Physical Sciences and Mathematics Commons^™

Learning To Represent Temporal Dynamics And Generative Factors For Intelligent Visual Navigation, Sahand Khoshdel

All Theses

Visual navigation systems are crucial in various applications, including autonomous driving, unmanned aerial systems (UAS), and industrial automation. For these systems to operate efficiently in dynamic environments, they must not only interpret complex surroundings but also anticipate changes over time. Temporal prediction—forecasting environmental changes like moving obstacles or shifting lighting conditions—enables navigation systems to act proactively, enhancing both safety and performance. This dissertation investigates representation learning methods both as a backbone feature extractor for RL agents as well as a proxy for systems oriented for Explainable AI (XAI). Two main projects are presented as case studies to achieve the aforementioned …

Toward A Globally Lunar Calendar: A Machine Learning-Driven Approach For Crescent Moon Visibility Prediction, Samia Loucif, Murad Al-Rajab, Raed Abu Zitar, Mahmoud Rezk

All Works

This paper presents a comprehensive approach to harmonizing lunar calendars across different global regions, addressing the long-standing challenge of variations in new crescent Moon sightings that mark the beginning of lunar months. We propose a machine learning (ML)-based framework to predict the visibility of the new crescent Moon, representing a significant advancement toward a globally unified lunar calendar. Our study utilized a dataset covering various countries globally, making it the first to analyze all 12 lunar months over a span of 13 years. We applied a wide array of ML algorithms and techniques. These techniques included feature selection, hyperparameter tuning, …

User Acceptance Of Ai Voice Assistants In Jordan's Telecom Industry, Mousa Al-Kfairy, Dheya Mustafa, Ahmed Al-Adaileh, Samah Zriqat, Obsa Sendaba

All Works

Purpose: This study aims to understand factors influencing consumer acceptance of artificial intelligence (AI) voice assistants used in customer support within telecom companies in Jordan. Methodology: A survey was conducted involving 248 individuals who have experience with telecom support services. To evaluate consumer acceptance, the study incorporates the Unified Theory of Acceptance and Use of Technology (UTAUT) framework and extends it with attributes specific to AI, such as Perceived Reliability, Voice Quality, and Quality of Information. Advanced statistical methods, including structural equation modeling with SPSS AMOS 28 and SmartPLS, were utilized to analyze the collected data. Findings: The results revealed …

Chatgpt In Higher Education - A Student's Perspective, Ahmed Shuhaiber, Mohammad Amin Kuhail, Sinan Salman

All Works

The purpose of this study is to assess the impact of factors influencing students' adoption of ChatGPT within the context of higher education. With the rapid expansion of its user base and its increasing utilization across various fields, there is a pressing need to comprehensively explore students' interactions and experiences with this innovative technology, a topic largely unaddressed in existing literature. This paper aims to identify the factors contributing to ChatGPT's rapid proliferation and to highlight its potential for reshaping higher education. To achieve our research objective, we extend the Unified Theory of Acceptance and Use of Technology (UTAUT2) with …

A Comparative Analysis Of Early Algebraic Thinking Activities From U.S. And Singapore Primary Textbooks, Christian Joel Hernandez

Theses and Dissertations

Many studies highlight the challenges students face when transitioning to algebra at the secondary level. Introducing algebraic concepts and fostering algebraic thinking at the primary level can help mitigate these difficulties. Prior to formal algebra instruction, early algebra can be cultivated as a mode of thinking known as algebraic thinking. Several international curricula, such as Singapore Math, incorporate early algebraic thinking into the early stages of schooling. Singapore Math, renowned for its high performance in international assessments, has been widely adopted by schools seeking to replicate its success.

