Physical Sciences and Mathematics Commons^™

Training Uav Teams With Multi-Agent Reinforcement Learning Towards Fully 3d Autonomous Wildfire Response, Bryce Hopkins

All Theses

As climate-exacerbated wildfires increasingly threaten landscapes and communities, there is an urgent and pressing need for sophisticated fire management technologies. Coordinated teams of Unmanned Aerial Vehicles (UAVs) present a promising solution for detection, assessment, and even incipient-stage suppression – especially when integrated into a multi-layered approach with other recent wildfire management technologies such as geostationary/polar-orbiting satellites and CCTV detection networks. However, there remains significant challenges in developing the necessary sensing, navigation, coordination, and communication subsystems that enable intelligent UAV teams. Further, federal regulations governing UAV deployment and autonomy pose constraints on real-world aerial testing, creating a disconnect between theoretical research …

Nonfactoid Question Answering As Query-Focused Summarization With Graph-Enhanced Multihop Inference, Yang Deng, Wenxuan Zhang, Weiwen Xu, Ying Shen, Wai Lam

Research Collection School Of Computing and Information Systems

Nonfactoid question answering (QA) is one of the most extensive yet challenging applications and research areas in natural language processing (NLP). Existing methods fall short of handling the long-distance and complex semantic relations between the question and the document sentences. In this work, we propose a novel query-focused summarization method, namely a graph-enhanced multihop query-focused summarizer (GMQS), to tackle the nonfactoid QA problem. Specifically, we leverage graph-enhanced reasoning techniques to elaborate the multihop inference process in nonfactoid QA. Three types of graphs with different semantic relations, namely semantic relevance, topical coherence, and coreference linking, are constructed for explicitly capturing the …

Causvsr: Causality Inspired Visual Sentiment Recognition, Xinyue Zhang, Zhaoxia Wang, Hailing Wang, Jing Xiang, Chunwei Wu, Guitao Cao

Research Collection School Of Computing and Information Systems

Visual Sentiment Recognition (VSR) is an evolving field that aims to detect emotional tendencieswithin visual content. Despite its growing significance, detecting emotions depicted in visual content,such as images, faces challenges, notably the emergence of misleading or spurious correlationsof the contextual information. In response to these challenges, we propose a causality inspired VSRapproach, called CausVSR. CausVSR is rooted in the fundamental principles of Emotional Causalitytheory, mimicking the human process from receiving emotional stimuli to deriving emotional states.CausVSR takes a deliberate stride toward conquering the VSR challenges. It harnesses the power of astructural causal model, intricately designed to encapsulate the dynamic causal …

Clamber: A Benchmark Of Identifying And Clarifying Ambiguous Information Needs In Large Language Models, Tong Zhang, Peixin Qin, Yang Deng, Chen Huang, Wenqiang Lei, Junhong Liu, Dingnan Jin, Hongru Liang, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Large language models (LLMs) are increasingly used to meet user information needs, but their effectiveness in dealing with user queries that contain various types of ambiguity remains unknown, ultimately risking user trust and satisfaction. To this end, we introduce CLAMBER, a benchmark for evaluating LLMs using a well-organized taxonomy. Building upon the taxonomy, we construct 12K high-quality data to assess the strengths, weaknesses, and potential risks of various off-the-shelf LLMs.Our findings indicate the limited practical utility of current LLMs in identifying and clarifying ambiguous user queries, even enhanced by chain-of-thought (CoT) and few-shot prompting. These techniques may result in overconfidence …

Di­Chlorido­Tetra­Kis­(3-Meth­­Oxy­Aniline)Nickel(Ii), Benjamin A. Mukda, Mark M. Turnbull

Chemistry

The reaction of nickel(II) chloride with 3-meth­oxy­aniline yielded di­chlorido­tetra­kis­(3-meth­oxy­aniline)nickel(II), [NiCl₂(C₇H₉NO)₄], as yellow crystals. The Ni^II ion is pseudo-octa­hedral with the chloride ions trans to each other. The four 3-meth­oxy­aniline ligands differ primarily due to different conformations about the Ni—N bond, which also affect the hydrogen bonding. Inter­molecular N—H⋯ Cl hydrogen bonds and short Cl⋯Cl contacts between mol­ecules link them into chains parallel to the b axis.

