Digital Commons Network^™

Patient Subset Classification Using Encoded Embeddings And Knowledge Graph Retrieval-Augmented Generation, Benjamin A. Holmes

Browse all Theses and Dissertations

The widespread adoption of electronic medical records has created a vast reservoir of clinical data that can be leveraged to better understand how interventions relate to patient outcomes. Much of this information, however, exists as unstructured free-text, posing significant challenges for traditional statistical and machine-learning methods. Solving these challenges would allow the extraction of specific patient subpopulations (clinically relevant cohorts of individuals who share overlapping symptoms, risk factors, or diagnostic criteria), which could be used in precision medicine. Despite this promise, extracting these subpopulations from unstructured medical notes is an ongoing challenge due to the variability of clinical language and …

Enhancing Cybersecurity Through Autonomous Knowledge Graph Construction By Integrating Heterogeneous Data Sources, Hatoon Alharbi, Ali Hur, Hasan Alkahtani, Hafiz Farooq Ahmad

Research outputs 2022 to 2026

Cybersecurity plays a critical role in today’s modern human society, and leveraging knowledge graphs can enhance cybersecurity and privacy in the cyberspace. By harnessing the heterogeneous and vast amount of information on potential attacks, organizations can improve their ability to proactively detect and mitigate any threat or damage to their online valuable resources. Integrating critical cyberattack information into a knowledge graph offers a significant boost to cybersecurity, safeguarding cyberspace from malicious activities. This information can be obtained from structured and unstructured data, with a particular focus on extracting valuable insights from unstructured text through natural language processing (NLP). By storing …

Symp25s: Can Llm Detect Dementia?, Rishank Singh, Youxiang Zhu, Xiaohui Liang, John A. Batsis, Caroline Summerour

Paul English Applied Artificial Intelligence (AI) Institute Publications

High Cost of Traditional Screening: Formal cognitive assessments for dementia are resource-intensive and not easily accessible for large-scale screening. Speech-Based Alternatives: Existing speech-based methods (e.g., picture description, telephone interviews) aim to address this but have limitations. Lack of Natural Dialogue: These conventional approaches often use rigid, repetitive prompts and do not simulate real conversations. Engagement Issues: Repetition and lack of conversational depth can reduce engagement and affect the accuracy of responses over time. Untapped Potential of LLMs: Large language models (LLMs) are capable of generating natural, coherent, and adaptive dialogue. Research Gap: The application of LLMs for dementia detection through …

Multi-Lingual And Cross-Domain Frontiers In Machine-Generated Content Detection, Gurunameh Singh Chhatwal

Theses and Dissertations (Comprehensive)

The rapid advancement of generative artificial intelligence, particularly Large Language Models (LLMs) such as GPT-4 and their multilingual capabilities, has significantly blurred the distinction between human-authored and machine-generated content. This technological evolution introduces critical challenges concerning the detection and attribution of textual authenticity and authorship, exacerbating societal issues like misinformation proliferation and compromising academic and professional integrity. Traditional detection methodologies, predominantly monolingual and heuristic-based, have demonstrated inadequate generalizability and efficacy against the sophisticated, multilingual capabilities of contemporary generative models.

This thesis addresses two major problems arising from these advancements. Firstly, it introduces novel multilingual detection methodologies explicitly designed to differentiate …

The Integration Of Artificial Intelligence And Ontologies: Transformations In Knowledge Representation And Application, Grazia Serratore, Julaine Clunis

STEMPS Faculty Publications

Artificial Intelligence (AI) is reshaping the landscape of knowledge representation. There is an increasingly strong bidirectional relationship, between AI techniques and ontologies. AI techniques revolutionized traditional, manual ontology development and contribute to automated ontology construction, while ontologies enhance the performance of AI systems and their semantic accuracy. Through a comprehensive review of current literature, this paper aims to examine: i) how Machine Learning (ML) techniques contribute to the automated construction, refinement, and validation of ontologies; ii) the most widely used and effective ML approaches for ontology construction; iii) how domain-specific requirements influence the selection and adaptation of AI techniques for …

