Physical Sciences and Mathematics Commons^™

A Data Driven Approach To Forecast Demand, Hannah Kosinovsky, Sita Daggubati, Kumar Ramasundaram, Brent Allen

SMU Data Science Review

Abstract. In this paper, we present a model and methodology for accurately predicting the following quarter’s sales volume of individual products given the previous five years of sales data. Forecasting product demand for a single supplier is complicated by seasonal demand variation, business cycle impacts, and customer churn. We developed a novel prediction using machine learning methodology, based upon a Dense neural network (DNN) model that implicitly considers cyclical demand variation and explicitly considers customer churn while minimizing the least absolute error between predicted demand and actual sales. Using parts sales data for a supplier to the oil and gas …

Integrating Lidar Data And Multi-Temporal Aerial Imagery To Map Wetland Inundation Dynamics Using Google Earth Engine, Qiusheng Wu, Charles B. Lane, Xuecao Li, Kaiguang Zhao, Yuyu Zhou, Nicholas Clinton, Ben Devries, Heather E. Golden, Megan W. Lang

United States Environmental Protection Agency: Publications

The Prairie Pothole Region of North America is characterized by millions of depressional wetlands, which provide critical habitats for globally significant populations of migratory waterfowl and other wildlife species. Due to their relatively small size and shallow depth, these wetlands are highly sensitive to climate variability and anthropogenic changes, exhibiting inter- and intra-annual inundation dynamics. Moderate-resolution satellite imagery (e.g., Landsat, Sentinel) alone cannot be used to effectively delineate these small depressional wetlands. By integrating fine spatial resolution Light Detection and Ranging (LiDAR) data and multi-temporal (2009–2017) aerial images, we developed a fully automated approach to delineate wetland inundation extent at …

Resurgence Of An Apex Marine Predator And The Decline In Prey Body Size, Jan Ohlberger, Daniel E. Schindler, Eric J. Ward, Timothy E. Walsworth, Timothy E. Essington

Watershed Sciences Faculty Publications

In light of recent recoveries of marine mammal populations worldwide and heightened concern about their impacts on marine food webs and global fisheries, it has become increasingly important to understand the potential impacts of large marine mammal predators on prey populations and their life-history traits. In coastal waters of the northeast Pacific Ocean, marine mammals have increased in abundance over the past 40 to 50 y, including fish-eating killer whales that feed primarily on Chinook salmon. Chinook salmon, a species of high cultural and economic value, have exhibited marked declines in average size and age throughout most of their North …

Synthesis And Connection Of Iridium Hydrogen Evolution Catalyst To Chlorella Vulgaris Photosystem I For Light-Driven Hydrogen Evolution, Anna Ramirez

Honors Program Theses and Projects

Hydrogen gas has been shown to be a promising energy source as options other than fossil fuels are being looked at in the face of anthropogenic climate change. It is known that anthropogenic climate change is caused by the production of greenhouse gases being let into the atmosphere, specifically a common reason for this is the burning of fossil fuels for energy. The overall goal of this project is to design a biochemical hybrid system that will be used to make H 2 gas and does not require the use of fossil fuels. Burning hydrogen as fuel produces only water …

Ordinal Hyperplane Loss, Bob Vanderheyden

Doctor of Data Science and Analytics Dissertations

This research presents the development of a new framework for analyzing ordered class data, commonly called “ordinal class” data. The focus of the work is the development of classifiers (predictive models) that predict classes from available data. Ratings scales, medical classification scales, socio-economic scales, meaningful groupings of continuous data, facial emotional intensity and facial age estimation are examples of ordinal data for which data scientists may be asked to develop predictive classifiers. It is possible to treat ordinal classification like any other classification problem that has more than two classes. Specifying a model with this strategy does not fully utilize …

