Statistics and Probability Commons^™

Energy Integrated Ratio Analysis Of The Anomalous Precession Frequency In The Fermilab Muon G-2 Experiment, Ritwika Chakraborty

Theses and Dissertations--Physics and Astronomy

The muon’s anomalous magnetic moment, a_μ, provides a unique way for probing physics beyond the standard model experimentally as it gathers contributions from all the known and unknown forces and particles in nature. The theoretical prediction of a_μ has been in greater than 3 σ tension with the experimental measurement since the results of the Muon g-2 Experiment at the Brookhaven National Laboratory (E-821) were published in the early 2000s with a precision of 540 ppb. To settle this tension, the new Fermilab Muon g - 2 Experiment (E-989) is currently taking data with the aim of …

Role Of Inhibition And Spiking Variability In Ortho- And Retronasal Olfactory Processing, Michelle F. Craft

Theses and Dissertations

Odor perception is the impetus for important animal behaviors, most pertinently for feeding, but also for mating and communication. There are two predominate modes of odor processing: odors pass through the front of nose (ortho) while inhaling and sniffing, or through the rear (retro) during exhalation and while eating and drinking. Despite the importance of olfaction for an animal’s well-being and specifically that ortho and retro naturally occur, it is unknown whether the modality (ortho versus retro) is transmitted to cortical brain regions, which could significantly instruct how odors are processed. Prior imaging studies show different …

Fact Sheet, Yale University Office Of Institutional Research

Fact Sheets

No abstract provided.

Mindfulness And Pain Regulation: The Role Of Acceptance And Commitment Therapy For Individuals With Chronic Pain, Ariana C. White

Honors Theses and Capstones

Chronic pain is a significant and widely prevalent health condition which requires comprehensive care to address the many facets contributing to symptomatology. In 2016, 20% of American adults (about 50 million) reported experiencing chronic pain, of which 7.4% indicated that chronic pain frequently limited their life and participation in activities within the past 3 months (CDC, 2018). As a result, many individuals with chronic pain turn to opioid-based medication for pain relief, but long-term use of opioids actually increases pain sensation (Tobin, 2019). Moreover, opioid medication is unable to target underlying mental health components which emerge as part of chronic …

Realtime Event Detection In Sports Sensor Data With Machine Learning, Mallory Cashman

Honors Theses and Capstones

Machine learning models can be trained to classify time series based sports motion data, without reliance on assumptions about the capabilities of the users or sensors. This can be applied to predict the count of occurrences of an event in a time period. The experiment for this research uses lacrosse data, collected in partnership with SPAITR - a UNH undergraduate startup developing motion tracking devices for lacrosse. Decision Tree and Support Vector Machine (SVM) models are trained and perform with high success rates. These models improve upon previous work in human motion event detection and can be used a reference …

Modeling Joint Survival Probabilities Of Runs Scored And Balls Faced In Limited Overs Cricket Using Copulas, Lochana K. Palayangoda, Hasika W. Senevirathne, Ananda B. Manage

Mathematics & Statistics Faculty Publications

In limited overs cricket, the goal of a batsman is to score a maximum number of runs within a limited number of balls. Therefore, the number of runs scored and the number of balls faced are the two key statistics used to evaluate the performance of a batsman. In cricket, as the batsmen play as pairs, having longer partnerships is also key to building strong innings. Moreover, having a steady opening partnership is extremely important as a team aims to build such a stronger innings. In this study, we have shown a way to evaluate the performance of opening partnerships …

Optimizing Model Observer Performance In Learning-Based Ct Reconstruction, Gregory Ongie, Emil Y. Sidky, Ingrid S. Reiser, Xiaochuan Pan

Mathematical and Statistical Science Faculty Research and Publications

Deep neural networks used for reconstructing sparse-view CT data are typically trained by minimizing a pixel- wise mean-squared error or similar loss function over a set of training images. However, networks trained with such losses are prone to wipe out small, low-contrast features that are critical for screening and diagnosis. To remedy this issue, we introduce a novel training loss inspired by the model observer framework to enhance the detectability of weak signals in the reconstructions. We evaluate our approach on the reconstruction of synthetic sparse-view breast CT data, and demonstrate an improvement in signal detectability with the proposed loss.

