Digital Commons Network^™

Physics-Guided Strategies For Enhancing Neural Networks Trained With Limited Data, Jose Guadalupe Perez Zamora

Open Access Theses & Dissertations

Deep neural networks excel at a wide range of processing tasks across various disciplines. However, the quantity and quality of data significantly impact network performance. In specialized domains, high-quality datasets are often difficult to gather, interpret, and curate for effective learning. Few-shot learning techniques, including transfer learning, data augmentation, and meta-learning, have emerged to address these constraints.

We propose three physics-guided strategies for enhancing neural networks trained with limited data: (1) combining existing models like LSTMs with Physics-Informed Neural Networks through two-branch architectures that merge their outputs, (2) deriving custom physics-informed data augmentation algorithms to expand limited datasets, and (3) …

Is Noise Exposure Associated With Impaired Extended High Frequency Hearing Despite A Normal Audiogram? A Systematic Review And Meta-Analysis, Sajana Aryal, Monica Trevino, Hansapani Rodrigo, Srikanta K. Mishra

School of Mathematical & Statistical Sciences Faculty Publications

Understanding the initial signature of noise-induced auditory damage remains a significant priority. Animal models suggest the cochlear base is particularly vulnerable to noise, raising the possibility that early-stage noise exposure could be linked to basal cochlear dysfunction, even when thresholds at 0.25-8 kHz are normal. To investigate this in humans, we conducted a meta-analysis following a systematic review, examining the association between noise exposure and hearing in frequencies from 9 to 20 kHz as a marker for basal cochlear dysfunction. Systematic review and meta-analysis followed PRISMA guidelines and the PICOS framework. Studies on noise exposure and hearing in the 9 …

Estimation Of 3d Facial Dynamics With Nonlinear Filters For Position Tracking, Thoa Thieu, Roderick Melnik

School of Mathematical & Statistical Sciences Faculty Publications

This study presents a comparative evaluation of three nonlinear state estimation filters, the Extended Kalman Filter (EKF), Unscented Kalman Filter (UKF), and Particle Filter (PF), for the task of 3D facial landmark tracking. Using a publicly available dataset, we assess each filter's performance under both deterministic (noise-free) and stochastic (noisy) conditions. Metrics such as mean squared error (MSE), convergence rates of state and covariance estimates, and consistency over time are used to quantify tracking performance. Results show that the EKF consistently outperforms the UKF and PF, achieving faster convergence and lower estimation error, particularly in scenarios characterized by mild nonlinearity. …

Cosmetic Surgery And Physiological Disorder: You Should Talk To Someone About Your Unwinding Anxiety, Mona Muzammil, Washain Muzammil

School of Integrative Biological & Chemical Sciences (Formerly Dept. of Chemistry)

Body dysmorphic disorder is a mental health condition in which you can't stop thinking about one or more perceived defects or flaws in your appearance — a flaw that appears minor or can't be seen by others. But you may feel so embarrassed, ashamed and anxious that you may avoid many social situations.

When you have body dysmorphic disorder, you intensely focus on your appearance and body image, repeatedly checking the mirror, grooming or seeking reassurance, sometimes for many hours each day. Your perceived flaw and the repetitive behaviors cause you significant distress and impact your ability to function in …

Design And Evaluation Of Gamified Kahoot Modules For Improving Engagement And Conceptual Understanding Of Introductory Physics Students, Yaritza Villarreal

Theses and Dissertations

This study investigates the effectiveness of gamified learning modules in enhancing the engagement and conceptual understanding of introductory physics students. The first phase of this study focused on the design and development of gamified learning modules for selected topics in introductory physics. The modules were developed by integrating principles of Backward Design, following an escape-room theme with interactive scenarios, and incorporating classic game elements (e.g., points and leaderboards).