Neural Network Semantic Backdoor Detection And Mitigation: A Causality-Based Approach, Bing Sun, Jun Sun, Wayne Koh, Jie Shi

Research Collection School Of Computing and Information Systems

Different from ordinary backdoors in neural networks which are introduced with artificial triggers (e.g., certain specific patch) and/or by tampering the samples, semantic backdoors are introduced by simply manipulating the semantic, e.g., by labeling green cars as frogs in the training set. By focusing on samples with rare semantic features (such as green cars), the accuracy of the model is often minimally affected. Since the attacker is not required to modify the input sample during training nor inference time, semantic backdoors are challenging to detect and remove. Existing backdoor detection and mitigation techniques are shown to be ineffective with respect …

Prompt Tuning On Graph-Augmented Low-Resource Text Classification, Zhihao Wen, Yuan Fang

Research Collection School Of Computing and Information Systems

Text classification is a fundamental problem in information retrieval with many real-world applications, such as predicting the topics of online articles and the categories of e-commerce product descriptions. However, low-resource text classification, with no or few labeled samples, presents a serious concern for supervised learning. Meanwhile, many text data are inherently grounded on a network structure, such as a hyperlink/citation network for online articles, and a user-item purchase network for e-commerce products. These graph structures capture rich semantic relationships, which can potentially augment low-resource text classification. In this paper, we propose a novel model called Graph-Grounded Pre-training and Prompting (G2P2) …

Beyond Automation: Ai As A Catalyst For New Job Creation In Software Development, Jill Willard, James Hutson

Faculty Scholarship

As artificial intelligence (AI) continues to evolve, its impact on software development and programming is profound, drawing parallels to the shift from assembler to object-oriented programming. This article explores how AI is reshaping the landscape of software jobs, creating new opportunities rather than diminishing them. By simplifying complex tasks and lowering barriers to coding, AI is expanding the technology "pie," introducing new use cases, and enhancing efficiency. The transition from monolithic services to microservices has reduced risks and accelerated deployment processes, and AI is poised to further this evolution by managing the complexities of service interactions through advanced orchestration layers. …

Palynostratigraphy And Bayesian Age Stratigraphic Model Of New Ca-Id-Tims Zircon Ages From The Walloon Coal Measures, Surat Basin, Australia, K. Sobczak, J. Cooling, T. Crossingham, H. G. Holl, M. Reilly, J. Esterle, J. L. Crowley, C. Hannaford, M. T. Mohr, Z. Hamerli, S. Hurter

Geosciences Faculty Publications and Presentations

The Surat Basin hosts significant coal and coal seam gas resources. New high-precision CA-TIMS U/Pb zircon ages from tuffs and Bayesian age stratigraphic models are combined with palynology from fine-grained sedimentary rocks and zircon trace elements to provide further chronostratigraphic and biostratigraphic constrains on the Walloon Coal Measures in the eastern margin of the Surat Basin and infer the palaeoenvironment and tectonic setting. The tuff ages range from 165.88 ± 0.11 Ma to 158.84 ± 0.05 Ma, with those from the stratigraphically lower Taroom Coal Measures ranging from 165.88 ± 0.11 to 163.05 ± 0.08 Ma and Juandah Coal Measures …

Accretion Of Warm Chondrules In Weakly Metamorphosed Ordinary Chondrites And Their Subsequent Reprocessing, Alex M. Ruzicka, Richard C. Hugo, Jon M. Friedrich, Michael T. Ream

Geology Faculty Publications and Presentations

To better understand chondrite accretion and subsequent processes, the textures, crystallography, deformation, and compositions of some chondrite constituents in ten lithologies of different cluster texture strength were studied in seven weakly metamorphosed (Type 3) and variably shocked ordinary chondrites (Ragland—LL3 S1, Tieschitz—H/L3 S1, NWA 5421—LL3 S2, NWA 5205—LL3 S2, NWA 11905—LL3-5 S3, NWA 5781—LL3 S3, NWA 11351—LL3-6 S4) using optical and electron microscopy and microtomography techniques.

