspective, I first address the instruction-following capabilities of embedding models. While Large Language Models (LLMs) excel at instruction following, they are primarily designed for generation rather …

Do Algorithms Dream Of Electric Muses? Teaching Creative Writing In The Age Of Generative Ai, Anna Leahy

English Faculty Articles and Research

In Philip K. Dick’s novel Do Androids Dream of Electric Sheep? androids are given a psychological test to confirm they are not human before killing them. The story’s end suggests that humans will treat a seemingly harmless android as authentically as a human even when humans are aware the android is not human. Students use tools like ChatGPT, which function as autocomplete on steroids, to produce text using probabilistic relationships among words, and instructors can’t always tell the difference between average student writing and Gen AI text. In creative writing classes, instructors might use thinking for oneself as a central …

Multimodal Deep Learning For Biological Data Understanding, Saiyang Na

Computer Science and Engineering Dissertations

This dissertation presents three contributions to multimodal deep learning for biological data understanding, addressing the fundamental challenge of cross-modal alignment from two complementary perspectives: designing effective multimodal fusion methods for specific biomedical applications, and proposing a general framework for higher-order multimodal alignment that captures hierarchical structure in data.

First, we develop Cmai, a deep learning framework for B cell receptor (BCR) to antigen binding prediction that aligns BCR sequence information with antigen three-dimensional structures using contrastive learning. Cmai achieves an average AUROC of 0.907 across 17 antigens and 5 independent cohorts, and demonstrates clinical utility in predicting immune checkpoint inhibitor …

Systematic Approaches To Characterizing Vulnerabilities And Enhancing Robustness Of Text And Vision-Language Models, Poojitha Thota

Computer Science and Engineering Dissertations

The proliferation of artificial intelligence (AI) across critical domains, including news summarization, privacy-policy analysis, and medical decision support, has raised growing concerns about the security and robustness of these systems against adversarial manipulation. This dissertation investigates adversarial robustness in generative AI by addressing three key research goals: (1) characterizing adversarial vulnerabilities across generative models, (2) developing systematic defenses to improve the robustness of generative models, and (3) designing deployment-time safeguards for securing LLM interactions.

Towards the first goal, we characterize adversarial vulnerabilities across text-based and multimodal systems. In abstractive text summarization, we show that inference-time perturbations can exploit lead bias …

Leading The Change: Staff-Driven Ai Transformation In Smu Libraries’ Collection Team, Siew Khim Lim, Fion Goh

Research Collection Library

Why do libraries need to use AI? It is crucial for Libraries to stay relevant in this digital age by improving efficiency, access, and user experience. By adopting AI, libraries can better manage growing digital collections, provide innovative services, and ensuring they remain essential as hubs for knowledge and learning in an AIdriven world.

Shaping The Future: Emerging Technologies And Their Role In Industry 4.0 And Beyond, Liuliu Qin

Information Technology & Decision Sciences Faculty Publications

This paper provides a comprehensive review of emerging technologies driving the transition from Industry 4.0 to Industry 5.0. It examines the foundational concepts and pillars of Industry 4.0 and explores the transformative roles of Artificial Intelligence (AI), Extended Reality (XR), Collaborative Cobots (Cobots), Brain–Computer Interfaces (BCIs), quantum technologies, and next-generation connectivity (5G/6G). By integrating technological, human-centric, and sustainability perspectives, the study outlines how these emerging technologies reshape industrial systems and enable intelligent, adaptive, and inclusive futures.

Beyond Fixed Thresholds: Per-Label Calibration For Fine-Grained Emotion Detection On The Goemotions Dataset, Sai Puneet Naga Venkata Subramanyam Patchipulusu

Selected Full-Text Master Theses 2021-

This study investigates the effectiveness of five community fine-tuned transformer models for fine-grained emotion detection on the GoEmotions dataset: SamLowe/roberta- base-go_emotions (RoBERTa-base), cirimus/modernbert-base-go-emotions (ModernBERT), mrm8488/deberta-v3-base-goemotions (DeBERTa-v3-base), bhadresh-savani/bert-base-go- emotion (BERT-base-cased),and tasinhoque/distilbert-go-emotions (DistilBERT) . While the original GoEmotions research by Demszky et al. (2020) established a BERT-base baseline with a macro-F1 of 0.46, this thesis extends that work through independent empirical evaluation of five derivative models, systematic per-label threshold optimization, and comparative analysis of architectural trade-offs across the full transformer model family. Using the GoEmotions simplified test split (5,427 examples across 28 categories), all five models were evaluated at a fixed 0.5 …