Information Extraction From Biomedical Text Using Machine Learning, Deepti Garg

Master's Projects

Inadequate drug experimental data and the use of unlicensed drugs may cause adverse drug reactions, especially in pediatric populations. Every year the U.S. Food and Drug Administration approves human prescription drugs for marketing. The labels associated with these drugs include information about clinical trials and drug response in pediatric population. In order for doctors to make an informed decision about the safety and effectiveness of these drugs for children, there is a need to analyze complex and often unstructured drug labels. In this work, first, an exploratory analysis of drug labels using a Natural Language Processing pipeline is performed. Second, …

Assessing Wildfire Damage From High Resolution Satellite Imagery Using Classification Algorithms, Ai-Linh Alten

Master's Projects

Wildfire damage assessments are important information for first responders, govern- ment agencies, and insurance companies to estimate the cost of damages and to help provide relief to those affected by a wildfire. With the help of Earth Observation satellite technology, determining the burn area extent of a fire can be done with traditional remote sensing methods like Normalized Burn Ratio. Using Very High Resolution satellites can help give even more accurate damage assessments but will come with some tradeoffs; these satellites can provide higher spatial and temporal resolution at the expense of better spectral resolution. As a wildfire burn area …

Analyze Informant-Based Questionnaire For The Early Diagnosis Of Senile Dementia Using Deep Learning, Fubao Zhu, Xiaonan Li, Daniel Mcgonigle, Haipeng Tang, Zhuo He, Chaoyang Zhang, Guang-Uei Hung, Pai-Yi Chu, Weihua Zhou

Faculty Publications

Objective: This paper proposes a multiclass deep learning method for the classification of dementia using an informant-based questionnaire.

Methods: A deep neural network classification model based on Keras framework is proposed in this paper. To evaluate the advantages of our proposed method, we compared the performance of our model with industry-standard machine learning approaches. We enrolled 6,701 individuals, which were randomly divided into training data sets (6030 participants) and test data sets (671 participants). We evaluated each diagnostic model in the test set using accuracy, precision, recall, and F1-Score.

Results: Compared with the seven conventional machine learning …

Two Algorithms For The Reorganisation Of The Problem List By Organ System, Daniel B. Hier, Joshua Pearson

Chemistry Faculty Research & Creative Works

Objective Long Problem Lists Can Be Challenging to Use. Reorganization of the Problem List by Organ System is a Strategy for Making Long Problem Lists More Manageable. Methods in a Small-Town Primary Care Setting, We Examined 4950 Unique Problem Lists over 5 Years (24 033 Total Problems and 2170 Unique Problems) from Our Electronic Health Record. All Problems Were Mapped to the International Classification of Diseases, 10th Revision, Clinical Modification (ICD-10-CM) and SNOMED CT Codes. We Developed Two Different Algorithms for Reorganizing the Problem List by Organ System based on Either the ICD-10-CM or the SNOMED CT Code. Results the …

Landscape Evolution Of The Southern Colorado Plateau Using Low-Temperature Apatite Thermochronology And Detrital Zircon And Sanidine Provenance Studies, Carmen L. Winn

Earth and Planetary Sciences ETDs

Chapter 1: Westernmost Grand Canyon

Conflicting hypotheses about the timing of carving of the Grand Canyon involve either a 70 Ma (“old”) or < 6 Ma (“young”) Grand Canyon. This paper evaluates the controversial westernmost segment of the Grand Canyon where the following lines of published evidence firmly favor a “young” Canyon. 1) North-derived Paleocene Hindu Fanglomerate was deposited across the present track of the westernmost Grand Canyon, which therefore was not present at ~55 Ma. 2) The 19 Ma Separation Point basalt is stranded between high relief side canyons feeding the main stem of the Colorado River and was emplaced before these tributaries and the main canyon were incised. 3) Geomorphic constraints indicate that relief generation in tributaries and on plateaus adjacent to the westernmost Grand Canyon took place after 17 Ma. 4) The late Miocene-Pliocene Muddy Creek Formation constraint shows that no river carrying far-traveled materials exited at the mouth of the Grand Canyon until after 6 Ma.

