Physical Sciences and Mathematics Commons^™

Space Transformation For Open Set Recognition, Atefeh Mahdavi

Theses and Dissertations

Open Set Recognition (OSR) is about dealing with unknown situations that were not learned by the models during training. In OSR, only a limited number of known classes are available at the time of training the model and the possibility of unknown classes never seen at training time emerges in the test environment. In such a setting, the unknown classes and their risk should be considered in the algorithm. Such systems require not only to identify and discriminate instances that belong to the source domain (i.e., the seen known classes contained in the training dataset) but also to reject unknown …

Investigating The Impact Of Human-Centered Interface Design On The User Experience Of Mobile Device Users, Ruchir Gupta

Theses and Dissertations

In order to investigate the intricate interaction between interface design, user technological proficiency, and other components of the user experience, this research study used a mixed-method approach. The beginner user group—those with little experience or expertise with technology - were the main target audience. The important discovery emphasizes the substantial influence that careful design can have on improving the effectiveness and usability of interfaces for non-tech-savvy individuals. When using the suggested Interface B instead of the current Interface A, beginner participants' task completion times significantly improved, according to the user study. This underlines the significance of creating with the needs …

Development Of Chiral Lewis Base Catalysts For Chlorosilane-Mediated Asymmetric C-C Bond Formations, Changgong Xu

Theses and Dissertations

The chiral hydrazine is a crucial structural motif that serves as pivotal structural elements in numerous natural products and biologically significant molecules. We are particularly interested in the catalytic asymmetric reduction of hydrazones, as well as the catalytic asymmetric propargylation and allenylation of hydrazones, because they provide direct pathways to these enantio-enriched chiral building blocks. In this work, we will explore the potential of two different categories of chiral Lewis base catalysts in the said transformations.

Developed by another student in our group, axial-chiral 3,3’-triazolyl biisoquinoline N,N’-dioxides derived catalysts are tested and demonstrated its capability in activating various hydrazone …

Using Predictive Analytics To Identify Risk Of Heart Disease Based On Lifestyle Factors And Health Metrics., Luiza Cavalcanti Albuquerque Brayner, Edgard Pacheco

ICT

In this project, we will report an innovative application, for the healthcare sector usage, which basically is a health tracking and disease prevention application. The application will enable users to log their daily meals, exercise routines, and lifestyle habits, providing a comprehensive overview of the user's health status. By making use of Machine Learning and data analytics, our solution offers a personalised and automated insight and predictive analytics, which empowers users to proactively manage their well-being.

Through a detailed data analysis, users will gain valuable insights of potential diseases development and risk. This report will explore the development process, implementation …

Hilbert Reciprocity Over Number Fields, Dillon Snyder

Honors Scholar Theses

A Hilbert symbol has the value 1 or −1 depending on the existence of solutions to a certain quadratic equation in a local field, R, or C. Hilbert reciprocity states that for a number field F and two nonzero a and b in F, the product of Hilbert symbols associated to a and b at all the places of F is 1. That is, these Hilbert symbols are −1 for a finite, even number of places of F . Hilbert reciprocity when F = Q is equivalent to the classical quadratic reciprocity law, so Hilbert reciprocity in number fields can …

A Ui-Enhanced Approach To Generic Web-Based Scheduling, Tyler Hinrichs

Honors Scholar Theses

Administrative scheduling is a key aspect of a wide variety of systems, but despite being a widespread need, it is not a straightforward task. Organizational uniqueness introduces complexity when attempting to use algorithmic methods to automate scheduling, as individual organizations often have their own ways of determining various details and constraints of a schedule. However, in this paper, we assert that there are relevant commonalities that many different schedules fundamentally possess, allowing us to create a generic scheduling application that can be productively used for as many different scenarios as possible. After devising a schema that captures this generic representation, …

Implementation Of Explainable Ai For Bearing Fault Classification, Mohammad Mundiwala