The second phase examined the effectiveness of the gamified Kahoot modules using a pretest-posttest control-group design. Sixty-eight (68) students were equally randomly assigned to the control and experimental groups. The experimental group …

Array Of Mini-Graphene-Silicon Solar Cells Intermittently Recharges Storage Capacitors Powering A Temperature Sensor, Ashaduzzaman, Syed M. Rahman, Md R. Kabir, James M. Mangum, Hung Do, Gordon Carichner, David Blaauw, Paul M. Thibado

Physics Faculty Publications and Presentations

Developing autonomous sensor systems that draw power from the ambient environment is a critical step for creating the Internet of Things. In this study, the authors built dozens of graphene-based solar cells, wire bonded them into standard packages, and characterized the current-voltage characteristics of each under illumination. Next, solar cells were connected in series to increase the output voltage. Three different sets of solar cells were used to charge three storage capacitors to the voltage levels required by our temperature sensor. The storage capacitors require only a few minutes to charge, yet power the sensor system for more than 24 …

Precision-Weighted Federated Learning, Jonatan Reyes, Lisa Di Jorio, Cecile Low-Kam, Marta Kersten-Oertel

Computer Science Faculty Publications

Federated learning (FL) using the federated averaging (FedAvg) algorithm has shown great advantages for large-scale applications that rely on collaborative learning, especially when the training data is either unbalanced or inaccessible due to privacy constraints. We hypothesize that FedAvg underestimates the full extent of heterogeneity of data when the aggregation is performed. We propose Precision-Weighted Federated Learning (PW) a novel algorithm that takes into account the second raw moment (uncentered variance) of the stochastic gradient when computing the weighted average of the parameters of independent models trained in a FL setting. With PW, we address the communication and statistical challenges …

Universal Systems Simulation Via Constraint Hypergraphs With Applications To Digital Twins, John Morris

All Dissertations

The characterization of systems encompasses a variety of modeling frameworks designed to capture specific behaviors and components of various system domains. Whatever the framework, the core elements of a system representation are the information of the system and a description of how that information is related. The relations in deterministic systems are functions, which, when composed to form executable processes, can be used to simulate system data. A declarative modeling framework is one that encodes mechanisms for preparing these simulations within the model structure, allowing an external agent to form the execution processes required for a given context. To date, …

Leveled Homomorphic Encryption Schemes: Noise And Precision Control, Kyle Yates

All Dissertations

Homomorphic encryption allows for computations on encrypted data without exposing the underlying plaintext, enabling secure and private data processing in various applications such as cloud computing and machine learning. In this thesis, we conduct a comprehensive worst-case noise analysis for three prominent leveled homomorphic encryption schemes: Brakerski-Gentry-Vaikuntanathan (BGV), Brakerski-Fan-Vercauteren (BFV), and Cheon-Kim-Kim-Song (CKKS). We propose modifications to these schemes and their residue number system (RNS) variants, ensuring fresh encryption noise falls under a constant bound. For BFV and BGV, we design and prove parameter conditions which guarantee certain homomorphic circuit evaluations return ciphertexts containing noise within a fixed bound. For …

Digital Reflections: Evaluating Body Dissatisfaction In Xr Through Eye- And Body-Tracked Virtual Humans, Deyrel Diaz

All Dissertations

In an era where digital and physical realities increasingly intertwine, the perception of body image is undergoing a significant transformation. Traditional understandings of body dissatisfaction, long studied in relation to psychological distress and eating disorders, are now being reshaped by technologies such as Virtual Reality (VR), Augmented Reality (AR), and Artificially Intelligent (AI)- generated media. These technologies have introduced novel ways of experiencing and interacting with the human form, raising critical questions about their impact on self-perception and internalization of beauty standards.

As virtual representations become more prevalent in entertainment, social media, and interactive platforms, it is becoming more crucial …

Predicting Major Solar Flares Using Convolutional Neural Networks And Multivariate Magnetic Field Time-Series Data, Arash Azizian Foumani

All Graduate Theses and Dissertations, Fall 2023 to Present

Major solar flares are sudden, intense bursts of X-ray energy from the Sun, capable of severely impacting critical technological infrastructure like satellites, communication networks, and power grids on Earth. Accurate prediction of these high-intensity events is crucial but presents a significant challenge. This is largely due to their infrequent occurrence and the complex, dynamic nature of the Sun's underlying magnetic activity which drives these events. This research focuses on improving the prediction of major solar flares by utilizing detailed historical data that tracks the evolution of magnetic properties within solar active regions over time. This time-based data, however, contains inherent …