Results support a four-stage model for chondrite formation. This includes 1) limited annealing following collisions during chondrule crystallization and rapid cooling in space prior to accretion, as evidenced by olivine microstructures consistent with dislocation …

A Comprehensive And Interactive Visualization Tool To Support Equitable Adoption Of Electrified Transportation, Aashay Maheshwarkar

All Graduate Theses and Dissertations, Fall 2023 to Present

As urban areas continue to grow, the deployment of electric vehicle (EV) charging infrastructure becomes crucial for sustainable development. This study is focused on the development of a data visualization tool that integrates diverse datasets, including traffic patterns, Points of Interest (POI), pollution levels, and socioeconomic indicators, to analyze the current state and potential expansion of EV charging stations. Our visualization tool highlights the significant impact of EV infrastructure on reducing urban pollution and improving socioeconomic outcomes. Areas with a higher density of charging stations show significantly lower levels of unemployment and pollution, emphasizing the dual benefits of EV adoption. …

Optimization Of Learning Algorithms In Neuromorphic Computing Systems., Oyinpere S. Ameli

Masters Theses

Spiking Neural Networks (SNNs) are a type of artificial neural network that aim to more closely mimic the data processing processes observed in biological neural systems. However, one major challenge in training these networks has been their non-differentiable nature, which makes it difficult to apply traditional gradient-based learning techniques. Different approaches have been proposed to address this challenge, ranging from supervised learning - largely inspired by error backpropagation in Deep Neural Networks - to unsupervised learning, which closely emulates biological learning approaches such as spike-timing dependent plasticity (STDP). Neuromorphic hardware platforms such as Intel's Loihi offer programmable plasticity that allows …

Spontaneous Plant Colonization Of Newly Established Green Roofs: An Experimental Approach, Braden Matthew Coats

Masters Theses

Urban Heat Island Effect (UHI) increases heat risks in densely developed environments. Ecosystem services provided by green spaces are known to mitigate UHI. Green roofs, designed as novel ecosystems, transform less-utilized spaces like rooftops into functional areas, executing ecosystem functions in densely populated urban environments where traditional green spaces are less common. Research has examined ways to reduce the obstacles of implementing green roofs to maximize accessibility and efficiency of the performed ecosystem services. Research involving plant community dynamics found that maximizing biodiversity on green roofs enhances the ecosystem services provided. Utilizing spontaneous colonizing species, or species that are not …

Assessment Of Enzyme Stability In Subsurface Sediments By Computational Methods, Kambiz Kalhor

Masters Theses

The microorganisms found in marine subseafloor sediment play a vital role in global carbon and nitrogen cycles, with an estimated 2.9×10²⁹ cells, accounting for about 0.6% of Earth’s total living biomass. These microbes grow at a very slow rate, with carbon turnover occurring over the course of years to thousands of years, about six orders of magnitude slower than sulfate reducing bacteria in pure culture. These slow metabolic rates suggest that the enzymes they produce must also have extended lifespans in order to be effective over such long periods of time. As a result, these enzymes are likely to …

2d Temperature Map Acquisition Using Hyperspectral Imaging System (Hsis), Anthony Kim

Masters Theses

Imaging techniques are close to our lives and are used for various applications. In the engineering field, one of the dominant techniques is hyperspectral imaging. It is a necessary tool that combines spectroscopy and digital photography and provides additional information on what is imaged by the imaging system. Hyperspectral imaging has been applied to various fields including remote sensing, cultural relic conservation, food microbiology, forensic science, biomedicine, etc.

