Physical Sciences and Mathematics Commons^™

A Machine Learning Approach To Forecasting Sep Intensity And Times Based On Cme And Other Solar Activities, Peter John Thomas

Theses and Dissertations

High intensity Solar Energetic Particle (SEP) events pose severe risks for astronauts and critical infrastructure. The ability to accurately forecast the peak intensity and times of these events would enable preparatory measures to mitigate much of this risk. Machine learning approaches have the potential to use characteristics of CMEs and other space weather phenomena to predict SEP intensities and times. However, the severe sparsity of SEP events in current datasets poses a problem to traditional machine learning techniques. In this work, we present a dataset of proton event intensities and times, as well as features for corresponding CMEs and space …

Analyzing The Impact Of Governance Strategies On Trust And Risk In The Salish Sea Transboundary Fishery Context, Evelyn Roozee

Theses and Dissertations

The Salish Sea is the site of a transboundary fishery whose coastal jurisdiction includes British Columbia, Washington State, the two federal governments, and many Indigenous tribes with sovereign rights. Fishery management becomes increasingly complex when transboundary cooperation is needed. Furthermore, while the Salish Sea region has attempted to facilitate better transboundary collaborative governance, these have generally failed to institutionalize the principles of adaptive management. This research seeks to assess current trust and risk perceptions and analyze the effects of control mechanisms used in the transboundary fishery management network. The data consists of a survey measuring collaborative precursors, barriers, and outcomes …

Traffic Behavior Recognition From Traffic Videos Under Occlusion Condition: A Kalman Filter Approach, Junfeng Jiao, Huihai Wang

Research Collection College of Integrative Studies

Real-time traffic data at intersections is significant for development of adaptive traffic light control systems. Sensors such as infrared radiation and GPS are not capable of providing detailed traffic information. Compared with these sensors, surveillance cameras have the potential to provide real scenes for traffic analysis. In this research, a You Only Look Once (YOLO)-based algorithm is employed to detect and track vehicles from traffic videos, and a predefined road mask is used to determine traffic flow and turning events in different roads. A Kalman filter is used to estimate and predict vehicle speed and location under the condition of …

A Comparison Of Machine Learning Models To Prioritise Emailsusing Emotion Analysis For Customer Service Excellence, Mohammad Yasser Chuttur, Yashinee Parianen

Knowledge Engineering and Data Science

There has been little research on machine learning for email prioritization for customer service excellence. To fill this gap, we propose and assess the efficacy of various machine learning techniques for classifying emails into three degrees of priority: high, low, and neutral, based on the emotions inherent in the email content. It is predicted that after emails are classified into those three categories, recipients will be able to respond to emails more efficiently and provide better customer service. We use the NRC Emotion Lexicon to construct a labeled email dataset of 517,401 messages for our proposal. Following that, we train …

The Efficacy Of Research-Based "Mathematics For All" Professional, Kathleen Melhuish, Eva P. Thanheiser, Alexander White, Brenda Rosencrans, J. Michael Shaughnessy, Linda Foreman, Andrew Riffel, Layla Guyot

Mathematics and Statistics Faculty Publications and Presentations

This article contributes to the larger narrative around what makes a mathematics professional development (PD) successful and in what ways. We share a research-based PD model that was implemented in elementary schools in an urban school district for 3 years. The model uses a pseudo lesson study approach and emphasizes standards-based instruction. We found that teachers made gains in knowledge and instruction quality. However, whereas some students saw gains on standardized assessments, this was the case only for students who were not members of historically minoritized groups (Black/Latino), countering our assumptions that the PD would lead to equitable achievement results. …

Infrared Search For N-Butane And Trans-2-Butene In Titan’S Atmosphere, Brendan Steffens

Theses and Dissertations

This dissertation constitutes a study of the possible presence of trace hydrocarbons, namely n-butane (n-C4H10) and trans-2-butene (trans-2-C4H8) in Titan’s atmosphere. These molecules, both of which bear specific connections of interest to Titan’s astrobiological potential, are predicted by photochemical models to occur at detectable abundances within Titan’s atmosphere. In spite of this, neither has been detected to date, by any means. For this work, both of these molecules were characterized in the laboratory by obtaining a comprehensive set of highresolution, infrared cross section measurements at cold temperatures appropriate for Titan. In the case of n-butane, a pseudoline list (i.e. an …

Identifying Legal And Ethical Values In Ai, Keng Siau, Fiona Nah, Chunyan Ding, Fiona Fui-Hoon Nah

