Computer Sciences Commons^™

Actively Learn From Llms With Uncertainty Propagation For Generalized Category Discovery, Jinggui Liang, Lizi Liao, Hao Fei, Bobo Li, Jing Jiang

Research Collection School Of Computing and Information Systems

Generalized category discovery faces a key issue: the lack of supervision for new and unseen data categories. Traditional methods typically combine supervised pretraining with self-supervised learning to create models, and then employ clustering for category identification. However, these approaches tend to become overly tailored to known categories, failing to fully resolve the core issue. Hence, we propose to integrate the feedback from LLMs into an active learning paradigm. Specifically, our method innovatively employs uncertainty propagation to select data samples from high-uncertainty regions, which are then labeled using LLMs through a comparison-based prompting scheme. This not only eases the labeling task …

Mix-Initiative Response Generation With Dynamic Prefix Tuning, Yuxiang Nie, Heyan Huang, Xian-Ling Mao, Lizi Liao

Research Collection School Of Computing and Information Systems

Mixed initiative serves as one of the key factors in controlling conversation directions. For a speaker, responding passively or leading proactively would result in rather different responses. However, most dialogue systems focus on training a holistic response generation model without any distinction among different initiatives. It leads to the cross-contamination problem, where the model confuses different initiatives and generates inappropriate responses. Moreover, obtaining plenty of human annotations for initiative labels can be expensive. To address this issue, we propose a general mix-Initiative Dynamic Prefix Tuning framework (IDPT) to decouple different initiatives from the generation model, which learns initiative-aware prefixes in …

Sgsh : Stimulate Large Language Models With Skeleton Heuristics For Knowledge Base Question Generation, Shasha Guo, Lizi Liao, Jing Zhang, Yanling Wang, Cuiping Li, Hong Chen

Research Collection School Of Computing and Information Systems

Knowledge base question generation (KBQG) aims to generate natural language questions from a set of triplet facts extracted from KB. Existing methods have significantly boosted the performance of KBQG via pre-trained language models (PLMs) thanks to the richly endowed semantic knowledge. With the advance of pre-training techniques, large language models (LLMs) (e.g., GPT-3.5) undoubtedly possess much more semantic knowledge. Therefore, how to effectively organize and exploit the abundant knowledge for KBQG becomes the focus of our study. In this work, we propose SGSH — a simple and effective framework to Stimulate GPT-3.5 with Skeleton Heuristics to enhance KBQG. The framework …

Combining Cloud Architecting With Education, Sharon P. Pagidipati

Liberal Arts and Engineering Studies

I pursued the AWS Solutions Architect Professional Certification while applying my knowledge to build and revise technical solutions for an educational company known as EDFX.

Impact Of Similarities In Gender And Physical Appearance Between User And Embodied Conversational Agents On Trustworthiness, Empathy, And Service Evaluation, Sookyoung Park

Dartmouth College Master’s Theses

Embodied conversational agents (ECAs) have significantly enhanced human-machine interactions and show considerable potential in various industries such as customer service, education, healthcare, entertainment, and finance [1, 2]. This study explores the impact of similarities in gender and physical appearance between ECAs and users on the perceptions of trustworthiness, empathy, and service evaluation within the context of counselor ECAs. We conducted a within-subject experiment (n=50), using a 2x2 factorial arrangement, that varied the gender and the physical appearance of four distinct AI avatars. Participants interacted with each avatar, completing a post-experiment survey and participating in semi-structured interviews. Our findings indicate that …

Community Discovery Over Attributed Graphs, Yudong Niu

Dissertations and Theses Collection (Open Access)

Community discovery, as a fundamental problem in graph mining, finds applications in various domains such as biological analysis, system optimization and fraud detection. Although many efforts have been made to address community discovery based on graph topology, few works have been devoted to community discovery over attributed graphs, where graphs are equipped with attribute information such as node and edge types. Thus, this thesis is devoted to designing innovative solutions that can utilize the attribute information together with graph topology for community discovery. In particular, we study novel problems with efficient algorithms for both homogeneous and heterogeneous attributed graphs and …