In particular, work was done to apply hyperspectral imaging to measure the temperature and emissivity of an object. Due to its ability to measure temperature and emissivity without being in contact with …

Transfer Learning For Predictive Maintenance: A Case Study, Colter A. Swanson

Masters Theses

In light of recent strides in high-performance computing, the concept of transfer learning has emerged as a prominent paradigm within the realm of Artificial Intelligence and Machine Learning methodologies. Analogous to the human brain's capacity to assimilate information across related domains for pattern recognition, transfer learning has swiftly asserted its dominance, particularly in deep learning applications such as image classification and natural language processing. Despite its ascendancy in these domains, there exists a lack of comprehensive investigations in alternative domains, notably those encompassing tabular data formats. This thesis seeks to redress this gap by conducting an empirical examination of transfer …

Phthalocyanine-Enabled Technologies For Water Treatment And Disinfection Strategies, Hooralain Bushnaq, Catherine Munro, Sisi Pu, Amir Razmjou, Masoumeh Zargar, Giovanni Palmisano, Srinivas Mettu, Ludovic F. Dumée

Research outputs 2022 to 2026

Water treatment and disinfection are critical factors in ensuring a safe and sustainable water supply. Phthalocyanines (Pcs), a class of versatile and robust organic compounds, have garnered significant attention for their application in various water treatment processes. This review paper offers a groundbreaking investigation of Pc-enabled technologies within the domain of water treatment applications. The core aim of this review is to meticulously analyze the chemical and optical properties of Pcs, elucidate their photosensitization mechanism and establish the crucial connection between their chemical structure and photodynamic efficacy. The various modes of Pcs application in water treatment processes - whether in …

The Geometry Of Ancient Solutions To Curvature Flows, Sathyanarayanan Rengaswami

Doctoral Dissertations

Following the tremendous success of the mean curvature flow, other variants such as the Gauss curvature flow, inverse mean curvature flow have been investigated in great detail, leading to interesting applications to other fields including partial differential equations, convex geometry etc. This calls for an investigation of curvature flow as a general phenomenon. While basic existence and uniqueness results, roundness estimates etc have been obtained, there isn't a substantial body of work that addresses the geometry of solutions of curvature flows and their relation to the choice of speed function used. It is therefore interesting to investigate curvature flows as …

Mathematical Modeling And Numerical Approximations Of Combustion Instability Frequencies And Growth Rates, Harvey B. Ring Iii

Doctoral Dissertations

This dissertation presents a mathematical model and numerical simulations to determine the resonant frequencies and their associated growth rates for longitudinal modes in a combustion system similar to that found in a rocket engine. The mathematical model, which is applicable to a two-duct system with a thin flame between the two ducts, each of which having constant area and properties, considers the case of axial mean velocity and uses a vibrating wall at the inlet to select the frequency so that all modes may be found. The model is applied to the acoustics equations describing pressure and velocity fluctuations, derived …

Hierarchical Neural Constructive Solver For Real-World Tsp Scenarios, Yong Liang Goh, Zhiguang Cao, Yining Ma, Yanfei Dong, Mohammed Haroon Dupty, Wee Sun Lee

Research Collection School Of Computing and Information Systems

Existing neural constructive solvers for routing problems have predominantly employed transformer architectures, conceptualizing the route construction as a set-to-sequence learning task. However, their efficacy has primarily been demonstrated on entirely random problem instances that inadequately capture real-world scenarios. In this paper, we introduce realistic Traveling Salesman Problem (TSP) scenarios relevant to industrial settings and derive the following insights: (1) The optimal next node (or city) to visit often lies within proximity to the current node, suggesting the potential benefits of biasing choices based on current locations. (2) Effectively solving the TSP requires robust tracking of unvisited nodes and warrants succinct …