This study compares two primary-level mathematics curricula—CCSSM-aligned textbooks and Singapore Math—specifically focusing …

Machine Learning Methods For Quantification Of Glacier Variations Through Satellite Imagery, Robert D. Breininger

Theses and Dissertations

Glaciers around the world have experienced a trend of recession within the past century. Quantification of glacier variations using satellite imagery is of great interest due to the importance of glaciers as freshwater resources and as indicators of climate change. The potential methods to quantify glacier variations with increasing complexity include detecting the terminus location, quantifying the glacier surface area, and measuring glacier volume. Although there are methods in literature designed purposefully for glacier area segmentation that have achieved acceptable results, they are often localized to the region where their training data were acquired and further rely on training sets …

Morphometric Based Roughness Estimates For Wind Loading Applications In The Coastal Transition Zone, Hadley Rose Besing

Theses and Dissertations

This project was developed to support the Florida Tech Wireless Sensor Network System (WSNS) hurricane research team in determining wind loads during high-impact wind events. The WSNS team objectives included estimating the critical pressure (𝐶_p) from observed 3-s gusts during high impact weather events (tropical cyclones). The field work was conducted at a single-story residential home in Satellite Beach, FL approximately 400 m from the coast. During data collection periods, more than 1-million 20-second LiDAR wind profiles were observed.

The bulk roughness at the test residence is characterized utilizing an existing morphometric technique with geometry that is derived …

Advancing Grid Modernization Through Data-Driven Resilience Modeling And Hosting Capacity Of Distributed Energy Resources, Oscar Samuel Acosta

Open Access Theses & Dissertations

This Ph.D. dissertation focuses on advancing the integration of distributed energy resources (DERs) through concepts surrounding their impacts on power system stability, resilience, and hosting capacity (HC). This dissertation addresses crucial topics in renewable energy deployment, transient fault response, and dynamic modeling. The work begins with the development of renewable energy source (RES) models tailored for offsetting residential heating, ventilation, and air conditioning~(HVAC) and commercial cooling loads. These models utilize solar photovoltaic (PV) and wind energy systems to produce scalable frameworks adapted across diverse climates and building types in application of a partial-load targeting methodology. The dissertation then transitions from …

A Machine Learning Approach For Estimating Evapotranspiration For Urban Landscaping Vegetation In Semi-Arid Regions, Damian Lorenzo Gallegos Espinoza

Open Access Theses & Dissertations

Water management is important for residents in semi-arid urban areas due to increasing demand, water scarcity, and rising costs. It is estimated that in semi-arid regions, 40-70% of the household water consumption is used in landscaping. Therefore, urban landscaping water use can substantially contribute to water conservation. This work aims to estimate the water needs of urban landscaping vegetation to inform residents in semi-arid regions.Evapotranspiration indicates water and energy exchange between the atmosphere, soil, and vegetation. This interaction depends on solar radiation, evaporation, transpiration, and other biophysical parameters. Evapotranspiration has become a reference for water management in agriculture (e.g., crop …

Efficient Anomaly Detection Driven By Different Machine Learning Architectures And Models, William Marfo

Open Access Theses & Dissertations

The rapid growth and ubiquitous adoption of the internet and cyber-physical systems (CPS) have fundamentally transformed modern communication, work, and human-system interactions. While networks now form the backbone of critical digital ecosystems, enabling seamless data transmission across diverse, interconnected systems, this increased connectivity also expands the attack surface, making real-time detection of network intrusions and anomalies a pressing challenge. Detecting unusual activities within network infrastructure requires advanced data traffic analysis to differentiate between legitimate and malicious interactions. Traditional approaches to network anomaly detectionâ??such as rule-based and signature-based systemsâ??often depend on predefined patterns to identify known anomalies, limiting their effectiveness against …

Using The Schism Model And Hf Radar Data To Study Surface Currents In Texas Bays: A Case Study Of Sabine Lake (Sl) And Galveston Bay (Gb)., Cletus Ozoemena Ogbodo