Previsit Ai: A Retrieval-Augmented Generation For Patient Readiness In Clinical Encounters, Rolande Umuhoza

All Graduate Theses, Dissertations, and Other Capstone Projects

With healthcare systems under growing pressure from rising patient volumes and shrinking consultation windows, improving how patients communicate with physicians has become essential to delivering quality care. Yet patients routinely arrive at appointments unable to clearly describe their symptoms, recall their medical history, or articulate concerns, contributing to miscommunication, diagnostic inefficiency, and pre-visit anxiety. This study introduces PreVisit AI, a conversational system designed to address this gap through structured, knowledge-based patient preparation. The system is built on a Retrieval-Augmented Generation (RAG) architecture combining HuggingFace sentence embeddings (all-MiniLM-L6-v2), a Chroma vector store, and Google’s Gemini language model over a curated seven-document …

Regulating Ai Beyond Product Liability, Shruti Trikanad

Michigan Technology Law Review

Artificial Intelligence (AI) is being used by governments across the world to enforce regulatory mandates, adjudicate benefits and privileges, predict and analyze risks, and much more. Although this has significant potential to increase efficiency and responsiveness, it also comes with several risks of transparency, government accountability, and the amplification of discrimination and bias. It is crucial we oversee and regulate these AI systems effectively. This essay argues against the models that current regulatory frameworks are adopting to govern AI use: those resembling product liability.

Through the lens of the European Union's AI Act and Liability Directive, it highlights the unsuitability …

Trustworthy Multimodal Ai For Medical Imaging: Enhancing Diagnosis, Reasoning, And Human-Agent Interaction In Extended Reality, Jai Prakash Veerla

Computer Science and Engineering Dissertations

The transition from traditional microscopy to digital pathology has digitized diagnostic data, yet clinical workflows remain constrained by two-dimensional screens and passive, opaque analysis tools that fail to capture the spatial complexity of biological systems. While Foundation Models now promise to reason across histology and genomics, a critical disconnect persists between the richness of this data and the limited cognitive bandwidth of clinicians, who currently lack the immersive interfaces and trustworthy agents necessary to utilize it effectively. This dissertation presents a unified framework for "Embodied Agentic AI," establishing a pipeline that augments physician capabilities through immersive visualization, robust security, and …

Impact Of Cross-Client Heterogeneity In Federated Learning For Real-World Plant Disease Classification, Ritesh Janga

All Graduate Theses, Dissertations, and Other Capstone Projects

Deep learning applications are being adopted in agricultural image analysis that include challenges of data privacy and limited institutional data and heterogeneity of different types of architectures. However, Federated Learning is a model that allows collaborative training on data that does not have to be shared among parties. Therefore, Federated Learning is an effective method of collaborative training; however, its comparative effectiveness as compared to individual (local) training on diverse architectures has never been examined in an agricultural context. The objective of this study was to examine Federated Learning for the purpose of crop disease classification on extreme non-IID distributed …

Reinforcement Learning-Enabled Control And Design Of Rigid-Link Robotic Fish: A Comprehensive Review, Nhat Dinh, Darion Vosbein, Yuehua Wang, Qingsong Cui

Faculty Publications

With the rising demand for maritime surveys of infrastructure, energy resources, and environmental conditions, autonomous robotic fish have emerged as a promising solution with their biomimetic propulsion, agile motion, efficiency, and capacity for underwater inspection, monitoring, data collection, and exploration tasks in complex aquatic environments. Inspired by fish spines, rigid-link fish robots (RLFRs), a category of robotic fish, are widely utilized in robotics research and applications. Their rigid, actuated joints enable them to reproduce the undulatory locomotion and high maneuverability of biological fishes, while the modular nature of rigid links between joints makes them cost-effective and easy to assemble. This …

Hierarchy And Ideology Antagonism: Artificial Intelligence In Ridley Scott's Alien, Grace Anastasia Pula

Theses, Dissertations and Culminating Projects

This thesis examines the objectively threatening structure of artificial intelligence (AI) in the narrative plot of Alien and how it exerts control over the humans. Using a structuralist approach with Louis Althusser's Ideological State Apparatuses (ISAs), I will examine the character relationships and how an android, Ash, enforces a patriarchal, hierarchical system. Drawing on Mark Coeckelbergh’s AI Ethics and Jacques Ellul’s The Technological Society, I will outline broader fears that technology will surpass human intellect and serve a destructive function within an oppressive system. Analyzing two examples of AI characters, the film showcases capitalist ambitions through technological identities and their …

Toward Interpretable Multi-Omics Multimodal Biomedical Artificial Intelligence, Yanjun Lyu