Cognitive Map Generation For Vision And Language Navigation, Alexander Sandoval Mesa

Dissertations and Theses

Visual-Language Navigation (VLN) presents significant challenges for autonomous agents, such as robots and virtual assistants, particularly in complex, dynamic environments where the seamless integration of visual perception and natural language understanding is critical. Traditional VLN systems often struggle with effectively aligning language instructions and visual scene understanding, limiting their adaptability and navigation efficiency.

This thesis proposes a novel Cognitive Map-based framework that addresses these challenges by transforming natural language navigation instructions into structured graph representations. The Cognitive Map consists of nodes representing waypoints, landmarks, decision points, and edges encoding spatial relationships and navigational actions. These maps are generated using Large …

Interpreting Topic Models In Byte-Pair Encoding Space, Jia Peng Lim, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

Byte-pair encoding (BPE) is pivotal for processing text into chunksize tokens, particularly in Large Language Model (LLM). From a topic modeling perspective, as these chunksize tokens might be mere parts of valid words, evaluating and interpreting these tokens for coherence is challenging. Most, if not all, of coherence evaluation measures are incompatible as they benchmark using valid words. We propose to interpret the recovery of valid words from these tokens as a ranking problem and present a model-agnostic and training-free recovery approach from the topic-token distribution onto a selected vocabulary space, following which we could apply existing evaluation measures. Results …

Adapting Installation Instructions In Rapidly Evolving Software Ecosystems, Haoyu Gao, Christoph Treude, Mansooreh Zahedi

Research Collection School Of Computing and Information Systems

files play an important role in providing installation-related instructions to software users and are widely used in open source software systems on platforms such as GitHub. Software projects evolve rapidly alongside their dependencies in dynamic software ecosystems, requiring frequent updates to installation instructions. These instructions are crucial for users to start with a software project. Despite their significance, there is a lack of systematic understanding regarding the documentation efforts invested in README files and the triggers behind them. To fill the research gap, we conducted a qualitative study, investigating 400 GitHub repositories with 1,163 README commits that focused on updates …

The Gradient Puppeteer: Adversarial Domination In Gradient Leakage Attacks Through Model Poisoning, Kunlan Xiang, Haomiao Yang, Meng Hao, Shaofeng Li, Haoxin Wang, Zikang Ding, Wenbo Jiang, Tianwei Zhang

Research Collection School Of Computing and Information Systems

In Federated Learning (FL), clients share gradients with a central server while keeping their data local. However, malicious servers could deliberately manipulate the models to reconstruct clients' data from shared gradients, posing significant privacy risks. Although such Active Gradient Leakage Attacks (AGLAs) have been widely studied, they suffer from two severe limitations: 1) coverage: no existing AGLAs can reconstruct all samples in a batch from the shared gradients; 2) stealthiness: no existing AGLAs can evade principled checks of clients. In this paper, we address these limitations with two core contributions. First, we introduce a new theoretical analysis approach, which uniformly …

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 …

Action This Day: The Mathematics And Machinations That Bested The German Enigma, Jonah Weinbaum

Dartmouth College Master’s Theses

This thesis presents a comprehensive and chronological overview of cryptographic techniques designed to break Enigma, beginning in 1932 and culminating in the creation of the Turing-Welchman Bombe. We discuss the mathematical theory and electromechanical implements used to decode one of history's greatest ciphers.