Cross-Problem Learning For Solving Vehicle Routing Problems, Zhuoyi Lin, Yaoxin Wu, Bangjian Zhou, Zhiguang Cao, Wen Song, Yingqian Zhang, Senthilnath Jayavelu

Research Collection School Of Computing and Information Systems

Existing neural heuristics often train a deep architecture from scratch for each specific vehicle routing problem (VRP), ignoring the transferable knowledge across different VRP variants. This paper proposes the cross-problem learning to assist heuristics training for different downstream VRP variants. Particularly, we modularize neural architectures for complex VRPs into 1) the backbone Transformer for tackling the travelling salesman problem (TSP), and 2) the additional lightweight modules for processing problem-specific features in complex VRPs. Accordingly, we propose to pre-train the backbone Transformer for TSP, and then apply it in the process of fine-tuning the Transformer models for each target VRP variant. …

Upscaling Relative Permeability And Capillary Pressure From Digital Core Analysis In Otway Formation: Considering The Order And Size Effects Of Facies, Masoud Aslannezhad, Mohammad Sayyafzadeh, David Tang, Zhenjiang You, Stefan Iglauer, Alireza Keshavarz

Research outputs 2022 to 2026

Digital Core Analysis (DCA) has emerged as a crucial instrument in reservoir characterization in recent times. With the advent of high-resolution micro-CT imaging, it is now possible to visualize the three-dimensional microstructures of in-situ pores and flow patterns within rocks. DCA offers several notable benefits over traditional techniques, such as a higher density of measurements, faster processing times, and the preservation of rock samples. It also demonstrates considerable flexibility with challenging core conditions and can derive numerous parameters from each individual sample. The objective of this work is to utilise DCA data from Otway formation to enhance reservoir characterisation and …

Creating A Virtual Hierarchy From A Relational Database, Yucong Mo

All Graduate Theses and Dissertations, Fall 2023 to Present

In data management and modeling, the value of the hierarchical model is that it does not require expensive JOIN operations at runtime; once the hierarchy is built, the relationships among data are embedded in the tree-like hierarchical structure, and thus querying data could be much faster than using a relational database. Today most data is stored in relational databases, but if the data were stored in hierarchies, what would these hierarchies look like? And more importantly, would this transition lead to a more efficient database? This thesis explores these questions by introducing a set of algorithms to convert a relational …

Shedding Light On Past Ice-Free Intervals In Northwest Greenland: Luminescence Dating Of The Base Of The Camp Century Ice Core, Hawke Woznick

All Graduate Theses and Dissertations, Fall 2023 to Present

The goal of this thesis is to provide greater resolution on the age and character of the subglacial sediment recovered from the base of the Camp Century ice core, northwestern Greenland. Geochemical analysis indicated that the upper sub-ice sediments were geochemically different and experienced greater weathering than the basal unit underlying a one-meter silty ice lens. Analysis of feldspars within the very fine sand fraction indicates they are dominated by potassium feldspar. Sediment was dated using luminescence, which provides an age for the last time sediment was exposed to light. Luminescence analysis returned ages around 420 thousand years old, which …

Evaluation Of Electrochemical Corrosion, Electrodeposition, And Other Electroanalytical Methods As Investigative Forensic Techniques For Advancing Metal Substrate Analysis, Crystal C. Kitanovski

UNLV Theses, Dissertations, Professional Papers, and Capstones

Friction ridge skin, bearing unique patterns of epidermal ridges commonly known as fingerprints, has served as a crucial tool for identification since ancient times, with its utilization dating back to Chinese culture around 221 B.C. Today, friction ridge skin impressions remain vital evidence in forensic investigations, aiding in the identification of suspects. While fingerprints, palm prints, and footprints can all serve as identifying markers, this dissertation focuses specifically on fingerprints, broadly classified as visible or latent. Latent fingerprints, though invisible to the naked eye, constitute the majority of prints collected from crime scenes, necessitating physical, chemical, or physicochemical processing for …