Research Collection School Of Computing and Information Systems

Artificial intelligence (AI) applications in health care, education, finance, mining, communications, and arts have brought about rapid and dramatic advances in these fields (Hyder et al., 2019). The rapidly expanding potential of AI in the economy and society has raised a set of legal and ethical issues (Wang and Siau, 2019; Siau and Wang, 2020). In-depth research into the ethical and legal aspects of AI to enable policymakers to introduce effective legislation and regulate AI development and applications is needed. This research uses a systematic qualitative research methodology, Value-Focused Thinking (VFT) (Keeney, 1996; Sheng et al., 2007), to identify the …

3pc: Three Point Compressors For Communication-Efficient Distributed Training And A Better Theory For Lazy Aggregation, Peter Richtarik, Igor Sokolov, Ilyas Fatkhullin, Elnur Gasanov, Zhize Li, Eduard Gorbunov

Research Collection School Of Computing and Information Systems

We propose and study a new class of gradient communication mechanisms for communication-efficient training -- three point compressors (3PC) -- as well as efficient distributed nonconvex optimization algorithms that can take advantage of them. Unlike most established approaches, which rely on a static compressor choice (e.g., Top-$K$), our class allows the compressors to {\em evolve} throughout the training process, with the aim of improving the theoretical communication complexity and practical efficiency of the underlying methods. We show that our general approach can recover the recently proposed state-of-the-art error feedback mechanism EF21 (Richt\'arik et al., 2021) and its theoretical properties as …

Time Dependent Orienteering Problem With Time Windows And Service Time Dependent Profits, M. Khodadadian, A. Divsalar, C. Verbeeck, Aldy Gunawan, P. Vansteenwegen

Research Collection School Of Computing and Information Systems

This paper addresses the time dependent orienteering problem with time windows and service time dependent profits (TDOPTW-STP). In the TDOPTW-STP, each vertex is assigned a minimum and a maximum service time and the profit collected at each vertex increases linearly with the service time. The goal is to maximize the total collected profit by determining a subset of vertices to be visited and assigning appropriate service time to each vertex, considering a given time budget and time windows. Moreover, travel times are dependent of the departure times. To solve this problem, a mixed integer linear model is formulated and a …

Digbug: Pre/Post-Processing Operator Selection For Accurate Bug Localization, Kisub Kim, Sankalp Ghatpande, Kui Liu, Anil Koyuncu, Dongsun Kim, Tegawendé F. Bissyande, Jacques Klein, Yves Le Traon

Research Collection School Of Computing and Information Systems

Bug localization is a recurrent maintenance task in software development. It aims at identifying relevant code locations (e.g., code files) that must be inspected to fix bugs. When such bugs are reported by users, the localization process become often overwhelming as it is mostly a manual task due to incomplete and informal information (written in natural languages) available in bug reports. The research community has then invested in automated approaches, notably using Information Retrieval techniques. Unfortunately, reported performance in the literature is still limited for practical usage. Our key observation, after empirically investigating a large dataset of bug reports as …

Designing Flipped Learning Activities For Beginner Programming Course, Benjamin Gan, Eng Lieh Ouh

Research Collection School Of Computing and Information Systems

This study focuses on designing flipped classroom learning activities across pre-class problem-based exercises; with in-class active discussions and practical problem-solving sessions; and follow up with postclass problem-based labs and assessments. We evaluate the effectiveness of our learning activities based on student surveys, course feedback, grades, and teacher feedback for a beginner programming course with non-IS students. We describe detail programming learning activities with comparisons to existing practices based on related work. Our findings are that majority of students (86%) agreed with flipped classroom, but teachers should be aware of the 14% who disagreed and cater for them. Teachers should avoid …

Data-Driven Retail Decision-Making Using Spatial Partitioning And Delineation Of Communities, Ming Hui Tan, Kar Way Tan

Research Collection School Of Computing and Information Systems

Urbanisation is resulting in rapid growth in road networks within cities. The evolution of road networks can be indicative of a city's economic growth and it is a field of research gaining prominence in recent years. This paper proposes a framework for spatial partition of large scale road networks that produces appropriately sized geospatial units in order to identify the type of community they serve. To this end, we have developed a three-stage procedure which first partitions the road network using Louvain method, followed by outlining the boundary of each partition using Uber H3 grids before classifying each partition using …

Docee: A Large-Scale And Fine-Grained Benchmark For Document-Level Event Extraction, Meihan Tong, Bin Xu, Shuai Wang, Meihuan Han, Yixin Cao, Jiangqi Zhu, Siyu Chen, Lei Hou, Juanzi Li