Open Access Theses & Dissertations

Surface currents study provides invaluable understanding into the physical dynamics of oceans, bays, estuaries, and nearshore environments, offering critical insights about water movement and related coastal processes. These currents play a fundamental role in understanding the state of estuarine and marine systems, such as their effects on sediment transport, heat distribution and climate change, nutrient distribution, and pollutant dispersal. In addition, surface current data provides significant economic and ecological implications for coastal communities essential for managing resources effectively and ensuring the resilience of coastal regions against environmental and anthropogenic pressures. This study was driven by the need to address the …

The United States National Security And Policy Implications Of Desertification, Eric Olvera

Open Access Theses & Dissertations

Contemporary climate security literature reveals that desertification appears to be overlooked as a climate change security threat to the United States (US). This investigation demonstrates that an inequity exists between sea-level-rise- and desertification-based climate security literature. This inequity may reveal that the US may be ignoring desertification at a time when land use in some dryland areas is reaching a critical point where it can no longer support human activity. Due to the interdisciplinary nature (science and security) of this work, a review of the terminology used in the article is provided to establish a baseline understanding of “desertification” and …

Computational Investigation Of Boundary-Layer Transition Mechanisms In A Blunt Cone, Arturo Rodriguez

Open Access Theses & Dissertations

In this study, we have performed two-dimensional steady-state hypersonic CFD and one-and-two-dimensional steady-state heat conduction numerical simulations. We are using them to guide and study hypersonic boundary-layer transition ground testing physical experiments to be performed at Holloman High-Speed Test Track. We use surface heat transfer and fluid flow spot signatures to identify fluid flow regimes using laminar and turbulent numerical simulation solvers to understand boundary-layer transition thermocouple temperatures and fluid flow-forming structures. We have also analyzed the fluid flow in the geometries to be inviscid. We passed the CFD solution into the boundary-layer Harris code developed by NASA to explore …

Synthesis Of Photocleavable Molecules For Neurological Applications, Nishal Madujith Egodawaththa Arachchilage Don

Theses and Dissertations

In recent biomedical research, the precise control of molecular dynamics through light activation has emerged as a powerful tool, particularly in the field of neurobiology. This approach involves the use of photocleavable cages or photoprotective groups (PPGs) that are chemically tethered to biologically active molecules such as neurotransmitters or calcium chelators. These cages remain inert until exposed to specific wavelengths of light, typically in the visible range, triggering the release of the active compound with high spatiotemporal precision.

For neurotransmitter systems, such as glutamate (Glu), which plays a critical role in synaptic transmission and memory formation, researchers have developed novel …

A Machine Learning Approach For Survival Analysis Of Transplanted Kidneys Based On Donors’ And Recipients’ Factors., Alain Edward Despeignes

Theses and Dissertations

Over seven thousand people on average die each year in the United States waiting for an organ transplant due to the shortage of donated organs. With this alarming concern, efforts from the health organizations like the United Network Organ Sharing (UNOS) and government officials have considered avenues to remedy this distress, one of which is to investigate the characteristics among donors and recipients that affects the longevity of donated organs. The goal of this project is to investigate the survival time of transplanted kidneys from 1987 to 2018 with regards to the donors’ and the recipients’ characteristics including gender, ethnicity, …

Novel, Ultra-Fast Electrochemical Sensors For The Enhanced Detection Of Neurotransmitters And Toxic Heavy Metals In Aqueous Solutions, Noel Manring

Theses and Dissertations

Neurodegenerative diseases (NDDs) are a growing global health concern, affecting millions of people worldwide. NDDs arise from the progressive loss of neuronal cell function, ultimately leading to cell death. Abnormal levels of neurotransmitters, the chemical messengers in the brain, have also been linked to NDDs. Despite various treatments and medications aimed at alleviating physical and mental symptoms, there is currently no cure or means to halt disease progression. While the exact pathogenesis of NDDs remain poorly understood, cognitive decline is largely attributed to brain volume reduction, particularly in the hippocampus. Clinical studies suggest that environmental factors, such as exposure to …

