Digital Commons Network^™

Enhancing Imbalanced Data Augmentation: A Comparative Study Of Ganified-Smote And Latent Factor Integration, Rusma Anieza Ruslan, Nureize Arbaiy, Pei-Chun Lin

Journal of Informatics and Web Engineering

One such serious problem in machine learning (ML) is imbalanced datasets. Minority class samples are usually sparse but hold significant meaning. The model can become biased toward the majority class due to unbalanced class distribution. This results in fraudulently high accuracy without being able to detect minority cases. This bias is also most perilous in critical applications, where ignoring minority cases can be highly destructive. To overcome this problem, the Synthetic Minority Oversampling Technique (SMOTE) is one of the most widely used. SMOTE creates balanced class distribution by interpolating between existing minority samples. It creates samples that are too close …

Bifusenet: A Multimodal Network For Estimating Blood Alcohol Concentration Via Bidirectional Hierarchical Fusion, Abdullah Tariq, Arooba Maqsood, Martin Masek, Syed Zulqarnain Gilani

Research outputs 2022 to 2026

Drunk driving remains a significant public safety challenge, demanding innovative alternatives to conventional methods such as field sobriety tests and breathalysers. Estimating a driver's level of intoxication through facial cues is particularly challenging due to the subtle and person-specific nature of alcohol-induced behaviours. In this paper, we present BiFuseNet, a 3D spatio-temporal multi-modal network designed to classify alcohol impairment levels into three categories: sober, moderate, and severe. Unlike prior approaches that rely on either uni-modal RGB video or hand-crafted facial features, our method exploits complementary physiological cues from RGB and infrared (IR) facial videos. We introduce a Bi-directional Hierarchical Fusion …

Discriminative Accuracy Of Cha2ds2-Vasc Score, And Development Of Predictive Accuracy Model Using Machine Learning For Ischemic Stroke Risk In Cardiac Amyloidosis And Atrial Fibrillation, Waqas Ullah, Abhinav Nair, Eric Warner, Salman Zahid, Mansoor Rahman, Palwasha Khan, Indranee Rajapreyar, Sridhara S. Yaddanapudi, M. Chadi Alraies, Said Ashraf, Jeffery Van Hook, Yegeny Brailovsky

Department of Medicine Faculty Papers

BACKGROUND: CHA2DS2-VASc score in cardiac amyloidosis (CA) with atrial fibrillation (AF) is believed to underestimate ischemic stroke risk, necessitating a better predictive model.

METHODS: Data were obtained from the National Readmission Database (NRD). Outcomes between CA-AF and no-CA-AF were compared using multivariate regression analysis to calculate adjusted odds ratios (aORs). AutoScore, an interpretable machine learning framework, was used to develop a stroke risk prediction model, and its predictive accuracy was evaluated with an area under the curve (AUC) using the receiver operating characteristic analysis.

RESULTS: A total of 11,860,804 (CA-AF 22,687 (0.19%) and no-CA-AF 11,838,117) patients were identified from 2015 …

Ophthoacr (Ophthalmology Automated Chart Review): An Ai-Powered Tool For Complete Automation Of Ophthalmology Chart Reviews And Cohort Data Analysis, Karen M. Chen, Kevin W. Chen, Vlad Diaconita, Stanley Chang, Leejee H. Suh

School of Medicine Faculty Publications

Purpose: Retrospective chart reviews in ophthalmology are essential for gaining clinical insights, but they remain labor-intensive and prone to error. Despite digitization through electronic health records, extracting and interpreting lengthy, unstructured patient histories remains challenging, particularly in ophthalmology, which relies heavily on both imaging and text-based reports. We introduce OphthoACR, a Health Insurance Portability and Accountability Act-compliant artificial intelligence (AI)-powered tool for automated chart review and cohort analyses in ophthalmology. Methods: OphthoACR was applied to extract 16 variables of increasing task difficulty from the complete chart histories of 91 patients who underwent secondary intraocular lens surgery at the Columbia University …

The Challenge Of Achieving Attributability In Multilingual Table-To-Text Generation With Question-Answer Blueprints, Aden Haussmann

International Journal of Undergraduate Research and Creative Activities

Generating faithful text descriptions from data tables is a significant challenge in Natural Language Processing (NLP), especially for the world’s many low-resource languages. This paper investigates whether Question-Answer (QA) blueprints—an intermediate planning step where a model first asks and answers questions about the data—can improve the factual accuracy of multilingual table-to-text generation. This novel approach is tested on the TaTA dataset, which includes several African languages, by finetuning models with and without these blueprints.

