Barrett

Barrett, The Honors College at Arizona State University proudly showcases the work of undergraduate honors students by sharing this collection exclusively with the ASU community.

Barrett accepts high performing, academically engaged undergraduate students and works with them in collaboration with all of the other academic units at Arizona State University. All Barrett students complete a thesis or creative project which is an opportunity to explore an intellectual interest and produce an original piece of scholarly research. The thesis or creative project is supervised and defended in front of a faculty committee. Students are able to engage with professors who are nationally recognized in their fields and committed to working with honors students. Completing a Barrett thesis or creative project is an opportunity for undergraduate honors students to contribute to the ASU academic community in a meaningful way.

Displaying 1 - 5 of 5
Filtering by

Clear all filters

Deriving Intrinsic Baseball Pitcher Value By Predicting Pitcher Performance From Individual Pitch Metrics

Description

Historically, the predominant strategy for evaluating baseball pitchers has been through statistics created directly from the offensive production against the pitcher, such as ERA. Such statistics are inherently relative to the abilities and competition level of the opposing offense and the field defense, which the pitcher has no control over,…

Historically, the predominant strategy for evaluating baseball pitchers has been through statistics created directly from the offensive production against the pitcher, such as ERA. Such statistics are inherently relative to the abilities and competition level of the opposing offense and the field defense, which the pitcher has no control over, making it difficult to compare pitchers across leagues. In this paper, I use cutting edge pitch-tracking data to develop a pitch evaluation model that is intrinsic to the attributes of the pitches themselves, and not influenced directly by the outcomes of each individual pitch. I train four different classifiers to predict the probability of each pitch belonging to different subsets of outcomes, then multiply the probability of each outcome by that outcome’s average run value to arrive at an expected run value for the pitch. I compare the performance of each classifier to a baseline, examine the most impactful features, and compare the top pitchers identified by the model to those identified by a different baseball statistics resource, ultimately concluding that three of the four classification models are productive and that the overall intrinsic evaluation model accurately identifies the sports top performers.
ContributorsSmith, Roman (Author) / Shakarian, Paulo (Thesis director) / Macdonald, Brian (Committee member) / Barrett, The Honors College (Contributor) / Computer Science and Engineering Program (Contributor)
Created2023-05

A Graph-Based Machine Learning Approach to Realistic Traffic Volume Generation

Description
In this work, we explore the potential for realistic and accurate generation of hourly traffic volume with machine learning (ML), using the ground-truth data of Manhattan road segments collected by the New York State Department of Transportation (NYSDOT). Specifically, we address the following question– can we develop a ML algorithm…

In this work, we explore the potential for realistic and accurate generation of hourly traffic volume with machine learning (ML), using the ground-truth data of Manhattan road segments collected by the New York State Department of Transportation (NYSDOT). Specifically, we address the following question– can we develop a ML algorithm that generalizes the existing NYSDOT data to all road segments in Manhattan?– by introducing a supervised learning task of multi-output regression, where ML algorithms use road segment attributes to predict hourly traffic volume. We consider four ML algorithms– K-Nearest Neighbors, Decision Tree, Random Forest, and Neural Network– and hyperparameter tune by evaluating the performances of each algorithm with 10-fold cross validation. Ultimately, we conclude that neural networks are the best-performing models and require the least amount of testing time. Lastly, we provide insight into the quantification of “trustworthiness” in a model, followed by brief discussions on interpreting model performance, suggesting potential project improvements, and identifying the biggest takeaways. Overall, we hope our work can serve as an effective baseline for realistic traffic volume generation, and open new directions in the processes of supervised dataset generation and ML algorithm design.
ContributorsOtstot, Kyle (Author) / De Luca, Gennaro (Thesis director) / Chen, Yinong (Committee member) / Barrett, The Honors College (Contributor) / School of Mathematical and Statistical Sciences (Contributor) / Computer Science and Engineering Program (Contributor)
Created2022-05

An Analysis of Significant Factors Affecting Grades Using Student Data

Description

This project tackles a real-world example of a classroom with college students to discover what factors affect a student’s outcome in the class as well as investigate when and why a student who started well in the semester may end poorly later on. First, this project performs a statistical analysis…

This project tackles a real-world example of a classroom with college students to discover what factors affect a student’s outcome in the class as well as investigate when and why a student who started well in the semester may end poorly later on. First, this project performs a statistical analysis to ensure that the total score of a student is truly based on the factors given in the dataset instead of due to random chance. Next, factors that are the most significant in affecting the outcome of scores in zyBook assignments are discovered. Thirdly, visualization of how students perform over time is displayed for the student body as a whole and students who started well at the beginning of the semester but trailed off towards the end. Lastly, the project also gives insight into the failure metrics for good starter students who unfortunately did not perform as well later in the course.
ContributorsChung, Michael (Author) / Meuth, Ryan (Thesis director) / Samara, Marko (Committee member) / Barrett, The Honors College (Contributor) / School of Mathematical and Statistical Sciences (Contributor) / Computer Science and Engineering Program (Contributor)
Created2023-05

US Forest Fire Size Prediction using Machine Learning

Description
The number of extreme wildfires is on the rise globally, and predicting the size of a fire will help officials make appropriate decisions to mitigate the risk the fire poses against the environment and humans. This study attempts to find the burned area of fires in the United States based…

The number of extreme wildfires is on the rise globally, and predicting the size of a fire will help officials make appropriate decisions to mitigate the risk the fire poses against the environment and humans. This study attempts to find the burned area of fires in the United States based on attributes such as time, weather, and location of the fire using machine learning methods.
ContributorsPrabagaran, Padma (Author, Co-author) / Meuth, Ryan (Thesis director) / McCulloch, Robert (Committee member) / Barrett, The Honors College (Contributor) / Computer Science and Engineering Program (Contributor) / School of Mathematical and Statistical Sciences (Contributor)
Created2022-12

An Empirical Study of View Construction for Multi-View Learning

Description
Multi-view learning, a subfield of machine learning that aims to improve model performance by training on multiple views of the data, has been studied extensively in the past decades. It is typically applied in contexts where the input features naturally form multiple groups or views. An example of a naturally…

Multi-view learning, a subfield of machine learning that aims to improve model performance by training on multiple views of the data, has been studied extensively in the past decades. It is typically applied in contexts where the input features naturally form multiple groups or views. An example of a naturally multi-view context is a data set of websites, where each website is described not only by the text on the page, but also by the text of hyperlinks pointing to the page. More recently, various studies have demonstrated the initial success of applying multi-view learning on single-view data with multiple artificially constructed views. However, there lacks a systematic study regarding the effectiveness of such artificially constructed views. To bridge this gap, this thesis begins by providing a high-level overview of multi-view learning with the co-training algorithm. Co-training is a classic semi-supervised learning algorithm that takes advantage of both labelled and unlabelled examples in the data set for training. Then, the thesis presents a web-based tool developed in Python allowing users to experiment with and compare the performance of multiple view construction approaches on various data sets. The supported view construction approaches in the web-based tool include subsampling, Optimal Feature Set Partitioning, and the genetic algorithm. Finally, the thesis presents an empirical comparison of the performance of these approaches, not only against one another, but also against traditional single-view models. The findings show that a simple subsampling approach combined with co-training often outperforms both the other view construction approaches, as well as traditional single-view methods.
ContributorsAksoy, Kaan (Author) / Maciejewski, Ross (Thesis director) / He, Jingrui (Committee member) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2019-12