Interpretations of previously-published low-temperature thermochronologic data conflict with these lines of evidence, but are reconciled in this paper via the integration of three methods of analyses on the same sample: apatite (U-Th)/He ages (AHe), ⁴He/³He thermochronometry (⁴He/³He), and apatite fission-track ages and lengths (AFT). “HeFTy” software was used to generate time-temperature (t-T) paths that predict all new and published ⁴He/³He, AH, and AFT data to within assumed …

A Feasibility Study On The Application Of Tvdi On Accessing Wildfire Danger In The Korean Peninsula, Kwang Nyun Kim, Seung Hee Kim, Myoung Soo Won, Keun Chang Jang, Won Jun Choi, Yun Gon Lee

Mathematics, Physics, and Computer Science Faculty Articles and Research

Wildfire is a major natural disaster affecting socioeconomics and ecology. Remote sensing data have been widely used to estimate the wildfire danger with an advantage of higher spatial resolution. Among the several wildfire related indices using remote sensing data, Temperature Vegetation Dryness Index (TVDI) assesses wildfire danger based on both Normalized Difference Vegetation Index (NDVI) and Land Surface Temperature (LST). Although TVDI has physical advantages by considering both weather and vegetation condition, previous studies have shown TVDI does not performed well compare to other wildfire related indices over the Korean Peninsula. In this study we have attempted multiple modification to …

A Landscape On The Threshold Of Change: Patterns Of Soil Microbial Ecology Along Dynamic Geomorphic And Hydrologic Features In A Polar Desert, Kelli L. Feeser, David James Van Horn, Heather N. Buelow, Daniel R. Colman, Theresa A. Mchugh, Jordan G. Okie, Egbert Schwartz, Cristina D. Takacs-Vesbach, Becky A. Ball, Andrew G. Fountain, Michael N. Gooseff, Joseph S. Levy, Maciej K. Obryk

Biology ETDs

The McMurdo Dry Valleys (MDV) of Antarctica are on the threshold of widespread landscape scale change due to increasing temperature and solar radiation and altered hydrology: buried ice is melting, the soil active layer is thickening, thermokarst features are developing along streams, water tracks are expanding, and lake levels are rising. These changes will impact the microbial communities found in each of the affected habitats. The purpose of this work is to first, understand the spatial distribution of soil bacteria in the MDV, specifically investigating the scale-dependent effects of environmental heterogeneity, and second, to perform surveys and coupled experiments to …

Flood Dynamics In The Portland Metropolitan Area, Past, Present, And Future, Lumas Terence Helaire

Dissertations and Theses

The Portland area has an extensive flood history since it was founded in 1845. In the late 19th century, the Portland area was prone to flooding from snowmelt freshets (3-6 months duration) and brief winter rain or rain-on-snow events. Since that time the magnitude of spring freshets has been curtailed by 45% due to climate change, flow diversions, and reservoir management. Along with changes in hydrology, the bathymetry of the Lower Columbia River has been altered by the dredging of the navigation channel, diking, and land reclamation. To understand how these changes in hydrology and bathymetry have affected tidal and …

Rearrangement Operations On Unrooted Phylogenetic Networks, Remie Janssen, Jonathan Klawitter

Theory & Applications of Graphs

Rearrangement operations transform a phylogenetic tree into another one and hence induce a metric on the space of phylogenetic trees. Popular operations for unrooted phylogenetic trees are NNI (nearest neighbour interchange), SPR (subtree prune and regraft), and TBR (tree bisection and reconnection). Recently, these operations have been extended to unrooted phylogenetic networks, which are generalisations of phylogenetic trees that can model reticulated evolutionary relationships. Here, we study global and local properties of spaces of phylogenetic networks under these three operations. In particular, we prove connectedness and asymptotic bounds on the diameters of spaces of different classes of phylogenetic networks, including …

On The Frontlines - The Fishermen Of Ibrahim Hyderi, Muhammad Haris Aslam Khan

MSJ Capstone Projects

Climate change has become a matter of recent debate for much of the world. According to a report published by a German watch, a non-governmental organization, in 2019, Pakistan among the five countries at severe risk of climate change disasters.

During the last two decades, Pakistan saw more than 141 extreme climatic catastrophes. Only in 2016, more than 566 people died due to these conditions.