Research Collection School Of Computing and Information Systems

Event extraction aims to identify an event and then extract the arguments participating in the event. Despite the great success in sentencelevel event extraction, events are more naturally presented in the form of documents, with event arguments scattered in multiple sentences. However, a major barrier to promote documentlevel event extraction has been the lack of large-scale and practical training and evaluation datasets. In this paper, we present DocEE, a new document-level event extraction dataset including 27,000+ events, 180,000+ arguments. We highlight three features: largescale manual annotations, fine-grained argument types and application-oriented settings. Experiments show that there is still a big …

Reflection As An Agile Course Evaluation Tool, Siaw Ling Lo, Pei Hua Cher, Fernando Bello

Research Collection School Of Computing and Information Systems

Reflection is often used as a tool to analyse student learning, be it for internalizing of acquired knowledge or as a form of seeking help through expression of doubts or misconceptions. However, it can be a challenge to extract relevant information from the free-form reflection text. Often times the workload of manually analyzing the reflection text can be a form of deterrence instead of providing insights in the course delivery for instructors, let alone improving the learning experience. In this paper, we review the current usage of reflection and propose an automated reflection framework, together with an end-to-end analysis of …

Multi-Level Cross-View Contrastive Learning For Knowledge-Aware Recommender System, Ding Zou, Wei Wei, Xian-Ling Mao, Ziyang Wang, Minghui Qiu, Feida Zhu, Xin Cao

Research Collection School Of Computing and Information Systems

Knowledge graph (KG) plays an increasingly important role in recommender systems. Recently, graph neural networks (GNNs) based model has gradually become the theme of knowledge-aware recommendation (KGR). However, there is a natural deficiency for GNN-based KGR models, that is, the sparse supervised signal problem, which may make their actual performance drop to some extent. Inspired by the recent success of contrastive learning in mining supervised signals from data itself, in this paper, we focus on exploring the contrastive learning in KG-aware recommendation and propose a novel multi-level cross-view contrastive learning mechanism, named MCCLK. Different from traditional contrastive learning methods which …

A Recommendation System Approach To Tune A Qubo Solver, Siong Thye Goh, Jianyuan Bo, Matthieu Parizy, Hoong Chuin Lau

Research Collection School Of Computing and Information Systems

There are two major challenges to solving constrained optimization problems using a QuadraticUnconstrained Binary Optimization or QUBO solver (QS). First, we need to tune both the underlyingproblem parameters and the algorithm parameters. Second, the solution returned from a QSmight not be feasible. While it is common to use automated tuners such as SMAC and Hyperopt totune the algorithm parameters, the initial search ranges input for the auto tuner affect the performanceof the QS. In this paper, we propose a framework that resembles the Algorithm Selection(AS) framework to tune algorithm parameters for an annealing-based QS. To cope with constraints,we focus on …

Sediment Influence On Escherichia Coli Variability In The Rio Grande During The Dry Season In The South Valley, Albuquerque, New Mexico, Kate Wilkins

Water Resources Professional Project Reports

With Escherichia coli (E. coli) being a widely used indicator of pathogen contamination, concentrations need to be fully understood to create effective best management practices for water quality managers. While management and impairment standards are focused on concentrations in the water column, there is research showing that E. coli attaches to sediment in the river and acts as a reservoir for E. coli. The Middle Rio Grande in the South Valley, New Mexico is classified as an impaired reach because it exceeds the E. coli water quality standard. Exceedances are commonly seen during the wet season in high flows, but …

Galactic Component Mapping Of Galaxy Ugc 2885 By Machine Learning Classification, Robin J. Kwik, Jinfei Wang, Pauline Barmby, Benne Holwerda

Faculty and Staff Scholarship

Automating classification of galaxy components is important for understanding the formation and evolution of galaxies. Traditionally, only the larger galaxy structures such as the spiral arms, bulge, and disc are classified. Here we use machine learning (ML) pixel-by-pixel classification to automatically classify all galaxy components within digital imagery of massive spiral galaxy UGC 2885. Galaxy components include young stellar population, old stellar population, dust lanes, galaxy center, outer disc, and celestial background. We test three ML models: maximum likelihood classifier (MLC), random forest (RF), and support vector machine (SVM). We use high-resolution Hubble Space Telescope (HST) digital …

Beyond The Local Volume. Ii. Population Scaleheights And Ages Of Ultracool Dwarfs In Deep Hst/Wfc3 Parallel Fields, Christian Aganze, Adam J. Burgasser, Mathew Malkan, Christopher A. Theissen, Roberto A. Tejada Arevalo, Chih-Chun Hsu, Daniella C. Bardalez Gagliuffi, Russell E. Ryan Jr., Benne Holwerda