Honors Scholar Theses

It is difficult to overstate the impact of artificial intelligence (AI) over the past decade. The rapid expansion of machine learning has stimulated a race to deploy AI in all facets of life, one such domain being machine health monitoring. There is no doubt that machine learning excels in prediction accuracy, but oftentimes, these models are cryptic and fail to provide valuable insight into their decisions. This paper presents an overview of a neural network and what it means to learn. Next, two distinct Explainable AI (XAI) techniques will be presented: Gradient Class Activation Mapping and SimplEx . Finally, these …

How Does Hummock Creation In Submerging Salt Marshes Alter Nitrous Oxide Fluxes?, Juliette Doyle

Honors Scholar Theses

Climate change is altering ecosystems and the services they provide. Salt marsh ecosystems typically protect coastal areas and filter nitrogen out of water, but are rapidly submerging due to rising sea levels and human development that prevents landward migration. Recent restoration efforts to preserve salt marshes attempt to build elevation capital and promote vegetation and animal habitat, but it is unclear how such efforts affect salt marsh biogeochemistry and dynamics of nitrous oxide, a potent greenhouse gas. To better understand how adding sediment to submerging salt marshes may alter nitrous oxide fluxes, I leveraged a salt marsh hummock creation experiment …

Quantum Machine Learning For Credit Scoring, Nikolaos Schetakis, Davit Aghamalyan, Micheael Boguslavsky, Agnieszka Rees, Marc Rakotomalala, Paul Robert Griffin

Research Collection School Of Computing and Information Systems

This study investigates the integration of quantum circuits with classical neural networks for enhancing credit scoring for small- and medium-sized enterprises (SMEs). We introduce a hybrid quantum–classical model, focusing on the synergy between quantum and classical rather than comparing the performance of separate quantum and classical models. Our model incorporates a quantum layer into a traditional neural network, achieving notable reductions in training time. We apply this innovative framework to a binary classification task with a proprietary real-world classical credit default dataset for SMEs in Singapore. The results indicate that our hybrid model achieves efficient training, requiring significantly fewer epochs …

Heterogeneous Federated Learning At Scale, Dmitry Lukyanov

All Theses

Federated learning has emerged as a solution to the challenges faced by traditional centralized machine learning approaches, such as data privacy, security, ownership, and computational bottlenecks. However, federated learning itself introduced new challenges, including system heterogeneity and scalability. Existing federated learning approaches, such as hierarchical and heterogeneous federated learning, address some of these challenges but have limitations in real-world scenarios where multiple issues coexist, particularly in large-scale, heterogeneous environments like mobile applications and IoT devices. This work proposes a new federated learning architecture that combines heterogeneous federated learning and hierarchical federated learning into a unified architecture. The proposed approach aims …

A Post-Quantum Mercurial Signature Scheme, Madison Mabe

All Theses

This paper introduces the first post-quantum mercurial signature scheme. We also discuss how this can be used to construct a credential scheme, as well as some practical applications for the constructions.

Assessing Equitable Distribution Of The Urban Tree Canopy At The Neighborhood Scale In Greenville, South Carolina., April Riehm

All Theses

We are living in an era that necessitates adaptation and resilience. The Earth is warming. Our climate has changed (EPA, 2016). Our planet is also rapidly urbanizing. It is predicted that 68% of people will live in cities by 2050. The City of Greenville is a rapidly growing city in South Carolina that has been losing its tree canopy to development(City of Greenville, 2023). The Urban Tree Canopy (UTC) is a community asset that provides many quality-of-life benefits including improved air quality, stormwater management, carbon sequestration, mental and physical well-being, increased mobility and access, aesthetics, a reduction in energy costs, …

The Impacts Of Wind On Coastal Trees, Julian Halil

All Theses

Trees in hurricane-prone areas are exposed to severe winds and flooding. We studied the physiological and structural responses of forested wetland trees in relation to wind stress. We evaluated the windfirmness of two forested wetland tree species. Baldcypress was chosen because of high survival in post-hurricane studies. In contrast, laurel oak co-occurs with baldcypress yet resists hurricane-force winds poorly. In a static winching study, we quantified the critical turning moment (Mcrit) required to topple both species. Mcrit increased with trunk diameter at breast height (DBH) and crown size. Baldcypress and laurel oak demonstrated similar Mcrit, but regression models indicate baldcypress …