Reexamining the Bombe through the lens of modern group theory, we critique Alan Turing's estimation of the number of "stops" that the Bombe produces for various plaintext-ciphertext pairing structures. To address its limitations, we introduce a new framework for estimating the number of stops by extending John Dixon's theorem concerning the probability that uniformly distributed elements of …

A Study Of Pattern Of Cybercrime Abuse Of Individual Internet Users In Umuahia North Lga, Abia State Of South-Eastern Nigeria, Ogochukwu Favour Nzeakor, Rita Ngozi Okafor, Chibuike Ndubuisi Nwoke

International Journal of Cybersecurity Intelligence & Cybercrime

Although a number of studies exist on cybercrime and its abuses, little is known about the pattern of cybercrime abuses individual Internet users experience in Nigeria, especially the south eastern region. Using data collected via various methods, this study examines the pattern of cybercrime abuses of individual Internet users in Umuahia, Abia State, of South Eastern Nigeria. The result of the analysis of 1,067 samples drawn from 223,134 Internet users in Umuahia North LGA of Abia Sate showed that: while most users are victims of stolen ICT-gadgets (19%), fraud related offences (17%), and hacking (15%); they rarely fall victims of …

Fine-Tuned Large Language Models (Llms): Improved Prompt Injection Attacks Detection, Md Abdur Rahman, Hossain Shahriar, Guillermo Francia, Fan Wu, Alfredo Cuzzocrea, Sheikh Iqbal Ahamed

Computer Science Faculty Research and Publications

Large language models (LLMs) are becoming a popular tool as they have significantly advanced in their capability to tackle a wide range of language-based tasks. However, LLMs applications are highly vulnerable to prompt injection attacks, which poses a critical problem. These attacks target LLMs applications through using carefully designed input prompts to divert the model from adhering to original instruction, thereby it could execute unintended actions. These manipulations pose serious security threats which potentially results in data leaks, biased outputs, or harmful responses. This project explores the security vulnerabilities in relation to prompt injection attacks. To detect whether a prompt …

Contextual Embedding-Based Clustering To Identify Topics For Healthcare Service Improvement, K M Sajjadul Islam, Ravi Teja Karri, Srujan Vegesna, Jiawei Wu, Praveen Madiraju

Computer Science Faculty Research and Publications

Understanding patient feedback is crucial for improving healthcare services, yet analyzing unlabeled short-text feedback presents challenges due to limited data and domainspecific nuances. Traditional supervised approaches require extensive labeled datasets, making unsupervised methods more practical for extracting insights. This study applies unsupervised techniques to analyze 439 survey responses from a healthcare system in Wisconsin, USA. A keyword-based filter was used to isolate complaint-related feedback using a domain-specific lexicon. To identify dominant themes, we evaluated traditional topic models such as Latent Dirichlet Allocation (LDA) and Gibbs Sampling Dirichlet Multinomial Mixture (GSDMM) - alongside BERTopic, a neural embedding-based clustering method. To improve …

Synthesizing Deception: Countering Large Language Model-Generated Phishing Campaigns Through Adaptive Semantic Anomaly Detection, Bekim Fetaji, Debabrata Samanta

Mesopotamian Journal of Computer Science

The paper fills in a gap in the literature that demonstrates an insufficient number of sturdy detection schemes that can recognize the small semantic aberrations inherent in LLM-generated deceptive text. Our proposed co-design hybrid model is Semantic Anomaly Detection with Isolation Forest (SADI) model that combines the synergistic mixture of a fine-tuned transformer-based LLM for deep semantic feature extraction with Isolation Forest algorithm that detects anomalies efficiently. This study introduces SADI, an adaptive semantic-anomaly detector for large-language-model phishing emails. Using a corpus of 10 000 messages, SADI attains an F1 score of 0.981 (95 % CI 0.978–0.984) and processes a …

Data Privacy Regulations In The Gaming Industry: A Comparative Analysis Of Singapore, Macau, And Japan, Miloslava Plachkinova

Faculty Articles

This study explores the relatively under-researched area of comparing data privacy regulations and best practices across different countries, with a focus on the gaming industry. It provides an overview of general data privacy principles and existing global regulations, analyzing how gaming operators leverage personal data for competitive advantage. Specifically, the research examines the data privacy approaches and regulatory requirements in Singapore, Macau, and Japan, highlighting the cultural and historical contexts influencing these regulations. Through a comparative analysis, the article discusses the compliance needs for gaming operators in these jurisdictions.