M-Cubes: An Efficient And Portable Implementation Of Multi-Dimensional Integration For Gpus, Ioannis Sakiotis, Kamesh Arumugam, Marc Paterno, Desh Ranjan, Balŝa Terzić, Mohammad Zubair

Computer Science Faculty Publications

The task of multi-dimensional numerical integration is frequently encountered in physics and other scientific fields, e.g., in modeling the effects of systematic uncertainties in physical systems and in Bayesian parameter estimation. Multi-dimensional integration is often time-prohibitive on CPUs. Efficient implementation on many-core architectures is challenging as the workload across the integration space cannot be predicted a priori. We propose m-Cubes, a novel implementation of the well-known Vegas algorithm for execution on GPUs. Vegas transforms integration variables followed by calculation of a Monte Carlo integral estimate using adaptive partitioning of the resulting space. mCubes improves performance on GPUs by maintaining relatively …

Reinforcement Learning: Low Discrepancy Action Selection For Continuous States And Actions, Jedidiah Lindborg

College of Graduate Studies: Theses & Dissertations

In reinforcement learning the process of selecting an action during the exploration or exploitation stage is difficult to optimize. The purpose of this thesis is to create an action selection process for an agent by employing a low discrepancy action selection (LDAS) method. This should allow the agent to quickly determine the utility of its actions by prioritizing actions that are dissimilar to ones that it has already picked. In this way the learning process should be faster for the agent and result in more optimal policies.

Searching For Anomalous Extensive Air Showers Using The Pierre Auger Observatory Fluorescence Detector, Andrew Puyleart

Dissertations, Master's Theses and Master's Reports

Anomalous extensive air showers have yet to be detected by cosmic ray observatories. Fluorescence detectors provide a way to view the air showers created by cosmic rays with primary energies reaching up to hundreds of EeV . The resulting air showers produced by these highly energetic collisions can contain features that deviate from average air showers. Detection of these anomalous events may provide information into unknown regions of particle physics, and place constraints on cross-sectional interaction lengths of protons. In this dissertation, I propose measurements of extensive air shower profiles that are used in a machine learning pipeline to distinguish …

Maximum Likelihood Estimator Method To Estimate Flaw Parameters For Different Glass Types, Nabhajit Goswami

Dissertations, Master's Theses and Master's Reports

Glass is commonly used in architectural applications, such as windows and in-fill panels and structural applications, such as beams and staircases. Despite the popularity of structural glass use in buildings, an engineering design standard to determine the required component or member strength for design loads does not exist. Glass is a brittle material that lacks a well-defined yield or ultimate stress, unlike ductile materials. The traditional engineering methods used to design a ductile material cannot be used to design a glass component. Glass fails in tension primarily due to the presence of microscopic flaws present on the surface that acts …

Information Entropic Content Of Astrophysical Spectra: Applications To Cosmology And Astrobiology, Sara Vannah

Dartmouth College Ph.D Dissertations

Astrophysics faces two critical challenges: the difficulty of observing very distant targets and the difficulty of interpreting science in diverse and often extreme environments that have not been replicated on Earth. In this thesis, we discuss two types of spectra — one from early universe cosmology and one from astrobiology — where improvements in telescope technology are just ushering in a wave of precise observations, addressing the first challenge. This accelerates the need for a solution to the second challenge. Traditional methods for analyzing these two spectra rely heavily on unsettled science, biasing results to match the input assumptions. In …

The Three-Way Interplay Among Early Life Exposures, The Gut Microbiome, And Outcomes In Infancy, Yuka Moroishi

Dartmouth College Ph.D Dissertations

The bidirectional relationship between the gut microbiome and immune system plays an important role in host immune status: the immune system provides the gut microbiome the optimal environment to thrive in, and the gut microbiome helps regulate the immune system. This relationship is especially important in infants, whose immune system is still premature and rely on innate immunity.