Low-Resource Icd Coding Of Discharge Summaries, Ashton Williamson

All Theses

Medical coding is the process by which standardized medical codes are assigned to patient health records. This is a complex and challenging task that typically requires an expert human coder to review health records and assign codes from a classification system based on a standard set of rules. Considering the downstream use of these codes in statistical analysis, billing, and patient care, improving the accuracy and efficiency of the medical coding process through automation could have a far-reaching impact on the healthcare domain. Since health records typically consist of a large proportion of free-text documents, this problem has traditionally been …

Using Strainmeters To Characterize Enhanced Geothermal Systems, Clem Laffaille

All Theses

none

Ramanujan Type Congruences For Quotients Of Klein Forms, Timothy Huber, Nathaniel Mayes, Jeffery Opoku, Dongxi Ye

School of Mathematical and Statistical Sciences Faculty Publications and Presentations

In this work, Ramanujan type congruences modulo powers of primes p≥5 are derived for a general class of products that are modular forms of level p. These products are constructed in terms of Klein forms and subsume generating functions for t-core partitions known to satisfy Ramanujan type congruences for p=5,7,11. The vectors of exponents corresponding to products that are modular forms for Γ1(p) are subsets of bounded polytopes with explicit parameterizations. This allows for the derivation of a complete list of products that are modular forms for Γ1(p) of weights 1≤k≤5 for primes 5≤p≤19 and whose Fourier coefficients …

Brain-Inspired Continual Learning: Rethinking The Role Of Features In The Stability-Plasticity Dilemma, Hikmat Khan

Theses and Dissertations

Continual learning (CL) enables deep learning models to learn new tasks sequentially while preserving performance on previously learned tasks, akin to the human's ability to accumulate knowledge over time. However, existing approaches to CL face the challenge of catastrophic forgetting, which occurs when a model's performance on previously learned tasks declines after learning the new task. In this dissertation, we focus on the crucial role of input data features in determining the robustness of CL models to mitigate catastrophic forgetting. We propose a framework to create CL-robustified versions of standard datasets using a pre-trained Oracle CL model. Our experiments show …

A Survey Of Current Perceptions And Actual Use By Students And Faculty Of Generative Artificial Intelligence In Higher Education, Cameron Hasselbaum

Honors College

Generative AI as an emerging new technology may have large-scale impacts on how business is conducted and how schools teach students. OpenAI released ChatGPT to the public in November of 2022. Two similar surveys were conducted one year after ChatGPT was released in December 2023 to measure the perceptions of generative AI and changes in behavior in the academic space among students and faculty at the University of Maine. The survey findings were that student respondents have been quicker to adopt and find utility in the new technology. Still, it has yet to be readily adopted for use as widely …

Knowledge Enhanced Multi-Intent Transformer Network For Recommendation, Ding Zou, Wei Wei, Feida Zhu, Chuanyu Xu, Tao Zhang, Chengfu Huo

Research Collection School Of Computing and Information Systems

Incorporating Knowledge Graphs (KGs) into Recommendation has attracted growing attention in industry, due to the great potential of KG in providing abundant supplementary information and interpretability for the underlying models. However, simply integrating KG into recommendation usually brings in negative feedback in industry, mainly due to the ignorance of the following two factors: i) users' multiple intents, which involve diverse nodes in KG. For example, in e-commerce scenarios, users may exhibit preferences for specific styles, brands, or colors. ii) knowledge noise, which is a prevalent issue in Knowledge Enhanced Recommendation (KGR) and even more severe in industry scenarios. The irrelevant …

Automatic Grading Of Short Answers Using Large Language Models In Software Engineering Courses, Nguyen Binh Duong Ta, Yi Meng Chai

Research Collection School Of Computing and Information Systems

Short-answer based questions have been used widely due to their effectiveness in assessing whether the desired learning outcomes have been attained by students. However, due to their open-ended nature, many different answers could be considered entirely or partially correct for the same question. In the context of computer science and software engineering courses where the enrolment has been increasing recently, manual grading of short-answer questions is a time-consuming and tedious process for instructors. In software engineering courses, assessments concern not just coding but many other aspects of software development such as system analysis, architecture design, software processes and operation methodologies …