Advancing Biofabrication Methodologies To Develop Biomimetic Tissue Scaffolds For Musculoskeletal Applications, Nashaita Yezdi Patrawalla

Theses and Dissertations

Musculoskeletal injuries impose a significant global burden, affecting millions and generating an economic toll exceeding $14 billion. Tissue engineering has gained traction as a promising strategy offering potential for functional restoration of damaged musculoskeletal tissues. This research aims to advance biofabrication techniques for generation of biomimetic tissue scaffolds, by optimizing scaffold design and modulating fabrication process parameters to generate scaffolds for musculoskeletal regeneration with application-specific tailored properties. In this realm, collagen-based biomaterials have been extensively investigated for tendon and ligamentous applications, and in combination with bioceramics incorporated into the collagen framework to produce composite scaffolds that better recapitulate the native …

Decoding Neural Networks: An Information-Theoretic Guide To Interpretability, Error Analysis And Efficiency, Mackenzie J. Meni

Theses and Dissertations

This dissertation addresses critical challenges in neural network design by leveraging entropy-based techniques to improve model efficiency, interpretability, and bias reduction. Focusing on the unique demands of computer vision applications, particularly object detection and classification for real-time systems, this work introduces a series of innovative methods centered on information theory. At the core of these methods is the Probabilistic Explanations of Entropic Knowledge (PEEK) framework, a tool developed to analyze and visualize entropy distributions across feature maps. PEEK offers insights into information flow within neural networks, making it possible to pinpoint layers that contribute meaningfully to decision-making or identify those …

An Examination Of Hilbert Spaces, Fnu Sumaiya

Theses and Dissertations

This independent study focuses on the exploration of Hilbert spaces, a cornerstone of modern analysis and a fundamental construct in mathematics. It starts by introducing vector space, metric and metric spaces and then Hilbert spaces and its properties.

This study includes good amount of mathematical proofs, theorems and examples. Through extensive research and analysis, this independent study aims to offer a comprehensive examination of Hilbert spaces, detailing their properties and their pivotal role in modern analysis.

Artificial Intelligence And Machine Learning In Cancer Pain: A Systematic Review, Vivian Salama, Brandon Godinich, Yimin Geng, Laia Humbert-Vidan, Laura Maule, Mohamed A Naser, Abdallah S R Mohamed, Clifton D Fuller, Amy C Moreno

Faculty, Staff and Student Publications

Background/objectives: Pain is a challenging multifaceted symptom reported by most cancer patients. This systematic review aims to explore applications of artificial intelligence/machine learning (AI/ML) in predicting pain-related outcomes and pain management in cancer.

Methods: A comprehensive search of Ovid MEDLINE, EMBASE and Web of Science databases was conducted using terms: "Cancer," "Pain," "Pain Management," "Analgesics," "Artificial Intelligence," "Machine Learning," and "Neural Networks" published up to September 7, 2023. AI/ML models, their validation and performance were summarized. Quality assessment was conducted using PROBAST risk-of-bias andadherence to TRIPOD guidelines.

Results: Forty four studies from 2006 to 2023 were included. Nineteen studies used …

A Shared Mechanism For Tnp-Atp Recognition By Members Of The P2x Receptor Family, Jin Wang, Motoyuki Hattori, Chang-Zhu Li, Ye Yu, Chang-Run Guo

Faculty, Staff and Student Publications

P2X receptors (P2X1-7) are non-selective cation channels involved in many physiological activities such as synaptic transmission, immunological modulation, and cardiovascular function. These receptors share a conserved mechanism to sense extracellular ATP. TNP-ATP is an ATP derivative acting as a nonselective competitive P2X antagonist. Understanding how it occupies the orthosteric site in the absence of agonism may help reveal the key allostery during P2X gating. However, TNP-ATP/P2X complexes (TNP-ATP/human P2X3 (hP2X3) and TNP-ATP/chicken P2X7 (ckP2X7)) with distinct conformations and different mechanisms of action have been proposed. Whether these represent species and subtype variations or experimental differences remains unclear. Here, we show …