The results show a key distinction: while the QA blueprint method improves performance for English-only models, these gains disappear in the multilingual setting. This paper’s analysis …

Interdisciplinary Narratives On Artificial Intelligence & Personnel Selection Systems, John Hunter, Melissa Intindola, Neil Boyd, Thiago Serra Azevedo Silva

Faculty Journal Articles

Artificial intelligence (AI) has quickly and persistently become a daily presence in our lives, and its omnipresence has eclipsed the speed with which scholars can fully assess its efficacy and pitfalls. AI’s ubiquity and the lack of a clear understanding of its implications for humanity has spurred scholars across disciplines to action, and scholars in the field of Human Resource Management (HR) have certainly joined the fray. As scholars with a variety of experience and scholarship across disciplines, we believe that the burgeoning conversation in the HR literature would significantly benefit from a greater presence of interdisciplinary knowledge.

Building An Inclusive Ai Chatbot For Diverse Student Communities At Cal Poly: Uplift Ai, Gideon Telahun

College of Engineering Summer Undergraduate Research Program

This research project will investigate the ability of advanced Large Language Models (LLMs) to identify and assess misinformation across diverse forms of media, including text, images, and video. In an age where misleading content spreads rapidly across digital platforms, evaluating the reliability and integrity of AI systems tasked with fact-checking is critical. We will develop a comprehensive dataset composed of factual and misleading examples drawn from various well-known and reliable fact-checking organizations. Each item will be independently reviewed and transparently labeled to ensure reproducibility. We will then prompt a curated group of state-of-the-art LLMs—including GPT-4, Claude, Gemini, Perplexity, Grok, and …

Genai Literacy Framework For Library Instruction, Adwoa Boateng, Jennifer Freer, Greyson Pasiak, Erich Short, Ryan Tolnay, Rit Libraries

Presentations and other scholarship

A generative artificial intelligence (genai) framework for library instruction. This short framework is designed to incorporate into existing library instruction across many subject areas. The basic elements of the framework are: know & understand genai, use & evaluate genai, and library research & discovery with genai.

The Pastor As Romantic Author: Ai, Preaching, And The Unacknowledged Inheritance Of Authenticity, Daniel Plate, James Hutson

Faculty Scholarship

This article interrogates contemporary reactions to sermons produced with generative technologies through a historical–conceptual lens, arguing that widespread judgments of such outputs as “soulless,” “generic,” or lacking a “beating heart” are best explained by an unacknowledged inheritance from nineteenth-century Romantic expressivism. Rather than treating resistance to machine authorship as a theological verdict on computational incapacity, the study reconstructs how Romanticism centered authorship in sincere self-expression and solitary genius, displacing earlier heraldic expectations that prized fidelity to a received message. Methodologically, the analysis combines intellectual history with discourse analysis of global Christian experiments in synthetic composition (2020–2025), denominational guidance, and media …

Csc36000 - Modern Distributed Computing Assignment, Saptarashmi Bandyopadhyay

Open Educational Resources

This assignment covers standard performance metrics for Distributed Systems and the basics of Multiprocessing for CSC36000 - Modern Distributed Computing at the City College of New York CUNY. It is an interactive coding assignment intended to be executed in a Python notebook.