Faculty and Staff Scholarship

Ultracool dwarfs (UCDs) represent a significant proportion of stars in the Milky Way, and deep samples of these sources have the potential to constrain the formation history and evolution of low-mass objects in the Galaxy. Until recently, spectral samples have been limited to the local volume (d < 100 pc). Here, we analyze a sample of 164 spectroscopically characterized UCDs identified by Aganze et al. in the Hubble Space Telescope (HST) WFC3 Infrared Spectroscopic Parallel Survey (WISPS) and 3D-HST. We model the observed luminosity function using population simulations to place constraints on scaleheights, vertical velocity dispersions, and population ages as a function of spectral type. Our star counts are consistent with a power-law mass function and constant star formation history for UCDs, with vertical scaleheights of 249 pc for late-M dwarfs, 153 pc for L dwarfs, and 175 pc for T dwarfs. Using spatial and velocity dispersion relations, these scaleheights correspond to disk population ages of 3.6 Gyr for late-M dwarfs, 2.1 Gyr for L dwarfs, and 2.4 Gyr for T dwarfs, which are consistent with prior simulations that predict that L-type dwarfs are on average a younger and less dispersed population. There is an additional 1–2 Gyr systematic uncertainty on these ages due to variances in age-velocity relations. We use our population simulations to predict the UCD yield in the James Webb Space Telescope PASSAGES survey, a similar and deeper survey to WISPS and 3D-HST, and find that it will produce a comparably sized UCD sample, albeit dominated by thick disk and halo sources.

Water Quality Correlations With Phytoplankton Community Composition In A Polluted Shallow Subtropical Estuary, Connor Joseph Wong

Theses and Dissertations

The Indian River Lagoon (IRL) estuary has experienced eutrophication and degraded water quality due to high nutrient input, urbanization, and anthropogenic stressors. High nutrient input and restricted estuarine hydrology promotes algal blooms. Algal blooms or harmful algal blooms (HABs) are a global concern as they can cause negative ecological and economic impacts. The frequency and range of HABs is expected to be exacerbated by climate change and altered oceanic and estuarine conditions. Research on the formation and frequency of HABs is an ongoing global effort, but algal blooms are often dynamic and patchy making them difficult to study. This study …

Process For Designing And Implementing Provably Verifiable Voting Systems, Kholud Alghamdi

Theses and Dissertations

This research aims to explore processes for designing verifiable voting systems in which certain properties can be proven, exemplified with systems applicable to election processes in Saudi Arabia. The electronic government model has become a substantial channel for governments to connect to businesses and citizens, to develop services, and provide general information. E-voting and in particular online voting is one of the important tools that can be used in political and administrative places where information and communications technology devices and tools are utilized to simplify people’s lives and facilitate the election process and decision making. Election processes let a population …

Are You Really Muted?: A Privacy Analysis Of Mute Buttons In Video Conferencing Apps, Yucheng Yang, Jack West, George K. Thiruvathukal, Neil Klingensmith, Kassem Fawaz

Computer Science: Faculty Publications and Other Works

In the post-pandemic era, video conferencing apps (VCAs) have converted previously private spaces — bedrooms, living rooms, and kitchens — into semi-public extensions of the office. And for the most part, users have accepted these apps in their personal space, without much thought about the permission models that govern the use of their personal data during meetings. While access to a device’s video camera is carefully controlled, little has been done to ensure the same level of privacy for accessing the microphone. In this work, we ask the question: what happens to the microphone data when a user clicks the …

Mass Spectrometric Investigation Of Removal/Transformation Of Emerging Contaminants For Safer Potable Wastewater Reuse, Kristin Cochran

Theses and Dissertations

Water scarcity is of increasing global concern as rising demand depletes current sources, so other sources such as potable wastewater reuse are being utilized. Advanced wastewater reuse removes pathogens and many contaminants, but there are concerns about resistant contaminants and the transformation products that are generated during the treatment process. This research focuses on several different contaminant classes, how well they are removed via advanced treatment processes, what transformation products arise from both advanced treatment and chlorination disinfection, and how those treated waters may impact health via toxicity and estrogen activity.