Using Luminescence Of Quartz Temper From Archaeological Pottery To Infer Wildfire Intensity In The Southwestern Us, Brooklyn D. Dib

All Graduate Theses and Dissertations, Fall 2023 to Present

The size and frequency of wildfires have increased recently, impacting ecosystems, communities, and human health. This research uses the heat-sensitive luminescence signals of quartz sand temper within archaeological pottery to record past wildfire conditions. Pottery sherds, which are fragments of archaeological pottery, from the forest floor in sites in New Mexico and Arizona were collected from different fire contexts (no fire exposure, historical fires, prescribed burns, and modern wildfires). These forests are primarily Ponderosa Pine with a grassy understory. The interior sand grains of each sherd sample were analyzed using optically stimulated luminescence, which dates when the mineral grains were …

Island-Based Evolutionary Computation With Diverse Surrogates And Adaptive Knowledge Transfer For High-Dimensional Data-Driven Optimization, Xianrong Zhang, Yuejiao Gong, Zhiguang Cao, Jun Zhang

Research Collection School Of Computing and Information Systems

In recent years, there has been a growing interest in data-driven evolutionary algorithms (DDEAs) employing surrogate models to approximate the objective functions with limited data. However, current DDEAs are primarily designed for lower-dimensional problems and their performance drops significantly when applied to large-scale optimization problems (LSOPs). To address the challenge, this paper proposes an offline DDEA named DSKT-DDEA. DSKT-DDEA leverages multiple islands that utilize different data to establish diverse surrogate models, fostering diverse subpopulations and mitigating the risk of premature convergence. In the intra-island optimization phase, a semi-supervised learning method is devised to fine-tune the surrogates. It not only facilitates …

Digital Communications Between Firms And Investors: Impact Of Explanatory Responses On Investor Engagement In Online Financial Q&A, Runyu Wang, Zili Zhang, Keng Siau, Ziqiong Zhang

Research Collection School Of Computing and Information Systems

The emerging trend of digital communications between firms and investors through online question-and-answer (Q&A) platforms is recognized as a vital strategy for managing investor relations, contributing to enhanced market efficiency and information transparency through increased information exchange. Potential investors can seek responses from firm managers to address their information needs, thereby mitigating market uncertainties. To provide foundational insights, we conduct a survey of investors to assess their awareness, usage, and perceptions of firm-investor Q&A platforms. In the subsequent empirical study, we specifically focus on the substance of managers’ responses, which are primarily aimed at clarifying firm events or information. In …

Contx: Scene Context Prediction Via Context Bank And Layout Perception, Jingxin Liang, Yangyang Xu, Haorui Song, Yuan Lu, Yuhui Deng, Yiyi Long, Yan Huang, Shengxin Liu, Jianbo Jiao, Shengfeng He

Research Collection School Of Computing and Information Systems

Scene context prediction, which seeks to infer unknown contextual information from isolated object properties, currently faces limitations due to predominant reliance on pixel-wise supervision that overlooks real-world context priors. To address this, we present ContX, a context-prior-driven, coarse-to-fine model. ContX distinctively integrates explicit linguistic-contextual knowledge in two key ways. First, it proposes a linguistic guided context bank, leveraging linguistic-statistical contextual data to guide the rationality of segmentation shapes and foster meaningful inter-class contextual interactions. Second, ContX augments contextual comprehension by correlating layouts with linguistic descriptions, enhancing layout perception through a multi-modal strategy. Comprehensive experiments demonstrate ContX's superiority and versatility, outperforming …

Registration Is A Powerful Rotation-Invariance Learner For 3d Anomaly Detection, Yuyang Yu, Zhengwei Chen, Xuemiao Xu, Lei Zhang, Haoxin Yang, Yongwei Nie, Shengfeng He