A Near-Wall Methodology For Large-Eddy Simulation Based On Dynamic Hybrid Rans-Les, Michael Tullis, D. Keith Walters

Mechanical Engineering Faculty Publications and Presentations

Attempts to mitigate the computational cost of fully resolved large-eddy simulation (LES) in the near-wall region include both the hybrid Reynolds-averaged Navier–Stokes/LES (HRL) and wall-modeled LES (WMLES) approaches. This paper presents an LES wall treatment method that combines key attributes of the two, in which the boundary layer mesh is sized in the streamwise and spanwise directions comparable to WMLES, and the wall-normal mesh is comparable to a RANS simulation without wall functions. A mixing length model is used to prescribe an eddy viscosity in the near-wall region, with the mixing length scale limited based on local mesh size. The …

Optimal Strategy For Handling Unbalanced Medical Datasets: Performance Evaluation Of K-Nn Algorithm Using Sampling Techniques, Yulita Salim, Aulia Putri Utami, Abdul Rachman Manga, Huzain Azis, Fadhila Tangguh Admojo

Knowledge Engineering and Data Science

This study addresses the critical role of medical image classification in enhancing healthcare effectiveness and tackling the challenges of imbalanced medical datasets. It focuses on optimizing classification performance by integrating Canny edge detection for segmentation and Hu-moment feature extraction and applying oversampling and undersampling techniques. Five diverse medical datasets were utilized, covering Alzheimer’s and Parkinson’s diseases, COVID-19, brain tumours, and lung cancer. The K-Nearest Neighbors (K-NN) algorithm was implemented to enhance classification accuracy, aiming to develop a more robust framework for medical image analysis. The evaluation, conducted using cross-validation, demonstrated notable improvements in key metrics. Specifically, oversampling significantly enhanced lung …

Comparative Analysis Of Bpnn And Lvq For Sundanese Character Recognition, Haviluddin Haviluddin, Herman Santoso Pakpahan, Dinda Izmya Nurpadillah, Hario Jati Setyadi, Medi Taruk, Rayner Alfred

Knowledge Engineering and Data Science

The Sundanese script (Aksara Sunda), an essential part of Sundanese cultural heritage, has been used since the 14th century AD. However, recognizing handwritten Sundanese characters remains challenging due to variations in individual writing styles. This study compares the performance of Backpropagation Neural Network (BPNN) and Learning Vector Quantization (LVQ) for recognizing handwritten Sundanese vowel (Swara) characters. A dataset was collected from 15 individuals, each writing seven Sundanese vowel characters, which were then used for training and testing the recognition models. Experimental results show that BPNN outperforms LVQ, achieving a higher classification accuracy (95.23%), lower Mean Squared Error (MSE), and faster …

From A Timeline Contact Graph To Close Contact Tracing And Infection Diffusion Intervention, Yipeng Zhang, Zhifeng Bao, Yuchen Li, Baihua Zheng, Xiaoli Wang

Research Collection School Of Computing and Information Systems

This paper proposes a novel graph structure to address the problems of information spreading in a real-world, frequently updating graph, with two main contributions at hand: accurately tracing infection diffusion according to fine-grained user movements and finding vulnerable vertices under the virus immunization scenario to mitigate infection diffusion. Unlike previous work that primarily predicts the long-term epidemic trend at the census level, this study aims to intervene in the short-term at the individual level. Therefore, two downstream tasks are formulated to illustrate practicalities: Epidemic Mitigating in Public Area problem (EMA) and Epidemic Maximized Spread in Public Area problem (ESA), where …

Modeling And Regulating A Ride-Sourcing Market Integrated With Vehicle Rental Services, Dong Mo, Hai Wang, Zeen Cai, W. Y. Szeto, Xiqun (Michael) Chen