Contaminant classes considered are illicit drugs, pharmaceuticals such as …

Complex Functional Joint Models For Longitudinal Electronic Health Record, Siyuan Guo

Theses and Dissertations

Longitudinal measurements are important components in electronic health record (EHR) data. In practice, using longitudinal EHR history is expected to improve the estimation or prediction performance when studying some outcomes of interest, such as binary outcome or time to event outcome. However, the longitudinal observations in EHR data is complex due to irregular and sparse EHR visits. Therefore, modelling longitudinal data and further incorporating them with different types of outcomes is challenge. In this dissertation, we aim to develop methodology to first, describe the pattern of the longitudinal predictors with continuous or binary observations, and second, model the longitudinal predictors …

Knowledge-Infused Learning, Manas Gaur

Theses and Dissertations

In DARPA’s view of the three waves of AI, the first wave of AI, symbolic AI, focused on explicit knowledge. The second and current wave of AI is termed statistical AI. Deep learning techniques have been able to exploit large amounts of data and massive computational power to improve human levels of performance in narrowly defined tasks. Separately, knowledge graphs have emerged as a powerful tool to capture and exploit a variety of explicit knowledge to make algorithms better apprehend the content and enable the next generation of data processing, such as semantic search. After initial hesitancy about the scalability …

Structure Preserving Reduced-Order Models Of Hamiltonian Systems, Megan Alice Mckay

Theses and Dissertations

Large-scale dynamical systems are expensive to simulate due to the computational cost accrued y the substantial number of degrees of freedom. To accelerate repeated numerical simulations of the systems, proper orthogonal decomposition reduced order models (POD-ROMs) have been developed. When applied to Hamiltonian systems, however, special care must be taken when performing the reduced order modeling to keep their energy-preserving nature. This work presents a survey of several structure-preserving reduced order models (SP-ROMs). In addition, this work employs the discrete empirical interpolation method (DEIM) and develops an SP-DEIM model for nonlinear Hamiltonian systems. The wave equation is considered as a …

Modified Em Algorithm In Smcure Package Based On Proportional Hazards Mixture Cure Model With Offset Terms, Jiaying Yi

Theses and Dissertations

Mixture cure model is a useful method of survival analysis for population including cured proportion and uncured proportion. The R package SMCURE applies EM algorithm to estimate the coefficients of covariates in the mixture cure model. Although an offset term is specified in the SMCURE statement, the offset term is not appropriately handled in the algorithm. This thesis aims to adjust the EM algorithm for the proportional hazards mixture cure model in the SMCURE package. In addition, the offset term can be specified separately in the incidence part or the latency part. The numerical experiments include simulation study and real …

Statistical Methods For Analyzing Dependence Structures With Applications In Single-Cell Experiments, Zhen Yang

Theses and Dissertations

This dissertation focuses on studying methods in dependence structure analysis. In particular, it consists of two topics: (1) modeling dynamic correlation in zero-inflated bivariate count data; and (2) gene co-expression latent factor analysis for cell-type clustering.

In Chapter 2, a zero-inflated negative binomial model for analyzing the dynamic correlation in zero-inflated bivariate count data is proposed. Interactions between biological molecules in a cell are tightly coordinated and often highly dynamic. As a result of these varying signaling activities, changes in gene co-expression patterns could often be observed. The advancements in next-generation sequencing tech-nologies bring new statistical challenges for studying these …

Statistical Methods For Analyzing Multi-Omics Data: Dependence Structure And Missing Values, Wenda Zhang

Theses and Dissertations

The advancements in high-throughput technologies have made it possible to generate a huge number of "omics'' data, including genomics, proteomics, transcriptomics, epigenomics, metabolomics, and microbiomics. Combining multiple data sources and performing joint analyses with all available information and the phenotypic outcome can reflect various aspects in complex biological systems, such as revealing regulation processes, discovering novel associations between biological entities, and identifying relevant biomarkers for certain diseases or phenotypic outcomes. This dissertation focuses on developing statistical models for analyzing multi-omics data. It is comprised of three topics: (1) integrative analysis for multi-omics data with missing observations in intermediate variables; (2) …

Cnn-Based Semantic Segmentation With Shape Prior Knowledge, Yuhang Lu

Theses and Dissertations

Semantic segmentation that aims at grouping discrete pixels into connected regions is a fundamental step in many high-level computer vision tasks. In recent years, Convolutional Neural Networks (CNNs) have made breakthrough progresses in public semantic segmentation benchmarks. The ability of learning from large-scale labeled datasets empowers them to generalize to unseen images better than traditional nonlearning-based methods. Nevertheless, the heavy dependency on labeled data also limits their applications in tasks where high-quality ground truth segmentation masks are scarce or difficult to acquire. In this dissertation, we study the problem of alleviating the data dependency for CNN-based segmentation with a focus …