Research Collection School Of Computing and Information Systems

3D anomaly detection in point-cloud data is critical for industrial quality control, aiming to identify structural defects with high reliability. However, current memory bank-based methods often suffer from inconsistent feature transformations and limited discriminative capacity, particularly in capturing local geometric details and achieving rotation invariance. These limitations become more pronounced when registration fails, leading to unreliable detection results. We argue that point-cloud registration plays an essential role not only in aligning geometric structures but also in guiding feature extraction toward rotation-invariant and locally discriminative representations. To this end, we propose a registration-induced, rotation-invariant feature extraction framework that integrates the objectives …

Rising From Ashes: Generalized Federated Learning Via Dynamic Parameter Reset, Jiahao Wu, Ming Hu, Yanxin Yang, Xiaofei Xie, Zekai Chen, Chenyu Song, Mingsong Chen

Research Collection School Of Computing and Information Systems

Although Federated Learning (FL) is promising for privacy-preserving collaborative model training, it suffers from low inference performance due to heterogeneous client data. Due to heterogeneous data across clients, FL training easily learns client-specific overfitting features. Existing FL methods adopt coarsegrained averaging, which can easily cause the global model to get stuck in local optima, leading to poor generalization. Specifically, this paper presents a novel FL framework, FedPhoenix, to address this issue. It stochastically resets partial parameters in each round to destroy some features of the global model, guiding FL training to learn multiple generalized features for inference rather than specific …

When Less Language Is More: Language-Reasoning Disentanglement Makes Llms Better Multilingual Reasoners, Weixiang Zhao, Jiahe Guo, Yang Deng, Tongtong Wu, Wenxuan Zhang, Yulin Hu, Xingyu Sui, Yanyan Zhao, Wanxiang Che, Bing Qin, Tat-Seng Chua, Ting Liu

Research Collection School Of Computing and Information Systems

Multilingual reasoning remains a significant challenge for large language models (LLMs), with performance disproportionately favoring high-resource languages. Drawing inspiration from cognitive neuroscience, which suggests that human reasoning functions largely independently of language processing, we hypothesize that LLMs similarly encode reasoning and language as separable components that can be disentangled to enhance multilingual reasoning. To evaluate this, we perform a causal intervention by ablating language-specific representations at inference time. Experiments on 10 open-weight LLMs spanning 11 typologically diverse languages show that this language-specific ablation consistently boosts multilingual reasoning performance. Layer-wise analyses further confirm that language and reasoning representations can be effectively …

Coresets For Clustering Under Stochastic Noise, Lingxiao Huang, Zhize Li, Nisheeth K. Vishnoi, Runkai Yang, Haoyu Zhao

Research Collection School Of Computing and Information Systems

We study the problem of constructing coresets for $(k, z)$-clustering when the input dataset is corrupted by stochastic noise drawn from a known distribution. In this setting, evaluating the quality of a coreset is inherently challenging, as the true underlying dataset is unobserved. To address this, we investigate coreset construction using surrogate error metrics that are tractable and provably related to the true clustering cost. We analyze a traditional metric from prior work and introduce a new error metric that more closely aligns with the true cost. Although our metric is defined independently of the noise distribution, it enables approximation …

Design Principles For Customer‑Engaging Digital Service Systems: An Action Research Study, Keng Siau, Xiaofeng Chen, Xin Tan

Research Collection School Of Computing and Information Systems

Digital services represent a business approach employed by organizations to operate in the digital environment. However, systematic development guidelines for developing quality digital service systems are lacking in the literature. The authors identified four general challenges for developing and implementing customer-engaging digital service systems (CEDSS). By employing the method of canonical action research in a digital service system project, they derived 10 design principles for developing high-quality CEDSS. They empirically evaluated the design principles in the development project and through follow-up focus group sessions. The design principles provide applicable and actionable guidelines for the development of CEDSS.