Stock Market Volatility In The United Kingdom: Simulating Post-Covid-19 Recovery, Bala A. Dahiru, Mohammed Shuaibu, Najibullah Hassanov

CBN Journal of Applied Statistics (JAS)

This paper investigates the time it would take for the FTSE-100 index to reach its post-COVID-19 peak. The paper utilises an exponential generalised autoregressive conditional heteroscedasticity (EGARCH) model that accounts for leverage effect and asymmetries. The preferred models amongst competing variants was the Autoregressive Moving Average (ARMA)-EGARCH(2,1) specification and was used to predict daily FTSE-100 data from 5th January 2000 to 21st June 2024. The empirical exercise showed that the COVID-19-induced financial crisis negatively affected the United Kingdom’s stock market performance. The results show that the FTSE100 index could reach its post-pandemic peak around 27th August, 2024 (two months after …

Ai Employment Decision-Making: Integrating The Equal Opportunity Merit Principle And Explainable Ai, Gary Kok Yew Chan

Research Collection Yong Pung How School Of Law

Artificial intelligence (AI) tools used in employment decision-making cut across the multiple stages of job advertisements, shortlisting, interviews and hiring, and actual and potential bias can arise in each of these stages. One major challenge is to mitigate AI bias and promote fairness in opaque AI systems. This paper argues that the equal opportunity merit principle is an ethical approach for fair AI employment decision-making. Further, explainable AI can mitigate the opacity problem by placing greater emphasis on enhancing the understanding of reasonable users (employing organisations) and affected persons (employees and job candidates) as to the AI output. Both the …

Context In Computer Vision: A Taxonomy, Multi-Stage Integration, And A General Framework, Xuan Wang

Dissertations, Theses, and Capstone Projects

Contextual information has been widely used in many computer vision tasks, such as object detection, video action detection, image classification, etc. Recognizing a single object or action out of context could be sometimes very challenging, and context information may help improve the understanding of a scene or an event greatly. However, existing approaches design specific contextual information mechanisms for different detection tasks.

In this research, we first present a comprehensive survey of context understanding in computer vision, with a taxonomy to describe context in different types and levels. Then we proposed MultiCLU, a new multi-stage context learning and utilization framework, …

Semantic Structuring Of Digital Documents: Knowledge Graph Generation And Evaluation, Erik E. Luu

Master's Theses

In the era of total digitization of documents, navigating vast and heterogeneous data landscapes presents significant challenges for effective information retrieval, both for humans and digital agents. Traditional methods of knowledge organization often struggle to keep pace with evolving user demands, resulting in suboptimal outcomes such as information overload and disorganized data. This thesis presents a case study on a pipeline that leverages principles from cognitive science, graph theory, and semantic computing to generate semantically organized knowledge graphs. By evaluating a combination of different models, methodologies, and algorithms, the pipeline aims to enhance the organization and retrieval of digital documents. …

Morp: Monocular Orientation Regression Pipeline, Jacob Gunderson

Master's Theses

Orientation estimation of objects plays a pivotal role in robotics, self-driving cars, and augmented reality. Beyond mere position, accurately determining the orientation of objects is essential for constructing precise models of the physical world. While 2D object detection has made significant strides, the field of orientation estimation still faces several challenges. Our research addresses these hurdles by proposing an efficient pipeline which facilitates rapid creation of labeled training data and enables direct regression of object orientation from a single image. We start by creating a digital twin of a physical object using an iPhone, followed by generating synthetic images using …

Securing Tomorrow: Synergizing Change Management And Cybersecurity In The Digital Era, Sharon L. Burton

Publications

In the rapidly evolving business environment of 2024, organizational change management (OCM) leaders face unprecedented challenges driven by technological advancements, digital transformation, the integration of remote work, and a heightened focus on sustainability. This study examines the efficacy of traditional OCM models in addressing these modern complexities. Through a qualitative methodology employing an extensive literature review, the research identifies vital issues such as resistance to change, digital transformation imperatives, the shift to remote and hybrid work models, and the imperative for sustainable and ethical business practices. The study posits that while classical OCM frameworks offer foundational insights, there is a …

Boring But Demanding: Using Secondary Tasks To Counter The Driver Vigilance Decrement For Partially Automated Driving, Scott Mishler, Jing Chen

Psychology Faculty Publications

Objective

We investigated secondary–task–based countermeasures to the vigilance decrement during a simulated partially automated driving (PAD) task, with the goal of understanding the underlying mechanism of the vigilance decrement and maintaining driver vigilance in PAD.