Knowledge And Ontology Enhanced Approach To Natural Language Understanding (Koe-Nlu) In Computational Social Media And Healthcare, Naga Usha Gayathri Lokala

Theses and Dissertations

Natural Language Understanding (NLU) faces both opportunities and challenges as the amount of social media and healthcare data grows. This is particularly evident in context-sensitive applications such as evaluating cognitive health, identifying mental health symptoms, and monitoring drug abuse. Even though traditional NLU models work well for processing language in a wide range of areas, they often lack the ability to understand language in a specific domain, reason in context, and incorporate structured external knowledge. This dissertation talks about the Knowledge and Ontology Enhanced Approach to Natural Language Understanding (KOE-NLU), a new framework that is meant to make NLU systems …

Optimizing Ai Language Models: A Study Of Chatgpt-4 Vs. Chatgpt-4o, Md Nurul Absar Siddiky, Muhammad Enayetur Rahman, Md Fayaz Bin Hossen, Muhammad Rezaur Rahman, Md. Shahadat Jaman

Electrical & Computer Engineering Faculty Publications

This paper presents a comparative analysis of OpenAI's GPT-4 and its optimized variant, GPT-4o, focusing on their architectural differences, performance, and real-world applications. GPT-4, built upon the Transformer architecture, has set new standards in natural language processing (NLP) with its capacity to generate coherent and contextually relevant text across a wide range of tasks. However, its computational demands, requiring substantial hardware resources, make it less accessible for smaller organizations and real-time applications. In contrast, GPT-4o addresses these challenges by incorporating optimizations such as model compression, parameter pruning, and memory-efficient computation, allowing it to deliver similar performance with significantly lower computational …

Ml Model To Better Identify Instances Of Bullying Faced By Members Of The Lgbtq+ Community, Arslan Bisharat

Master's Theses

Cyberbullying poses a significant threat to online communities, with the LGBTQ+ community facing disproportionately higher rates of harassment. While existing cyberbullying detection systems have made progress in identifying general instances of online harassment, they often fail to capture the nuanced and context-dependent nature of LGBTQ+-targeted bullying. This thesis presents a novel approach to this challenge by developing SpectrumNet, an LGBTQ+-centric transformer-based model for cyberbullying detection. Our research was conducted in two phases. In Phase 1, we evaluated the effectiveness of pre-trained transformer models (RoBERTa, BERT, and GPT-2) in identifying LGBTQ+-related cyberbullying. Building on these findings, Phase 2 introduced SpectrumNet which …

Pfedrag: A Personalized Federated Retrieval-Augmented Generation System With Depth-Adaptive Tiered Embedding Tuning, Hangyu He, Xin Yuan, Kai Wu, Ren Ping Liu, Wei Ni

Research outputs 2022 to 2026

Large Language Models (LLMs) can undergo hallucinations in specialized domains, and standard Retrieval-Augmented Generation (RAG) often falters due to general-purpose embeddings ill-suited for domain-specific terminology. Though domain-specific fine-tuning enhances retrieval, centralizing data introduces privacy risks. The use of federated learning (FL) can alleviate this to some extent, but faces challenges of data heterogeneity, poor personalization, and expensive training data generation. We propose pFedRAG, a novel Personalized Federated RAG framework, which enables efficient collaborative fine-tuning of embedding models to address these challenges. The key contribution is a new Depth-Adaptive Tiered Embedding (DATE) architecture, which comprises a Global Shared Layer, combined using …

Application Of Machine Learning And Large Language Models In Healthcare For Data Prediction And Summarization, Chiazam Chisom Izuchukwu