What Students Really Think: Unpacking Ai Ethics In Educational Assessments Through A Triadic Framework, Lim Ming Soon Tristan, Gottipati Swapna, Michelle L. F. Cheong

Research Collection School Of Computing and Information Systems

The rise of AI in educational assessments has significantly enhanced efficiency and accuracy. However, it also introduces critical ethical challenges, including bias in grading, data privacy risks, and accountability gaps. These issues can undermine trust in AI-driven assessments and compromise educational fairness, making a structured ethical framework essential. To address these challenges, this study empirically validates an existing triadic ethical framework for AI-assisted educational assessments, originally proposed by Lim, Gottipati and Cheong (In: Keengwe (ed) Creative AI tools and ethical implications in teaching and learning, IGI Global, 2023), grounded in student perceptions. The framework encompasses three ethical domains—physical, cognitive, and …

Information Provision And Search Frictions: Evidence From The Taxi Industry In Singapore, Sumit Agarwal, Shih-Fen Cheng, Jussi Keppo, Long Wang, Yang Yang

Research Collection School Of Computing and Information Systems

Search frictions and misallocation are common in decentralized transportation markets. Using novel trip-level data of taxis in Singapore, this paper examines the impactof real-time demand information at airport terminals on search frictions. The information reduces taxi supply misallocation, increasing deadheading speed by 16.3% and decreasing deadheading time by 10.77%, benefiting both passengers and drivers. It raises daily earnings by $3.70 USD and adds 6.2 minutes of operational time per airport-trip taxi. Spatial spillovers are primarily observed among drivers in adjacentdistricts. Taxis from the Budget Terminal and drivers with fewer prior airport pickups benefit more from this information.

Filterfl: Knowledge Filtering-Based Data-Free Backdoor Defense For Federated Learning, Yanxin Yang, Ming Hu, Xiaofei Xie, Yue Cao, Pengyu Zhang, Yihao Huang, Mingsong Chen

Research Collection School Of Computing and Information Systems

As a distributed machine learning paradigm, Federated Learning (FL) enables large-scale clients to collaboratively train a model without sharing their raw data. However, due to the lack of data auditing for untrusted clients, FL is vulnerable to poisoning attacks, especially backdoor attacks. By using poisoned data for local training or directly changing the model parameters, attackers can easily inject backdoors into the model, which can trigger the model to make misclassification of targeted patterns in images. To address these issues, we propose a novel data-free trigger-generation-based defense approach based on the two characteristics of backdoor attacks: i) triggers are learned …

Stroke2sketch: Harnessing Stroke Attributes For Training-Free Sketch Generation, Rui Yang, Huining Li, Yiyi Long, Xiaojun Wu, Shengfeng He

Research Collection School Of Computing and Information Systems

Generating sketches guided by reference styles requires precise transfer of stroke attributes, such as line thickness, deformation, and texture sparsity, while preserving semantic structure and content fidelity. To this end, we propose Stroke2Sketch, a novel training-free framework that introduces cross-image stroke attention, a mechanism embedded within self-attention layers to establish fine-grained semantic correspondences and enable accurate stroke attribute transfer. This allows our method to adaptively integrate reference stroke characteristics into content images while maintaining structural integrity. Additionally, we develop adaptive contrast enhancement and semanticfocused attention to reinforce content preservation and foreground emphasis. Stroke2Sketch effectively synthesizes stylistically faithful sketches that closely …

Cross-Subject Mind Decoding From Inaccurate Representations, Yangyang Xu, Bangzhen Liu, Wenqi Shao, Yong Du, Shengfeng He, Tingting Zhu

Research Collection School Of Computing and Information Systems

Decoding stimulus images from fMRI signals has advanced with pre-trained generative models. However, existing methods struggle with cross-subject mappings due to cognitive variability and subject-specific differences. This challenge arises from sequential errors, where unidirectional mappings generate partially inaccurate representations that, when fed into diffusion models, accumulate errors and degrade reconstruction fidelity. To address this, we propose the Bidirectional Autoencoder Intertwining framework for accurate decoded representation prediction. Our approach unifies multiple subjects through a Subject Bias Modulation Module while leveraging bidirectional mapping to better capture data distributions for precise representation prediction. To further enhance fidelity when decoding representations into stimulus images, …