Background

Partial driving automation requires a human driver to monitor the roadway, but humans are notoriously bad at monitoring tasks over long periods of time, demonstrating the vigilance decrement in such tasks. The overload explanations of the vigilance decrement predict the decrement to be worse with added secondary tasks due to increased task demands and depleted attentional resources, whereas the underload explanations predict the vigilance …

Ai Competency Acquisition Online? Engaging Undergraduate Students In An Ai 101 Course Through A Chatbot Workshop, Thomas Menkhoff, Lydia Teo

Research Collection Lee Kong Chian School Of Business

In recent years, digital transformation has dominated industries at an unprecedented rate. Alongside the proliferation of Artificial ntelligence (AI) technologies in the workplace, institutions of higher learning are experiencing an unprecedented push to integrate AI into the education ecosystem (Popenici & Kerr, 2017; Renz & Hilbig, 2020). AI in education (AIED) has the propensity to enrich teaching and learning in higher education by personalising students’ learning courses, automating assessment tasks, or providing24/7 access to learning resources (Karandish, 2021). According to estimates by the AI Market in the US Education Report, the AIEDmarket will grow at a CAGR of 47.77% during …

Enhancing Robustness Of Machine Learning Models Against Adversarial Attacks, Ronak Guliani

University Honors Theses

Machine learning models are integral for numerous applications, but they remain increasingly vulnerable to adversarial attacks. These attacks involve subtle manipulation of input data to deceive models, presenting a critical threat to their dependability and security. This thesis addresses the need for strengthening these models against such adversarial attacks. Prior research has primarily focused on identifying specific types of adversarial attacks on a limited range of ML algorithms. However, there is a gap in the evaluation of model resilience across algorithms and in the development of effective defense mechanisms. To bridge this gap, this work adopts a two-phase approach. First, …

Enhancing Government Service Delivery: A Case Study Of Acqar Implementation And Lessons Learned From Chatgpt Integration In A Singapore Government Agency, Hui Shan Lee, Shankararaman, Venky, Eng Lieh Ouh

Research Collection Lee Kong Chian School Of Business

This paper presents the pilot implementation of AI Based Citizen Question-Answer Recommender (ACQAR) as an attempt to enhance citizen service delivery within a Singaporean government agency. Drawing insights from previous studies on the Empath library's use in Service Level Agreement (SLA) prediction and the implementation of the Citizen Question-Answer system (CQAS), we redesigned the pilot system, ACQAR. ACQAR integrates the outputs from Empath X SLA predictor and CQAS as essential inputs to the ChatGPT engine, creating contextually aware responses for customer service officers to use as responses to the citizens.Empath X SLA predictor anticipates the expected service response time based …

An Experimental Study Of Supervised Machine Learning Techniques For Minor Class Prediction Utilizing Kernel Density Estimation: Factors Impacting Model Performance, Abdullah Mana Alfarwan

Dissertations

This dissertation examined classification outcome differences among four popular individual supervised machine learning (ISML) models (logistic regression, decision tree, support vector machine, and multilayer perceptron) when predicting minor class membership within imbalanced datasets. The study context and the theoretical population sampled focus on one aspect of the larger problem of student retention and dropout prediction in higher education (HE): identification.