Accuracy-Enabling Differential Privacy-Preserving Truth Discovery, Man Zhang, Xinghua Li, Yinbin Miao, Bin Luo, Siqi Ma, Robert H. Deng

Research Collection School Of Computing and Information Systems

Perturbation-based privacy-preserving truth discovery requires the Service Provider (SP) to calculate the truthful aggregation result from perturbed data of the Data Sources (DSs), which inevitably damages the aggregation accuracy due to perturbation noise added in the data. Thus, the existing works attempt to relieve the perturbation errors by reducing noise amounts or adjusting aggregation weights of DSs. However, the former sacrifices DSs’ privacy preservation and the latter has the limited accuracy recovery performance. Aiming at it, we propose an accuracy-enabling differential privacy-preserving truth discovery consisting of an independence-guaranteed data perturbation module and a progressive-private noise elimination module. Specifically, in the …

Fl-Cdf: Collaborative Defense Framework For Backdoor Mitigation In Federated Learning, Haiyan Zhang, Xinghua Li, Yinbin Miao, Shunjie Yuan, Mengyao Zhu, Ximeng Liu, Robert H. Deng

Research Collection School Of Computing and Information Systems

Federated learning (FL) is vulnerable to backdoor attacks due to its distributed nature. Existing unilateral defense mechanisms often fail against persistent attack strategies, primarily due to their limited perspectives. To address the challenge of model misclassification on the server side caused by overlooked model similarity drift, and gradient misjudgment on the client side caused by semantic learning imbalances across classes, this paper proposes a collaborative defense framework for federated learning, termed FL-CDF. FL-CDF establishes an end-to-end defense through a bidirectional client-server collaboration mechanism. Specifically: (1) On the client side, an adversarial perturbation-based malicious neuron detection module is introduced. This module …

Genscore: Agent-Based Short-Answer Question Generation And Scoring In Software Engineering Courses, Nguyen Binh Duong Ta, Lwin Khin Shar

Research Collection School Of Computing and Information Systems

Short-answer questions are commonly used in educational assessments, as they are often viewed as a more effective way than multiple-choice questions to determine whether students have achieved the intended learning outcomes. However, manually creating appropriate questions targeting different cognitive levels such as those defined by the Bloom’s Taxonomy, and grading text answers from students are not trivial tasks for instructors. Existing work on auto-question generation and scoring in computing education typically targets coding-based questions. However, in software engineering courses, assessments can extend beyond coding to understanding of processes, DevOps methodologies, system design, etc. This work aims to address the dual …

Scalable Graph Indexing Using Gpus For Approximate Nearest Neighbor Search, Zhonggen Li, Xiangyu Ke, Yifan Zhu, Bocheng Yu, Baihua Zheng, Yunjun Gao

Research Collection School Of Computing and Information Systems

Approximate nearest neighbor search (ANNS) in high-dimensional vector spaces has a wide range of real-world applications. Numerous methods have been proposed to handle ANNS efficiently, while graph-based indexes have gained prominence due to their high accuracy and efficiency. However, the indexing overhead of graph-based indexes remains substantial. With exponential growth in data volume and increasing demands for dynamic index adjustments, this overhead continues to escalate, posing a critical challenge.In this paper, we introduce Tagore, a fasT library accelerated by GPUs for graph indexing, which has powerful capabilities of constructing refinement-based graph indexes such as NSG and Vamana. We first introduce …

Climate Change Has Increased Global Evaporative Demand Except In South Asia, Saeed Karimzadeh, Arman Ahmadi, Dennis Baldocchi, Joshua B. Fisher

Biology, Chemistry, and Environmental Sciences Faculty Articles and Research

Climate change alters how strongly the atmosphere draws water from the land, yet a consistent global assessment of this evaporative demand has been lacking. Here, we analyze 45 years of climate data and global models to quantify trends in the key drivers—air temperature, humidity, radiation, wind speed, and cloud cover—that determine the atmosphere’s drying power. We find that evaporative demand has increased worldwide, indicating a stronger atmospheric thirst, except in South Asia, where it has declined. There, widespread irrigation has increased soil and air moisture, enhanced cloud formation, and reduced sunlight reaching the surface, counteracting the global signal. These contrasting …

From Digital Divide To Equity-Enhancing Diffusion: Generative Ai And Writing Quality, Rebecca Tukachinsky Forster, Kerk Kee, Gabriel Miao Li