College of Graduate Studies: Theses & Dissertations

This study aims to examine the use of machine learning (ML) and large language models (LLMs) in healthcare to enhance disease prediction, clinical decision-making, and information management. Five supervised ML models—Logistic Regression (LR), Support Vector Machine (SVM), Random Forest (RF), Decision Trees (DT), and Naïve Bayes (NB)—on three different computing platforms—Google Colab, Databricks, and Snowflake—were employed for disease classification. Data preprocessing included treating missing values, encoding categorical variables utilizing one-hot-encoding, feature scaling when needed, and tackling class imbalance with Synthetic Minority Over-sampling Technique (SMOTE) before an 80-20 train-test separation. Models were created with Scikit-learn (Google Collab), Spark MLlib (Databricks), and …

Leveraging Deep Learning Models And Social Media Data For Enhanced Situation Awareness In Disaster Management, Ademola Abdulganiyu Adesokan

Doctoral Dissertations

"In recent years, social media has become a crucial source of real-time data for disaster management, supporting emergency responses when traditional channels like 911 are overcrowded and overwhelmed. It offers authorities valuable data for developing effective strategies, especially when swift actions are essential to save lives. However, the informal language, ambiguous meanings, and irrelevant content on social media pose challenges to accurate classification and hinder the efficient extraction of disaster-relevant information, leading to inefficiencies in emergency response efforts.

This research focuses on seven key questions: i) How can we detect, classify, and analyze hate and offensive tweet emotions during large-scale …

Parallel Algorithms For Large Scale Dynamic Graph Analysis, Arindam Khanda

Doctoral Dissertations

A complex system of interacting entities in contemporary scenarios, be it biological, technological, or social, can be represented using graphs. Dynamic graphs, unlike their static counterparts, are ones in which the underlying topology changes over time. These networks act as a model for numerous systems, from transportation to social interactions, capturing the ever-evolving nature of real-world phenomena. However, the inherent temporality of these networks presents a unique set of challenges and the traditional static graph algorithms often fall short in efficiency and applicability. In our research, we delve into the complexities presented by large dynamic networks and suggest various methodologies …

Leveraging Artificial Intelligent For Optimized Crop Production: An Ann-Based Approach, Yahya Layth Khaleel, Fadya A. Habeeb, Mustafa Abdulfattah Habeeb, Fatimah N. Ameen

Mesopotamian Journal of Computer Science

To incite modern day crop production and ensure sustainability, exact crop recommendations are key to the process. This study pays significant attention to the need for the use of big data tools in studies involving comprehensive data sets that contain information on soil and other environmental characteristics. The set of data used in this research includes Nitrogen, Phosphorus, and Potassium content coordinated with Temperature, Humidity, pH Value, and Rainfall. Knowing these factors is to make a favorable decision about improving agricultural products yield, availability and management of the resources, as well as general well-being of the crops. Specialized advisory on …

Self-Attention Enhanced Dual Bigru For Arabic Fake News Detection, Baqer M. Merzah, Jafar Razmara, Jaber Karimpour

Mesopotamian Journal of Computer Science

The rapid proliferation of social media platforms has greatly amplified the dissemination of fake news, representing significant obstacles to public trust and evidence-based decision-making, particularly for the Arabic-speaking population. Meeting the challenge of Arabic fake news detection is a problem compounded by the complex morphological nature of the language, as well as limited resources. This study presents a hybrid deep learning framework that integrates two Bidirectional Gated Recurrent Units (BiGRUs) along with an attention mechanism for efficiently detecting misinformation in Arabic news. The method leverages FastText word embeddings for disambiguating the intricate semantics of the Arabic language. The model is …

Agentic Ai-Enhanced Virtual Reality For Adaptive Immersive Learning Environments, Indra Kishor, Udit Mamodiya, Mohammed Almaayah, Amer Alqutaish, Rami Shehab, Theyazn H. H. Aldhyani