This study differs from current literature by implementing an experimental design approach with simulated student data that closely mirrors HE situational and student data. Specifically, this study tested the predictive ability of the four ISML classification models (CLS) under experimentally …

Sensing With Integrity: Responsible Sensor Systems In An Era Of Ai, David Eisenberg

Dissertations

Deep and machine learning now offer immense benefits for consumer choice, decision-making, medicine, mental health and education, smart cities, and intelligent transportation and driver safety. However, as communication and Internet technology further advances, these benefits have the potential to be outweighed by compromises to privacy, personal freedom, consumer trust, and discrimination. While ethical consequences for personal freedom and equity rise from these technological advances, the issue may not be the technology itself but a lack of regulation and policy that allow abuses to occur. A first study examines how emerging sensor-based technologies, limited to only accelerometer and gyroscope data from …

Charting A Path To The Quintuple Aim: Harnessing Ai To Address Social Determinants Of Health, Yash Shah, Zachary Goldberg, Erika Harness, David Nash

College of Population Health Faculty Papers

The Quintuple Aim seeks to improve healthcare by addressing social determinants of health (SDOHs), which are responsible for 70-80% of medical outcomes. SDOH-related concerns have traditionally been addressed through referrals to social workers and community-based organizations (CBOs), but these pathways have had limited success in connecting patients with resources. Given that health inequity is expected to cost the United States nearly USD 300 billion by 2050, new artificial intelligence (AI) technology may aid providers in addressing SDOH. In this commentary, we present our experience with using ChatGPT to obtain SDOH management recommendations for archetypal patients in Philadelphia, PA. ChatGPT identified …

Try It Together - Qualitative Coding With Atlas.Ti, Danping Dong, Bryan Leow

2024 AI for Research Week

This hands-on session introduces Atlas.ti, a well-established qualitative data analysis tool for analyzing your transcripts and textual data. The session will cover coding data, extracting insights, creating visualizations, and exploring the tool's latest AI features.

Try It Together: Transcribing Your Audio With Whisper Api, Bella Ratmelia

2024 AI for Research Week

In this hands-on session, we will explore using the Whisper API to transcribe audio recordings from interviews, focus groups, and speeches. The session will delve into best practices and address common issues that may arise during the transcription process.

Customization Of Large Language Models For Causal Inference And Data Quality, Xingqiao Wang

Theses and Dissertations

In the burgeoning fields of artificial intelligence (AI) and natural language processing (NLP), Large Language Models (LLMs) have emerged as powerful tools for understanding complex textual data. This dissertation focuses on the novel customization of LLMs for enhancing causal inference in pharmacovigilance and improving entity matching for data quality—two critical challenges in healthcare analytics and data management. Through an in-depth exploration of encoder and decoder LLMs, this study illustrates how domain-specific customization can significantly advance the processing and interpretation of textual information. For pharmacovigilance, it demonstrates how tailored LLMs can extract causal relationships from adverse event reports, offering a new …

Singleadv: Single-Class Target-Specific Attack Against Interpretable Deep Learning Systems, Eldor Abdukhamidov, Mohammed Abuhamad, George K. Thiruvathukal, Hyoungshick Kim, Tamer Abuhmed

Computer Science: Faculty Publications and Other Works

In this paper, we present a novel Single-class target-specific Adversarial attack called SingleADV. The goal of SingleADV is to generate a universal perturbation that deceives the target model into confusing a specific category of objects with a target category while ensuring highly relevant and accurate interpretations. The universal perturbation is stochastically and iteratively optimized by minimizing the adversarial loss that is designed to consider both the classifier and interpreter costs in targeted and non-targeted categories. In this optimization framework, ruled by the first- and second-moment estimations, the desired loss surface promotes high confidence and interpretation score of adversarial samples. By …

Detecting Drifts In Data Streams Using Kullback-Leibler (Kl) Divergence Measure For Data Engineering Applications, Jeomoan Francis Kurian, Mohamed Allali