Communication Faculty Articles and Research

This study investigates whether generative AI can narrow the gap between stronger and developing writers and explores the mechanisms underlying these effects. In a within-subject experiment, students wrote two essays, with and without AI assistance. Computer-aided analysis of the writing quality confirmed that while all students benefited from AI, that less skillful writers gained more. There was also no evidence of skillful writers using AI in more sophisticated and beneficial ways. The study contributes to theorizing the digital divide and offers insights into maximizing the benefits of AI tools. Theoretically, we situate generative-AI use within Diffusion of Innovations, treating ChatGPT …

Benchmarking Dna Foundation Models For Genomic And Genetic Tasks, Haonan Feng, Lang Wu, Bingxin Zhao, Chad Huff, Jianjun Zhang, Jia Wu, Lifeng Lin, Peng Wei, Chong Wu

School of Medicine Faculty Publications

The rapid evolution of DNA foundation models promises to revolutionize genomics, yet comprehensive evaluations are lacking. Here, we present a comprehensive, unbiased benchmark of five models (DNABERT-2, Nucleotide Transformer V2, HyenaDNA, Caduceus-Ph, and GROVER) across diverse genomic and genetic tasks including sequence classification, gene expression prediction, variant effect quantification, and topologically associating domain (TAD) region recognition, using zero-shot embeddings. Our analysis reveals that mean token embedding consistently and significantly improves sequence classification performance, outperforming other pooling strategies. Model performance varies among tasks and datasets; while general purpose DNA foundation models showed competitive performance in pathogenic variant identification, they were less …

Improving Glycemic Control Among Indonesian Urban Adults: A Digital And Behavioral Extension Of The Information–Motivation–Behavioral Skills Model, Imelda Appulembang

Kesmas

Management of type 2 diabetes mellitus (T2DM) in Indonesia continues to face challenges due to behavioral, informational, and technological gaps among patients. This study analyzed the influence of self-regulatory competence and information, motivation, family support, and digital health literacy on glycemic control behavior. A cross-sectional survey was conducted from February to April 2025 among 587 adults aged >30 years with T2DM enrolled in the Chronic Disease Management Program at primary health care in six major cities: Jakarta, Surabaya, Yogyakarta, Medan, Makassar, and Banjarmasin. Data were collected through structured questionnaires and analyzed using partial least squares structural equation modeling. The findings …

Transdisciplinary Perspectives On Ai: The Fourth Annual Conference Of The European Culture And Technology Laboratory, Connell Vaughan, Ioana Madalina Moldovan, Silivan Moldovan, Noel Fitzpatrick

Books/Book Chapters

The fourth annual conference of the ECT Lab+ was hosted by Technical University of Cluj-Napoca over two days in October 2024 at the Cluj Innovation Park. The conference brought together experts from the Arts, Humanities, Social Sciences, Technology, and other fields to discuss and reflect on the advent of Artificial Intelligence and how the associated technologies are transforming how we live, work and study. Under the title Transdisciplinary perspectives on AI: Alternative Histories, Current Practices and Possible Futures the conference moved beyond simplistic technophila and technophobia to consider whether we can co-evolve with these new technologies which combine machine learning …

An Objective Method To Locate Shear Lines During The Northeast Monsoon Season In The Philippines, Lyndon Mark P. Olaguera, John A. Manalo, Jun Matsumoto, Faye Abigail T. Cruz, Jose Ramon T. Villarin

SOSE Affiliate: Manila Observatory

The shear line is a narrow zone of maximum horizontal wind shear, typically identified as a confluence zone of low-level wind streams. Previous studies showed that this system can trigger heavy to extreme rainfall events in the Philippines during the northeast monsoon season. However, a research gap remains in objectively identifying and locating this system. Thus, this study develops a detection method that may be used for monitoring and forecasting the location of shear lines. Results show that the gradient of meridional winds in the y-direction (∂V925hPa/∂y), the boundary layer moisture flux convergence, and the 925 hPa relative vorticity may …