An Analysis Of The Propagation Of Gravitational Radiation Under A Graviton Of Nonzero Mass And Its Implications For Cosmological Measurements, Margaret Johnston

UNLV Theses, Dissertations, Professional Papers, and Capstones

Under the assumptions of General Relativity (GR), gravitational waves propagate at the speed of light and their mediation can be represented as a particle through a massless graviton. We investigate the impact and observability of the presence of a massive graviton, how such a modification to GR would also modify the observed gravitational waves from astrophysical sources, and how this effect can be used as an independent measurement of cosmmological parameters, including the Hubble parameter H0. We simulate the impact of a massive graviton on compact binary coalescence observation in a near-future LIGO-Virgo-KAGRA interferometer network through a modification to the …

New Insights Into The Diverse Intraplate Volcanism Present Within The Howland And Baker Island United States Exclusive Economic Zone, Nicholas Foresta

UNLV Theses, Dissertations, Professional Papers, and Capstones

The origin of oceanic volcanism has been attributed to various mechanisms, such as upwelling mantle plumes, lithospheric extension driven decompression melting, and small-scale convective cells in the asthenosphere. Discovering the range of magmatic drivers present in the ocean basins aids in understanding mantle geodynamics and tectonic processes. A recent seafloor exploration campaign within the Howland and Baker Island (HBI) U.S. Exclusive Economic Zone (EEZ; approximately near the equator and the International Date Line) resulted in the collection of multiple lava flow samples, which offer valuable insights into the complex origins and dynamics of intraplate seamounts. According to current absolute plate …

Application Of Machine Learning Algorithms In Healthcare, Dwaipayan Mukhopadhyay

UNLV Theses, Dissertations, Professional Papers, and Capstones

Machine Learning (ML) is a subset of artificial intelligence that has made substantial strides in predicting and identifying health emergencies, disease populations, and disease state and immune response, amongst a few fields of healthcare. Here we provide a brief overview of machine learning-based approaches and learning algorithms. Second, we discuss a general procedure of ML and review some studies presented in ML application for several healthcare fields. We also briefly discuss the risks and challenges of ML application to healthcare.This dissertation also consists of four different cases in healthcare where we have applied ML techniques on real life data sets. …

Effects Of Climate Change On (Semi)-Arid Ecosystems In The Southwestern United States, Charlotte Van Der Nagel

UNLV Theses, Dissertations, Professional Papers, and Capstones

Climate change is considered amongst the most severe threats to terrestrial and aquatic ecosystems globally. Ecosystems in the southwestern United States have specifically been impacted by intense drought conditions since 2000. Higher temperatures combined with altered precipitation stresses many ecosystems; however, ecosystem specific responses to such stressors may vary. Here, the effects of climate change on semi-arid ecosystems are analyzed for some of the most vulnerable ecosystems in the southwestern United States: lacustrine, riparian, and dryland ecosystems.

Lakes and reservoirs in arid environments often serve as drinking water sources and recreational areas where high water quality is essential. Climate change …

Characterizing Gsk3Β Interaction And Kinetics Via Isothermal Titration Calorimetry, W A Bhagya De Silva

UNLV Theses, Dissertations, Professional Papers, and Capstones

Glycogen synthase kinase 3β (GSK3β) is a multifunctional serine/threonine kinase involved in several key signaling pathways, including glycogen metabolism, WNT/β-catenin, and Hedgehog signaling. Hyperactivity of GSK3β has been linked to Alzheimer’s disease, bipolar disorder, type II diabetes, and some cancers. Therefore, GSK3β is of interest as a target for therapeutics. Lithium ion (Li+) is a classical inhibitor of GSK3β. Structurally similar beryllium ion (Be2+) is ~1000-fold more potent. Lithium and beryllium have demonstrated pathway-specific and cell type-specific inhibition of GSK3β, prompting an investigation into the inhibitory mechanisms and thermodynamic characteristics of the metal-enzyme interaction.Isothermal titration calorimetry (ITC) is a label-free …