Learning Adversarial Semantic Embeddings For Zero-Shot Recognition In Open Worlds, Tianqi Li, Guansong Pang, Xiao Bai, Jin Zheng, Lei Zhou, Xin Ning

Research Collection School Of Computing and Information Systems

Zero-Shot Learning (ZSL) focuses on classifying samples of unseen classes with only their side semantic information presented during training. It cannot handle real-life, open-world scenarios where there are test samples of unknown classes for which neither samples (e.g., images) nor their side semantic information is known during training. Open-Set Recognition (OSR) is dedicated to addressing the unknown class issue, but existing OSR methods are not designed to model the semantic information of the unseen classes. To tackle this combined ZSL and OSR problem, we consider the case of “Zero-Shot Open-Set Recognition” (ZS-OSR), where a model is trained under the ZSL …

Attribute-Hiding Fuzzy Encryption For Privacy-Preserving Data Evaluation, Zhenhua Chen, Luqi Huang, Guomin Yang, Willy Susilo, Xingbing Fu, Xingxing Jia

Research Collection School Of Computing and Information Systems

Privacy-preserving data evaluation is one of the prominent research topics in the big data era. In many data evaluation applications that involve sensitive information, such as the medical records of patients in a medical system, protecting data privacy during the data evaluation process has become an essential requirement. Aiming at solving this problem, numerous fuzzy encryption systems for different similarity metrics have been proposed in literature. Unfortunately, the existing fuzzy encryption systems either fail to achieve attribute-hiding or achieve it, but are impractical. In this paper, we propose a new fuzzy encryption scheme for privacy-preserving data evaluation based on overlap …

An Adaptive Large Neighborhood Search For The Multi-Vehicle Profitable Tour Problem With Flexible Compartments And Mandatory Customers, Vincent F. Yu, Nabila Yuraisyah Salsabila, Aldy Gunawan, Anggun Nurfitriani Handoko

Research Collection School Of Computing and Information Systems

The home-refill delivery system is a business model that addresses the concerns of plastic waste and its impact on the environment. It allows customers to pick up their household goods at their doorsteps and refill them into their own containers. However, the difficulty in accessing customers’ locations and product consolidations are undeniable challenges. To overcome these issues, we introduce a new variant of the Profitable Tour Problem, named the multi-vehicle profitable tour problem with flexible compartments and mandatory customers (MVPTPFC-MC). The objective is to maximize the difference between the total collected profit and the traveling cost. We model the proposed …

Cmd: Co-Analyzed Iot Malware Detection And Forensics Via Network And Hardware Domains, Ziming Zhao, Zhaoxuan Li, Jiongchi Yu, Fan Zhang, Xiaofei Xie, Haitao Xu, Binbin Chen

Research Collection School Of Computing and Information Systems

With the widespread use of Internet of Things (IoT) devices, malware detection has become a hot spot for both academic and industrial communities. Existing approaches can be roughly categorized into network-side and host-side. However, existing network-side methods are difficult to capture contextual semantics from cross-source traffic, and previous host-side methods could be adversary-perceived and expose risks for tampering. More importantly, a single perspective cannot comprehensively track the multi-stage lifecycle of IoT malware. In this paper, we present CMD, a co-analyzed IoT malware detection and forensics system by combining hardware and network domains. For the network part, CMD proposes a tailored …

Enhancing Visual Grounding In Vision-Language Pre-Training With Position-Guided Text Prompts, Alex Jinpeng Wang, Pan Zhou, Mike Zheng Shou, Shuicheng Yan

Research Collection School Of Computing and Information Systems

Vision-Language Pre-Training (VLP) has demonstrated remarkable potential in aligning image and text pairs, paving the way for a wide range of cross-modal learning tasks. Nevertheless, we have observed that VLP models often fall short in terms of visual grounding and localization capabilities, which are crucial for many downstream tasks, such as visual reasoning. In response, we introduce a novel Position-guided Text Prompt ( PTP ) paradigm to bolster the visual grounding abilities of cross-modal models trained with VLP. In the VLP phase, PTP divides an image into N x N blocks and employs a widely-used object detector to identify objects …