Parameter-Efficient Variational Autoencoder For Multimodal Multi-Interest Recommendation, Nhu Thuat Tran, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

Learning user preferences in recommendation systems is enriched by multimodal features, such as textual and visual content, and amplified by multi-interest modeling with Variational AutoEncoders (VAEs). However, prior efforts are limited by single modality focus and cumbersome, parameter-heavy architecture designs. To address these limitations, we introduce an innovative solution that blends the semantic richness of multimodal data with the representational power of multi-representation VAEs. Drawing inspiration from Mixture of Experts (MoE), we cast each VAE as an expert tailored to a specific modality, then fuse them via a novel parameter-merging function into a lean, unified model. This approach efficiently captures …

Memad: Structured Memory Of Debates For Enhanced Multi-Agent Reasoning, Shuai Ling, Lizi Liao, Dongmei Jiang, Weili Guan

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) demonstrate remarkable in-context learning capabilities but often struggle with complex, multi-step reasoning. Multi-Agent Debate (MAD) frameworks partially address these limitations by enabling iterative agent interactions. However, they neglect valuable historical insights by treating each new debate independently. In this paper, we propose Memory-Augmented MAD (MeMAD), a parameter-free memory-augmented MAD framework that systematically organizes and reuses past debate transcripts. MeMAD stores structured representations of successful and unsuccessful reasoning attempts enriched with self-reflections and peer feedback. It systematically retrieves them via semantic similarity at inference time to inform new reasoning tasks. Our experiments on challenging mathematical reasoning, scientific …

Boosting Chart-To-Code Generation In Mllm Via Dual Preference-Guided Refinement, Zhihan Zhang, Yixin Cao, Lizi Liao

Research Collection School Of Computing and Information Systems

Translating chart images into executable plotting scripts-referred to as the chart-to-code generation task-requires Multimodal Large Language Models (MLLMs) to perform fine-grained visual parsing, precise code synthesis, and robust cross-modal reasoning. However, this task is inherently under-constrained: multiple valid code implementations can produce the same visual chart, and evaluation must consider both code correctness and visual fidelity across diverse dimensions. This makes it difficult to learn accurate and generalizable mappings through standard supervised fine-tuning. To address these challenges, we propose a dual preference-guided refinement framework that combines a feedback-driven, dual-modality reward mechanism with iterative preference learning. Our approach introduces a structured …

Unsupervised Visual Chain-Of-Thought Reasoning Via Preference Optimization, Kesen Zhao, Beier Zhu, Qianru Sun, Hanwang Zhang

Research Collection School Of Computing and Information Systems

Chain-of-thought (CoT) reasoning greatly improves the interpretability and problem-solving abilities of multimodal large language models (MLLMs). However, existing ap proaches focus on text CoT, limiting their ability to lever age visual cues. Visual CoT remains underexplored, and the only work [35] is based on supervised fine-tuning that relies on extensive labeled bounding-box data and is hard to generalize to unseen cases. In this paper, we introduce Unsupervised Visual CoT (UV-CoT), a novel framework for image-level CoT reasoning via preference optimization. UV-CoTperforms preference comparisons between model generated bounding boxes (one is preferred and the other is dis-preferred), eliminating the need for …

Genwardrobe: A Fully Generative System For Travel Fashion Wardrobe Construction, Peng Jin, Yilin Wen, Mingzhe Yu, Yunshan Ma, Rong Zheng, Jin‑Tu Fan, Chong Wah Ngo

Research Collection School Of Computing and Information Systems

With the increasing demand for outfit planning in real-world travel scenarios, the need for constructing a travel fashion wardrobe, a series of outfits tailored to a user's personalization and destination-specific context over a short travel period, has grown significantly. However, existing systems or works often focus on isolated factors and rely on retrieval-based methods, with insufficient utilization of generative models, limiting their adaptability to real-world travel scenarios. To address this issue, this study introduces GenWardrobe, a fully generative system for travel fashion wardrobe construction. GenWardrobe consists of three key modules: user query analysis, fashion knowledge retrieval via retrieval-augmented generation and …