We investigated the three-way interplay among early-life exposures, the developing gut microbiome, and outcomes in infancy from the general population in New Hampshire, US. We used prospective cohort data from the New Hampshire Birth Cohort study to 1) determine whether timing of …

Analysis Of Minor League Rule Changes Effect On Stolen Bases, Zachary Houghtaling

Williams Honors College, Honors Research Projects

This study uses various statistical analyses to evaluate the justification of rule changes for Major League Baseball that were implemented within the Minor Leagues during the 2021 minor league season. The primary focus of the study is predicting how some of these Minor League rule changes could affect the stolen base success rate and the number of attempts per game within the Major Leagues. A survey was conducted to evaluate how fans feel about stolen bases within the current game and if rules should be altered to increase the number of stolen bases that occur. Additionally, recorded Major and Minor …

Maintenance Optimization In A Digital Twin For Industry 4.0, Abhijit Gosavi, Vy Khoi Le

Engineering Management and Systems Engineering Faculty Research & Creative Works

The advent of Internet of Things and artificial intelligence in the era of Industry 4.0 has transformed decision-making within production systems. In particular, many decisions that previously required significant human activity are now made automatically with minimal human intervention via so-called digital twins (DTs). In the context of maintenance and reliability modeling, this naturally calls for new paradigms that can be seamlessly integrated within DTs for decision-making. The input data for time to failure needed in reliability computations are directly collected from the work center in a digital setting and often do not satisfy a known distribution. A neural network …

An Analysis On Trends Of Research Topics In Civic Education Using Dynamic Topic Model, Poon Thongsai

Chulalongkorn University Theses and Dissertations (Chula ETD)

The aim of this thesis is to study the trend of civic and citizenship education research from 2000 to 2020 and the influence the regional background of researches has on the research discussion. Relevant data is collected from ERIC and SCOPUS database. This includes abstracts, published year, regional background of researchers, and author h-index. The keywords used are “civic education” or “citizenship education” or “civics”. There are 4917 papers extracted in total. Upon doing further preparation, 4854 articles are prepared for analysis. We apply Structural Topic model (STM) technique to the abstracts with covariates including the published year and the …

Perception Of Health Care Access In Rural Georgia: Findings From A Community Health Needs Assessment Survey, Elisa M. Childs, Tiffany R. Washington

Journal of the Georgia Public Health Association

Background: Limited access to health care services has been cited as a barrier to care for individuals who live in rural areas, contributing to significant health disparities in this population. While perception of services has been cited as a determinant of utilization of health services, it is unknown how perception of services influences health care access in rural areas. The paucity of studies specific to areas in the United States that are medically underserved, necessitated this study and its quantification of the issues that are relevant to individuals living in rural Georgia.

Methods: This study examined the perception of health …

A Comparison Of Imbalanced Data Handling Methods For Pre-Trained Model In Multi-Label Classification Of Stack Overflow, Arisa Umparat

Chulalongkorn University Theses and Dissertations (Chula ETD)

Tag classification is essential in Stack Overflow. Instead of combining through pages or replies of irrelevant information, users can easily and quickly pinpoint relevant posts and answers using tags. Since User-submitted posts can have multiple tags, classifying tags in Stack Overflow can be challenging. This results in an imbalance problem between labels in the whole labelset. Pretrained deep learning models with small datasets can improve tag classification accuracy. Common multi-label resampling techniques with machine learning classifiers can also fix this issue. Still, few studies have explored which resampling technique can improve the performance of pre-trained deep models for predicting tags. …

An Application Of Reinforcement Learning To Credit Scoring Based On The Logistic Bandit Framework, Kantapong Visantavarakul

Chulalongkorn University Theses and Dissertations (Chula ETD)

This study applies reinforcement learning to credit scoring by using the logistic bandit framework. The credit scoring and the credit underwriting are modeled into a single sequential decision problem where the credit underwriter takes a sequence of actions over an indefinite number of time steps. The traditional credit scoring approach considers the model construction separately from the underwriting process. This approach is identified as a greedy algorithm in the reinforcement learning literature, which is commonly believed to be inferior to an efficient reinforcement learning approach such as Thompson sampling. This is true under the simple setting, i.e., granting credit to …

Multi-Output Learning For Predicting Evaluation And Reopening Of Github Pull Requests On Open-Source Projects, Peerachai Banyongrakkul

Chulalongkorn University Theses and Dissertations (Chula ETD)

GitHub's pull-based development model is widely used by software development teams to manage software complexity. Contributors create pull requests for merging changes into the main codebase, and integrators review these requests to maintain quality and stability. However, a high volume of pull requests can overburden integrators, causing feedback delays. Previous studies have used machine learning and statistical techniques with tabular data as features, but these may lose meaningful information. Additionally, acceptance and latency may not be sufficient for the pull request evaluation. Moreover, reopened pull requests can add maintenance costs and burden already-busy developers. This thesis proposes a novel multi-output …