A report published by Asian Development Bank in 2017 indicates Pakistan’s climate change profile. It states that more than 1,600 people have lost their lives in the super flood of 2010 alone. A loss of …

Resolving Time-Space Histories Of Late Cenozoic Bedrock Incision Along The Upper Colorado River, Usa, Andres Aslan, Karl E. Karlstrom, Eric Kirby, Matthew T. Heizler, Darryl E. Granger, James K. Feathers, Paul R. Hanson, Shannon A. Mahan

School of Natural Resources: Faculty Publications

The upper Colorado River basin drains the western slope of the Rocky Mountains province of North America and hosts a rich record of fluvial terraces and volcanic deposits that provide an archive of bedrock river incision since the Late Miocene. Here we present new geochronology from fluvial deposits and associated volcanic units using multiple methods (luminescence, cosmogenic-burial, 40Ar/39Ar basalt and detrital sanidine, and U/Pb detrital zircon) to reconstruct a detailed record of bedrock incision in the upper Colorado River over timescales ranging from Miocene to Late Pleistocene. Late Miocene (ca. 11–8 Ma) basalt flows perched 800–1700 m above the Colorado …

Beavers Alter Stream Macroinvertebrate Communities In Northeastern Utah, Susan E. Washko, Brett B. Roper, Trisha Brooke Atwood

Watershed Sciences Faculty Publications

1. Understanding changes in macroinvertebrate communities is important because they play a large role in stream ecosystem functioning, and they are an important food resource for fish. Beaver‐induced changes to stream morphology could alter macroinvertebrate communities, which in turn could affect food webs and ecosystem function. However, studies investigating the effects of North American beaver activities on macroinvertebrates are rare in the inter‐mountain west, an area with high potential for beaver‐assisted restoration.
2. The aim of this study was to quantify differences in the macroinvertebrate community between unaltered segments of streams and within beaver ponds in north‐eastern Utah, U.S.A. We assessed macroinvertebrate …

Constructing Invariant Subspaces As Kernels Of Commuting Matrices, Carl C. Cowen, William Johnston, Rebecca G. Wahl

Scholarship and Professional Work - LAS

Given an n n matrix A over C and an invariant subspace N, a straightforward formula constructs an n n matrix N that commutes with A and has N = kerN. For Q a matrix putting A into Jordan canonical form, J = Q􀀀1AQ, we get N = Q􀀀1M where M= ker(M) is an invariant subspace for J with M commuting with J. In the formula J = PZT􀀀1Pt, the matrices Z and T are m m and P is an n m row selection matrix. If N is a marked subspace, m = n and Z is an n …

Respons Pertumbuhan Tanaman Kelapa Belum Menghasilkan Terhadap Pemberian Air Kelapa Dan Asam Humat, Mira Ariyanti, Santi Rosniawaty, Muhamad Rizky Permana

Jurnal Kultivasi

Kelapa kopyor banyak diminati masyarakat karena memiliki sifat yang unik. namun produktivitas kelapa kopyor masih rendah. Peningkatan pertumbuhan kelapa kopyor belum menghasilkan dapat dilakukan dengan aplikasi zat pengatur tumbuh alami (ZPT) seperti air kelapa yang diaplikasikan langsung pada tanaman dan asam humat sebagai bahan organik untuk meningkatkan kualitas tanah agar dapat sesuai bagi pertanaman kelapa kopyor. Penelitian ini bertujuan untuk mengetahui pengaruh kombinasi aplikasi air kelapa dan asam humat terbaik terhadap pertumbuhan tanaman kelapa kopyor belum menghasilkan. Penelitian dilaksanakan di Lahan Taman Buah Mekarsari, Cileungsi, Bogor, Jawa Barat, pada bulan Mei 2018-Oktober 2018. Penelitian ini menggunakan tanah berordo Ultisols. Metode …

Mojave Desert Ecosystem Recovery: Potency Of Biotic And Abiotic Restoration Methods In Low Elevation Plant Communities, Mary Amanda Balogh