Vaid: Indexing View Designs In Visual Analytics System, Lu Ying, Aoyu Wu, Haotian Li, Zikun Deng, Ji Lan, Jiang Wu, Yong Wang, Huamin Qu, Dazhen Deng, Yingcai Wu

Research Collection School Of Computing and Information Systems

Visual analytics (VA) systems have been widely used in various application domains. However, VA systems are complex in design, which imposes a serious problem: although the academic community constantly designs and implements new designs, the designs are difficult to query, understand, and refer to by subsequent designers. To mark a major step forward in tackling this problem, we index VA designs in an expressive and accessible way, transforming the designs into a structured format. We first conducted a workshop study with VA designers to learn user requirements for understanding and retrieving professional designs in VA systems. Thereafter, we came up …

Social Balance On Networks: Local Minima And Best-Edge Dynamics, Krishnendu Chatterjee, Jakub Svoboda, Dorde Zikelic, Andreas Pavlogiannis, Josef Tkadlec

Research Collection School Of Computing and Information Systems

Structural balance theory is an established framework for studying social relationships of friendship and enmity. These relationships are modeled by a signed network whose energy potential measures the level of imbalance, while stochastic dynamics drives the network toward a state of minimum energy that captures social balance. It is known that this energy landscape has local minima that can trap socially aware dynamics, preventing it from reaching balance. Here we first study the robustness and attractor properties of these local minima. We show that a stochastic process can reach them from an abundance of initial states and that some local …

From Tweets To Token Sales: Assessing Ico Success Through Social Media Sentiments, Donghao Huang, S. Samuel, Quoc Toan Huynh, Zhaoxia Wang

Research Collection School Of Computing and Information Systems

With the advent of social network technology, the influence of collective opinions has significantly impacted business, marketing, and fundraising. Particularly in the blockchain space, Initial Coin Offerings (ICOs) gain substantial exposure across various online platforms. Yet, the intricate relationships among these elements remain largely unexplored. This study aims to investigate the relationships between social media sentiment, engagement metrics, and ICO success. We hypothesize a positive correlation between favorable sentiment in ICO-related tweets and overall project success. Additionally, we recognize social media engagement indicators (mentions, retweets, likes, follower counts) as critical factors affecting ICO performance. Employing machine learning techniques, we conduct …

Exploring Diffusion Time-Steps For Unsupervised Representation Learning, Zhongqi Yue, Jiankun Wang, Qianru Sun, Lei Ji, Eric I-Chao Chang, Hanwang Zhang

Research Collection School Of Computing and Information Systems

Representation learning is all about discovering the hidden modular attributes that generate the data faithfully. We explore the potential of Denoising Diffusion Probabilistic Model (DM) in unsupervised learning of the modular attributes. We build a theoretical framework that connects the diffusion time-steps and the hidden attributes, which serves as an effective inductive bias for unsupervised learning. Specifically, the forward diffusion process incrementally adds Gaussian noise to samples at each time-step, which essentially collapses different samples into similar ones by losing attributes, e.g., fine-grained attributes such as texture are lost with less noise added (i.e., early time-steps), while coarse-grained ones such …

Regret-Based Defense In Adversarial Reinforcement Learning, Roman Belaire, Pradeep Varakantham, Thanh Hong Nguyen, David Lo

Research Collection School Of Computing and Information Systems

Deep Reinforcement Learning (DRL) policies are vulnerable to adversarial noise in observations, which can have disastrous consequences in safety-critical environments. For instance, a self-driving car receiving adversarially perturbed sensory observations about traffic signs (e.g., a stop sign physically altered to be perceived as a speed limit sign) can be fatal. Leading existing approaches for making RL algorithms robust to an observation-perturbing adversary have focused on (a) regularization approaches that make expected value objectives robust by adding adversarial loss terms; or (b) employing "maximin'' (i.e., maximizing the minimum value) notions of robustness. While regularization approaches are adept at reducing the probability …