Memory-Efficient 4-Bit Preconditioned Stochastic Optimization, Jingyang Li, Kuangyu Ding, Kim-Chuan Toh, Pan Zhou

Research Collection School Of Computing and Information Systems

Preconditioned stochastic optimization algorithms, exemplified by Shampoo, outperform first-order optimizers by offering theoretical convergence benefits and practical gains in large-scale neural network training. However, they incur substantial memory overhead due to the storage demands of non-diagonal preconditioning matrices. To address this, we introduce 4-bit quantization for Shampoo’s preconditioners. We introduce two key methods: First, we apply Cholesky decomposition followed by quantization of the Cholesky factors, reducing memory usage by leveraging their lower triangular structure while better preserving spectral properties to minimize information loss. To our knowledge, this is the first quantization approach applied to Cholesky factors of preconditioners. Second, we …

Cookingdiffusion: Cooking Procedural Image Generation With Stable Diffusion, Yuan Wang, Bin Zhu, Yanbin Hao, Chong-Wah Ngo, Yi Tan, Xiang Wang

Research Collection School Of Computing and Information Systems

Recent advancements in text-to-image generation models have excelled in creating diverse and realistic images. This success extends to food imagery, where various conditional inputs like cooking styles, ingredients, and recipes are utilized. However, a yet-unexplored challenge is generating a sequence of procedural images based on cooking steps from a recipe. This could enhance the cooking experience with visual guidance and possibly lead to an intelligent cooking simulation system. To fill this gap, we introduce a novel task called cooking procedural image generation. This task is inherently demanding, as it strives to create photo-realistic images that align with cooking steps while …

Stable Score Distillation, Haiming Zhu, Yangyang Xu, Chenshu Xu, Tingrui Shen, Wenxi Liu, Yong Du, Jun Yu, Shengfeng He

Research Collection School Of Computing and Information Systems

Text-guided image and 3D editing have advanced with diffusion-based models, yet methods like Delta Denoising Score often struggle with stability, spatial control, and editing strength. These limitations stem from reliance on complex auxiliary structures, which introduce conflicting optimization signals and restrict precise, localized edits. We introduce Stable Score Distillation (SSD), a streamlined framework that enhances stability and alignment in the editing process by anchoring a single classifier to the source prompt. Specifically, SSD utilizes Classifier-Free Guidance (CFG) equation to achieve cross-prompt alignment, and introduces a constant term null-text branch to stabilize the optimization process. This approach preserves the original content's …

Fine-Grained Abnormality Prompt Learning For Zero-Shot Anomaly Detection, Jiawen Zhu, Yew‑Soon Ong, Chunhua Shen, Guansong Pang

Research Collection School Of Computing and Information Systems

Current zero-shot anomaly detection (ZSAD) methods show remarkable success in prompting large pre-trained visionlanguage models to detect anomalies in a target dataset without using any dataset-specific training or demonstration. However, these methods often focus on crafting/learning prompts that capture only coarse-grained semantics of abnormality, e.g., high-level semantics like ‘damaged’, ‘imperfect’, or ‘defective’ objects. They therefore have limited capability in recognizing diverse abnormality details that deviate from these general abnormal patterns in various ways. To address this limitation, we propose FAPrompt, a novel framework designed to learn Fine-grained Abnormality Prompts for accurate ZSAD. To this end, a novel Compound Abnormality Prompt …

Advances In Iot, Ai, And Sensor‑Based Technologies For Disease Treatment, Health Promotion, Successful Ageing, And Ageing Well, Yuzhou Qian, Keng Siau

Research Collection School Of Computing and Information Systems

Recent advancements in the Internet of Things (IoT) and artificial intelligence (AI) are unlocking transformative opportunities across society. One of the most critical challenges addressed by these technologies is the ageing population, which presents mounting concerns for healthcare systems and quality of life worldwide. By supporting continuous monitoring, personal care, and data-driven decision-making, IoT and AI are shifting healthcare delivery from a reactive approach to a proactive one. This paper presents a comprehensive overview of IoT-based systems with a particular focus on the Internet of Healthcare Things (IoHT) and their integration with AI, referred to as the Artificial Intelligence of …