UNLV Theses, Dissertations, Professional Papers, and Capstones

The historic and current state of land in the Mojave Desert, including land managed by the National Park Service with fundamental goals of natural resource conservation and preservation, been severely degraded by a variety of anthropogenic disturbances. Due to increasingly sporadic and unpredictable precipitation patterns, land managers struggle to implement restoration projects with high success rates and are resource-limited for post-treatment monitoring. In this study, I examined success rates of biotic (outplanting, seeding) and abiotic (soil manipulation, vertical mulch) restoration treatments on various disturbance types in the creosote-bursage (Larrea tridentata-Ambrosia dumosa), blackbrush (Coleogyne ramosissima), and Joshua tree woodland (Yucca brevifolia) …

Sideromycin Pathway Elucidation: Insights Into Salmycin Biosynthesis, Transport Paradigms, And Drug Release, Gerry Sann Macaraeg Rivera

Arts & Sciences Graduate Student Theses and Dissertations

Antibiotic resistance is an increasing threat in today’s society. In order to overcome resistant bacteria, it is necessary to discover new drugs with novel mechanisms of action. This work focuses on the sideromycin pathway, encompassing the biosynthetic production, mechanism of entry and hydrolysis-mediated drug release. Sideromycins are an interesting approach to combat the rise of antibiotic resistance since they provide a different avenue that overcomes problems that arise when entering the cell. The dissertation is separated into distinct sections dealing with the various areas of interest in the sideromycin pathway, particularly for the sideromycin, salmycin, produced by Streptomyces violaceus. The …

Cyclotron Resonance In Graphene Heterostructurescyclotron Resonance In Graphene Heterostructures, Billy Jordan Russell

Arts & Sciences Graduate Student Theses and Dissertations

We present observations of cyclotron resonance in graphene Van der Waals heterostructure devices. Such devices provide dramatic improvements in sample quality and allow for ad- vanced electronic control, opening windows on previously inaccessible physics. The design and construction of a dedicated system for the measurement of electronic transport and infrared magnetospectroscopy in microscopic samples of atomically thin materials at cryogenic temperatures is presented. In high-mobility encapsulated monolayer graphene, electron- electron interaction effects are unambiguously observed to impact the interband cyclotron resonance as the Landau level filling factor is varied in a quantizing magnetic field. Additionally, a splitting of transitions involving …

Landscape Scale: Inter- And Intraspecific Variation In Plant Interactions Along A Stress Gradient In The Sheep Range Of Nevada, Jordan Dowell

UNLV Theses, Dissertations, Professional Papers, and Capstones

Impending threats to shrubland ecosystems, posed by climate change, necessitate niche modeling efforts to project vegetation range shifts. However, efforts often remain unguided by individual-scale interspecific plant interactions. The stress gradient hypothesis posits that facilitation should increase in areas of high abiotic stress, only if the individuals are able to ameliorate the surrounding area via functional traits. The Sheep Range of Nevada was used to assess the role of functional traits as predictors of plant association. Larrea tridentata, Coleogyne ramosissima, and Artemisia nova were selected as shrubs with variable life history strategies and ranges in order to identify general patterns …

Finding A Viable Neural Network Architecture For Use With Upper Limb Prosthetics, Maxwell Lavin

Master of Science in Computer Science Theses

This paper attempts to answer the question of if it’s possible to produce a simple, quick, and accurate neural network for the use in upper-limb prosthetics. Through the implementation of convolutional and artificial neural networks and feature extraction on electromyographic data different possible architectures are examined with regards to processing time, complexity, and accuracy. It is found that the most accurate architecture is a multi-entry categorical cross entropy convolutional neural network with 100% accuracy. The issue is that it is also the slowest method requiring 9 minutes to run. The next best method found was a single-entry binary cross entropy …

Development Of High-Speed Photoacoustic Imaging Technology And Its Applications In Biomedical Research, Yun He