Engineering Faculty Articles and Research

The exponential growth of data coupled with the widespread application of artificial intelligence(AI) presents organizations with challenges in upholding data accuracy, especially within data engineering functions. While the Extraction, Transformation, and Loading process addresses error-free data ingestion, validating the content within data streams remains a challenge. Prompt detection and remediation of data issues are crucial, especially in automated analytical environments driven by AI. To address these issues, this study focuses on detecting drifts in data distributions and divergence within data fields processed from different sample populations. Using a hypothetical banking scenario, we illustrate the impact of data drift on automated …

Automatic Measurement Of Dialogue Engagingness In Multilingual Settings, Amila Ferron

Dissertations and Theses

Expansive use of large language models (LLMs) as dialogue systems brings increased importance to the evaluation of the responses they generate. Although evaluation of qualities such as coherence and fluency are readily possible with well-established automatic metrics, engagingness is often measured with human evaluation -- a process that can be costly and slows the pace of development. Existing automatic metrics for engagingness have low to moderate correlation with human annotations, evaluate the response without the conversation history, are complicated to implement, or are designed for a specific dataset. Moreover, they have been tested exclusively on English conversations. Given that dialogue …

Academic Search And Discovery Tools In The Age Of Ai And Large Language Models: An Overview Of The Space, Aaron Tay

2024 AI for Research Week

In the ever-evolving landscape of academic research, “AI tools” for literature search and synthesis are currently getting a lot of attention. These tools promise to ramp up productivity, enabling us to accomplish more in less time or absorb more knowledge without drowning in endless reading. With the sheer number of these systems increasing daily, it's natural to wonder: are they really worth our time and money? And if they are, how should we go about picking the right one from the multitude of options?

In this talk, I will share my views on how the space has developed over two …

Queering Futures With Data-Driven Speculation: The Design Of An Expanded Mixed Methods Research Framework Integrating Quantitative, Qualitative, And Practice-Based Modes, Jess Parris Westbrook

College of Education Theses and Dissertations

Queering’ questions, unlearns, disrupts, and transforms approaches, expectations, and realities. Futures are time and change. The approach I have designed to operationalize Queering and futures, or Queering futures, is the Queering Futures Framework (QFF). The Queering Futures Framework (QFF) is a brand-new transdisciplinary research framework intersecting values, positionality, complexity, Queerness themes, and futures praxis. This framework expands traditional mixed methods research conventions by integrating quantitative, qualitative, and practice-based research modes and mindsets. The Queering Futures Framework (QFF) prototype presented in this dissertation functions as a test case and proof of concept. The prototype quantitative mode measures attitudes towards AI, and …

Context Aware Music Recommendation And Playlist Generation, Elias Mann

SMU Journal of Undergraduate Research

There are many reasons people listen to music, and the type of music is largely determined by what the listener may be doing while they listen. For example, one may listen to one type of music while commuting, another while exercising, and yet another while relaxing. Without access to the physiological state of the user, current music recommendation methods rely on collaborative filtering - recommending music based on what other similar users listen to - and content based filtering - recommending songs based on their similarities to songs the user already prefers. With the rise in popularity of smart devices …

Helping The Home Cook: How Unsupervised Machine Learning Can Prevent Food Waste, Ryan B. Watson

Honors Projects

A common problem for the home cook is having too much of one food ingredient leftover, then not knowing what to do with it. To alleviate this problem, I propose using an unsupervised machine learning model to recommend recipes based on what ingredients the home cook wants to use. This model is built with FastText and trained on the recipe ingredients in the RecipeNLG dataset. Recipes are recommended based on which recipe ingredient set is most similar to the recipe ingredients provided in the user input. This solution will reduce consumer food waste by giving the home cook the information …

Making The Most Of Artificial Intelligence And Large Language Models: A Novel Approach For Book Recommendation And Discovery In Medical Libraries, Ivan Portillo, David Carson

Library Presentations, Posters, and Audiovisual Materials

This poster presentation evaluates the use of Artificial Intelligence and large language models (LLMs) to assist health science libraries in recommending and discovering book titles as part of their collection development. Using pre-determined prompts, the researchers evaluated ChatGPT 4.0, Bing Chat, and Google Bard as recommender systems for book discovery and ranking existing titles.