Computer Science and Engineering Dissertations

The complexity of human disease arises from biological processes that unfold across multiple scales, from molecular variation through cellular function, tissue organisation, brain phenotypes, each of which is associated with distinct measurement modalities, regularities, and characteristic. Contemporary biomedical artificial intelligence has brought the opportunity to reveal the complexity with in; however, its methodological default, in which models are trained on most readily available modality, does not adequately engage with the multi-scale connected structure by which biological meaning is constituted. The research area of multi-omics and multi-modal AI for biomedicine remains at an early exploratory stage, and the work presented in …

Examining Inclusive Computing Education For Blind Students In India, Akshay Kolgar Nayak, Yash Prakash, Md Javedul Ferdous, Sampath Jayarathna, Hae-Na Lee, Vikas Ashok

Computer Science Faculty Publications

The growing demand for computer professionals, driven by the expanding Information Technology industry, has led to numerous inclusive computing education efforts. These efforts have even included blind or visually-impaired (BVI) students, who are being increasingly encouraged to pursue education and a career in computing, despite the visually-oriented nature of the discipline. Extant literature has predominantly focused on identifying and addressing the accessibility barriers faced by BVI students to promote more inclusive learning environments. While few studies have also investigated the accessibility of computing education from the perspectives of BVI learners and instructors, these have been primarily situated in the Global …

An Explainable Transformer Framework For Sentiment Analysis In Aviation Workforce Data, Sovon Chakraborty, Protiva Das, Fahmid Al Farid, Fuyad Hasan Bhoyan, Farig Yousuf Sadeque, Jia Uddin, Hezerul Abdul Karim

Computer Science Faculty Publications

Aviation is one of the predominant sectors that contribute significantly to the global economy. With the advent of technology, this industry is witnessing a paradigm shift towards data-driven approaches. The morale of the airline employees is barely noticed, which causes fatigue and depression. Furthermore, these mental health issues can be active reasons for destructive accidents. In this research, the authors are focused on collecting insightful information on aviation employees from Glassdoor.com. Moreover, the authors focus on analyzing the sentiments of the employees of renowned aviation companies. Primarily, the authors scraped necessary data from Glassdoor.com and created a dataset named JetJobJoy …

Paid Search Marketing Vs. Search Engine Optimization: Analytical Models Of Search Marketing Based On Search Engine Quality, Kai Li, Chunyang Shen, Mei Lin, Zhangxi Lin

Research Collection School Of Computing and Information Systems

As search engines are leading revenue growth in online marketing, search marketing has become a popular area of academic research. Although search engine advertising has interested researchers for decades and much has been learned, one thing that puzzles scholars is why search engine optimization companies are tolerated rather than excluded from the market, even though they capture a significant share of the advertising market. In this paper, we shed light on this phenomenon and establish an analytical model based on organic search quality. Through analysis of the model, we were able to draw several intriguing conclusions. First, there is no …

Do Comments And Expertise Still Matter? An Experiment On Programmers’ Adoption Of Ai-Generated Javascript Code, Changwen Li, Christoph Treude, Ofir Turel

Research Collection School Of Computing and Information Systems

This paper investigates the factors influencing programmers’ adoption of AI-generated JavaScript code recommendations within the context of lightweight, function-level programming tasks. It extends prior research by (1) utilizing objective (as opposed to the typically self-reported) measurements for programmers’ adoption of AI-generated code and (2) examining whether AI-generated comments added to code recommendations and development expertise drive AI-generated code adoption. We tested these potential drivers in an online experiment with 173 programmers. Participants were asked to answer some questions to demonstrate their level of development expertise. Then, they were asked to solve a LeetCode problem without AI support. After attempting to …

Attention-Based Geo–Textual Fusion Network For Disaster Risk Prediction, Mohammad Shafat Ahsan, Mst Sanjida Alam, Syed Sajjad Ahmed, Md Tanzimul Islam, Hashibul Ahsan Shoaib, M.F. Mridha, Md. Jakir Hossen

Student Publications [Scholarly]

Natural disasters pose recurring threats to human life and infrastructure, demanding intelligent systems that can process heterogeneous data streams and provide actionable insights in real time. Existing approaches often treat textual signals from social media and emergency communications separately from spatial hazard attributes, limiting their effectiveness in capturing the full complexity of evolving crises. This paper proposes an AI-driven geo–textual intelligence framework that integrates disaster-related text with GIS-based hazard features for real-time risk prediction and evacuation planning. The framework employs contextual text encoders and a neural GIS encoder, fused through an attention mechanism that dynamically weights cross-modal signals. Experiments on …