Learn To Fly: Enabling Deep Learning Based Perception And Control In Aerial Robotics, Krishna Muvva

School of Computing: Dissertations, Theses, and Student Research

Uncrewed Aerial Vehicles (UAVs) are increasingly deployed in dynamic, GPS degraded, and cluttered environments, yet their autonomy remains fundamentally constrained by limitations in onboard perception and real-time control. This dissertation addresses these challenges by proposing a unified framework that co-designs deep learning-based perception and model-based control, organized around three core thrusts: Learn to Track, Learn to Localize, and Learn to Evade.

Learn to Track develops dynamic and adaptive perception control mechanisms that optimize CNN inference for target tracking. A control-aware CNN framework dynamically adjusts inference frequency based on UAV motion, reducing latency while maintaining visual lock. An adaptive CNN with …

Improving Universities Through The Use Of Ai & Transformative Technology: A Case Study Analysis At The University Of South Carolina, Cameron A. Caulk

Senior Theses

This thesis aims to give university leaders a practical guide to implementing AI, using lessons learned from the University of South Carolina’s experience as a case study. The project started with a review of literature and industry practices for the Finance & Administration division, which led to key deliverables like AI usage guidelines, DoIT’s position paper on AI systems, and the ParkUSC parking app. One ongoing project, Project Shuttlecock, even sets the stage for future AI initiatives at the university.

AI holds immense promise, but universities often hesitate due to concerns about ethics, costs, and the learning curve for staff …

Seeing 3d Through 2d Lenses: 3d Few-Shot Class-Incremental Learning Via Cross-Modal Geometric Rectification, Tuo Xiang, Xuemiao Xu, Bangzhen Liu, Jinyi Li, Yong Li, Shengfeng He

Research Collection School Of Computing and Information Systems

The rapid growth of 3D digital content necessitates expandable recognition systems for open-world scenarios. However, existing 3D class-incremental learning methods struggle under extreme data scarcity due to geometric misalignment and texture bias. While recent approaches integrate 3D data with 2D foundation models (e.g., CLIP), they suffer from semantic blurring caused by texture-biased projections and indiscriminate fusion of geometric-textural cues, leading to unstable decision prototypes and catastrophic forgetting. To address these issues, we propose Cross-Modal Geometric Rectification (CMGR), a framework that enhances 3D geometric fidelity by leveraging CLIP’s hierarchical spatial semantics. Specifically, we introduce a Structure-Aware Geometric Rectification module that hierarchically …

Leveraging Machine Learning And Causal Inference For Loan Default Prediction, Luca Guida

Doctoral Dissertations and Master's Theses

This research explores a systematic application of machine learning techniques combined with causal inference to predict loan defaults in peer-to-peer lending. Accurately forecasting loan defaults is crucial for mitigating financial risk and optimizing lending strategies. This analysis is based on multiple datasets of loan applications spanning over a decade, containing detailed financial and credit information about borrowers. Beginning with extensive Exploratory Data Analysis (EDA) coupled with scaling strategies, the research identifies key trends in loan performance across a large number of factors, such as interest rates or borrower creditworthiness, and one objective is to determine from the many available predictors …

Analysis Of The Status And Thematic Trends Of Ai For Science Research Abroad From 2015 To 2024, Fangyuan Wang, Huiting Xu, Jinghua Xue

Journal of Scientific Information Research

[Purpose/significance] This paper analyzes the relevant literature in the field of AI for Science（AI4S）in the WoS core database from 2015 to 2024, and sorts out the research status and development trends in this field, aiming to provide forward-looking insights for the application of AI technology in scientific research.

[Method/process] This paper combines bibliometric analysis with the BERTopic model to analyze the publication trends, publishing countries, core authors, and topic identification and development trends in the field of AI4S.

[Result/conclusion] Through bibliometric analysis, this paper reveals the exponential growth trend of AI4S-related literature, and finds that China ranks first in the …