Research Collection School Of Computing and Information Systems

With the popularity of on-demand ride services worldwide, ride-sourcing platforms must maintain an adequate fleet size and cope with growing travel demand. Recently, platforms have attempted to provide vehicle rental services to drivers who do not own cars, then recruited them to provide on demand ride services. This helps lower the entry barrier for drivers and offers another profitable business for platforms. From the government's perspective, however, it is challenging to coordinately regulate a ride-sourcing business and vehicle rental business. This paper proposes a bi-level optimization model to investigate how the government regulates the ride-sourcing market integrated with vehicle rental …

Towards Unified Multimodal Editing With Enhanced Knowledge Collaboration, Kaihang Pan, Zhaoyu Fan, Juncheng Li, Qifan Yu, Hao Fei, Siliang Tang, Richang Hong, Hanwang Zhang, Qianru Sun

Research Collection School Of Computing and Information Systems

The swift advancement in Multimodal LLMs (MLLMs) also presents significant challenges for effective knowledge editing. Current methods, including intrinsic knowledge editing and external knowledge resorting, each possess strengths and weaknesses, struggling to balance the desired properties of reliability, generality, and locality when applied to MLLMs. In this paper, we propose UniKE, a novel multimodal editing method that establishes a unified perspective and paradigm for intrinsic knowledge editing and external knowledge resorting. Both types of knowledge are conceptualized as vectorized key-value memories, with the corresponding editing processes resembling the assimilation and accommodation phases of human cognition, conducted at the same semantic …

Learning De-Biased Representations For Remote-Sensing Imagery, Zichen Tian, Zhaozheng Chen, Qianru Sun

Research Collection School Of Computing and Information Systems

Remote sensing (RS) imagery, requiring specialized satellites to collect and being difficult to annotate, suffers from data scarcity and class imbalance in certain spectrums. Due to data scarcity, training any large-scale RS models from scratch is unrealistic, and the alternative is to transfer pre-trained models by fine-tuning or a more data-efficient method LoRA. Due to class imbalance, transferred models exhibit strong bias, where features of the major class dominate over those of the minor class. In this paper, we propose debLoRA---a generic training approach that works with any LoRA variants to yield debiased features. It is an unsupervised learning approach …

Reinforcement Learning Based Online Request Scheduling Framework For Workload-Adaptive Edge Deep Learning Inference, Xinrui Tan, Hongjia Li, Xiaofei Xie, Lu Guo, Nirwan Ansari, Xueqing Huang, Liming Wang, Zhen Xu, Yang Liu

Research Collection School Of Computing and Information Systems

The recent advances of deep learning in various mobile and Internet-of-Things applications, coupled with the emergence of edge computing, have led to a strong trend of performing deep learning inference on the edge servers located physically close to the end devices. This trend presents the challenge of how to meet the quality-of-service requirements of inference tasks at the resource-constrained network edge, especially under variable or even bursty inference workloads. Solutions to this challenge have not yet been reported in the related literature. In the present paper, we tackle this challenge by means of workload-adaptive inference request scheduling: in different workload …

Mvgamba : Unify 3d Content Generation As State Space Sequence Modeling, Xuanyu Yi, Zike Wu, Qiuhong Shen, Qingshan Xu, Pan Zhou, Joo-Hwee Lim, Shuicheng Yan, Xinchao Wang, Hanwang Zhang

Research Collection School Of Computing and Information Systems

Recent 3D large reconstruction models (LRMs) can generate high-quality 3D content in sub-seconds by integrating multi-view diffusion models with scalable multi-view reconstructors. Current works further leverage 3D Gaussian Splatting as 3D representation for improved visual quality and rendering efficiency. However, we observe that existing Gaussian reconstruction models often suffer from multi-view inconsistency and blurred textures. We attribute this to the compromise of multi-view information propagation in favor of adopting powerful yet computationally intensive architectures (e.g., Transformers). To address this issue, we introduce MVGamba, a general and lightweight Gaussian reconstruction model featuring a multi-view Gaussian reconstructor based on the RNN-like State …