Mesopotamian Journal of Computer Science

Immersive learning using Virtual Reality (VR) has gained prominence for delivering experiential, engaging education. However, most VR learning environments lack real-time adaptability, personalization, and cognitive responsiveness. This study presents an Agentic AI-enabled VR framework that autonomously adjusts pedagogical content, interaction style, and challenge level based on learner behavior, emotions, and performance feedback. The proposed system integrates a reinforcement learning-based agent with a virtual reality module to form an intelligent tutor capable of independent decision-making. A neuro-symbolic model processes multi-modal feedback (gesture, speech, gaze, performance) to determine context-aware pedagogical strategies. The system employs a self-evolving curriculum logic that adapts in real …

Adaptive Nussbaum Design For Nonholonomic Systems With Asymptotic Stabilization Against False Data Injection, Guilong Liu, Yongliang Yang, Weinan Gao, Donald C. Wunsch

Electrical and Computer Engineering Faculty Research & Creative Works

This article addresses the stabilization challenges of nonholonomic systems under the threat of false data injection (FDI) attacks, which compromise the integrity of state information. A novel adaptive control strategy using Nussbaum-type gains is proposed to ensure the asymptotic stability of the closed-loop system while maintaining signal boundedness. The approach extends conventional Nussbaum designs to handle multiple unknown control directions. It integrates online learning mechanisms to mitigate the impact of FDI attacks. Additionally, adaptive backstepping and fuzzy-logic systems are utilized to approximate and compensate for unknown nonlinear dynamics. The methodology transforms nonholonomic systems into equivalent cascade structures to address inherent …

Genai’S Impact On Global It Management: A Multi-Expert Perspective And Research Agenda, Yogesh K. Dwivedi, Laurie Hughes, Mohammad S. Al-Ahmadi, Vincent Dutot, Syed Q. Ahmed, Shahriar Akter, Rahul De’, Keyao Li, Nitish Singh, Paul Walton

Research outputs 2022 to 2026

Generative AI (GenAI) is disrupting global IT management and challenging established practice. The increasing use of GenAI technology is redefining localization, transforming existing workforce roles, outsourcing strategy, and team dynamics. Simultaneously, GenAI’s security complexities have prompted the rethinking of existing risk frameworks to meet a new set of challenges from GenAI enhanced cyber threats. This article explores these complex and converging factors, providing a roadmap to address GenAI’s significant impact on global IT management. We advocate the responsible adoption of GenAI and importance of building resilient, value-driven, globally consistent IT ecosystems able to adapt to the significant challenges and opportunities …

Securing Federated Learning From Distributed Backdoor Attacks Via Maximal Clique And Dynamic Reputation System, Priyesh Ranjan, Ashish Gupta, Sajal K. Das

Computer Science Faculty Research & Creative Works

Federated Learning (FL) is a distributed learning paradigm that leverages the computational strength of local devices to collaboratively train a model. The clients train the local model on their respective devices and submit the weight updates to the server for aggregation. This paradigm allows the clients to experience diverse data without sharing their local data with other participants or the server. However, FL is susceptible to backdoor attackers that deliberately train the model on altered data, essentially trying to get favor on a specific subtask separated from the main task. In this work, we focus on powerful backdoor attackers who …

Fuzzy-Based Deep Reinforcement Learning For Suicidal Ideation Detection In Online Social Networks, Greeshma Lingam, Sajal K. Das

Computer Science Faculty Research & Creative Works

Suicidal ideation is a major psychological problem, and preventing this social risk is recognized as an important research topic. In reality, there can be several reasons why a person experiences suicidal ideation. Each individual can express views, emotions, and several types of symptoms related to suicidal ideation on the most popular social media platforms. In online social networks (OSNs), identification of suicidal ideation is one of the major challenging tasks. Existing studies have shown that the delay in understanding and identifying various risk factors can cause the suicidal event to occur. Due to the scarcity of data and understanding, the …