McKelvey School of Engineering Graduate Student Theses & Dissertations

Photoacoustic (PA) tomography (PAT) is a novel imaging modality that combines the fine lateral resolution from optical imaging and the deep penetration from ultrasonic imaging, and provides rich optical-absorption–based images. PAT has been widely used in extracting structural and functional information from both ex vivo tissue samples to in vivo animals and humans with different length scales by imaging various endogenous and exogenous contrasts at the ultraviolet to infrared spectrum. For example, hemoglobin in red blood cells is of particular interest in PAT since it is one of the dominant absorbers in tissue at the visible wavelength.The main focus of …

Towards Interpretable Machine Learning With Applications To Clinical Decision Support, Zhicheng Cui

McKelvey School of Engineering Graduate Student Theses & Dissertations

Machine learning models have achieved impressive predictive performance in various applications such as image classification and object recognition. However, understanding how machine learning models make decisions is essential when deploying those models in critical areas such as clinical prediction and market analysis, where prediction accuracy is not the only concern. For example, in the clinical prediction of ICU transfers, in addition to accurate predictions, doctors need to know the contributing factors that triggered the alert, which factors can be quickly altered to prevent the ICU transfer. While interpretable machine learning has been extensively studied for years, challenges remain as among …

Graph Deep Learning: Methods And Applications, Muhan Zhang

McKelvey School of Engineering Graduate Student Theses & Dissertations

The past few years have seen the growing prevalence of deep neural networks on various application domains including image processing, computer vision, speech recognition, machine translation, self-driving cars, game playing, social networks, bioinformatics, and healthcare etc. Due to the broad applications and strong performance, deep learning, a subfield of machine learning and artificial intelligence, is changing everyone's life.Graph learning has been another hot field among the machine learning and data mining communities, which learns knowledge from graph-structured data. Examples of graph learning range from social network analysis such as community detection and link prediction, to relational machine learning such as …

The Role Of Multi-Charged Responses: Construction And Application Of A Tandem Differential Mobility Analyzer (Tdma), Christopher Ray Oxford

McKelvey School of Engineering Graduate Student Theses & Dissertations

Atmospheric aerosols impact health outcomes, visibility, and the energy balance of the earth. The atmosphere contains a variety of compounds, and the volatility (phase change enthalpy and vapor pressure) of each compound determines its partitioning between the gas phase and the particle phase. The hygroscopicity (an aerosol’s affinity for water) of an atmospheric aerosol particle is determined by the many compounds present in the particle, and thus, the volatility impacts hygroscopicity. Changes in hygroscopicity alter the fraction of the aerosol deposited in the lungs and the fraction of the aerosol activated into cloud droplets. Thus, understanding the volatility and hygroscopicity …

Contemporary Problems In Aerosol Aggregation And Gelation, Pai Liu

McKelvey School of Engineering Graduate Student Theses & Dissertations

Aggregation of nanoparticles in aerosols is a fundamental phenomenon with important implications to diverse fields ranging from material synthesis to pollutant control. The past few decades have witnessed extensive research on investigating the structure and growth mechanism of aerosol aggregates with sizes spanning across several orders of magnitude. This dissertation focuses on some contemporary problems that remain unaddressed in this topical area. Aerosol aggregates in sub-micron regimes, which are formed via the irreversible collision and aggregation of solid nanoparticle monomers, are fractal-like in their morphology. A mathematical description of this seemingly random structure dates to the seminal works by Forest …

Development And Application Of Mass Spectrometry-Based Protein Footprinting In Structural Proteomics, Ming Cheng

Arts & Sciences Graduate Student Theses and Dissertations

Integral mass spectrometry (MS) has emerged as an important tool for protein structural characterization. It readouts are a broad range of structural information, including stoichiometry, interactions, conformations and conformation change, and dynamics. Protein footprinting is a pivotal component in the intergral MS toolkit.My dissertation centers around the development and application of protein footprinting to characterize protein structure. It is divided into seven chapters.Chapter 1 serves as the introduction for integral mass spectrometry in structural proteomic.In Chapter 2, we extended the fast-photochemical oxidation of proteins (FPOP) platform by adding the trifluoromethyl radical (•CF3) as a new reagent. We discovered that •CF3 …