Matching Items (149)
Filtering by

Clear all filters

Description

Standardization is sorely lacking in the field of musical machine learning. This thesis project endeavors to contribute to this standardization by training three machine learning models on the same dataset and comparing them using the same metrics. The music-specific metrics utilized provide more relevant information for diagnosing the shortcomings of

Standardization is sorely lacking in the field of musical machine learning. This thesis project endeavors to contribute to this standardization by training three machine learning models on the same dataset and comparing them using the same metrics. The music-specific metrics utilized provide more relevant information for diagnosing the shortcomings of each model.

ContributorsHilliker, Jacob (Author) / Li, Baoxin (Thesis director) / Libman, Jeffrey (Committee member) / Barrett, The Honors College (Contributor) / Computer Science and Engineering Program (Contributor)
Created2021-12
161047-Thumbnail Image.png
ContributorsHilliker, Jacob (Author) / Li, Baoxin (Thesis director) / Libman, Jeffrey (Committee member) / Barrett, The Honors College (Contributor) / Computer Science and Engineering Program (Contributor)
Created2021-12
161048-Thumbnail Image.jpg
ContributorsHilliker, Jacob (Author) / Li, Baoxin (Thesis director) / Libman, Jeffrey (Committee member) / Barrett, The Honors College (Contributor) / Computer Science and Engineering Program (Contributor)
Created2021-12
161217-Thumbnail Image.png
Description

Among classes in the Computer Science curriculum at Arizona State University, Automata Theory is widely considered to be one of the most difficult. Many Computer Science concepts have strong visual components that make them easier to understand. Binary trees, Dijkstra's algorithm, pointers, and even more basic concepts such as arrays

Among classes in the Computer Science curriculum at Arizona State University, Automata Theory is widely considered to be one of the most difficult. Many Computer Science concepts have strong visual components that make them easier to understand. Binary trees, Dijkstra's algorithm, pointers, and even more basic concepts such as arrays all have very strong visual components. Not only that, but resources for them are abundantly available online. Automata Theory, on the other hand, is the first Computer Science course students encounter that has a significant focus on deep theory. Many
of the concepts can be difficult to visualize, or at least take a lot of effort to do so. Furthermore, visualizers for finite state machines are hard to come by. Because I thoroughly enjoyed learning about Automata Theory and parsers, I wanted to create a program that involved the two. Additionally, I thought creating a program for visualizing automata would help students who struggle with Automata Theory develop a stronger understanding of it.

ContributorsSmith, Andrew (Author) / Burger, Kevin (Thesis director) / Meuth, Ryan (Committee member) / Barrett, The Honors College (Contributor) / School of Mathematical and Statistical Sciences (Contributor)
Created2021-12
Description

Among classes in the Computer Science curriculum at Arizona State University, Automata Theory is widely considered to be one of the most difficult. Many Computer Science concepts have strong visual components that make them easier to understand. Binary trees, Dijkstra's algorithm, pointers, and even more basic concepts such as arrays

Among classes in the Computer Science curriculum at Arizona State University, Automata Theory is widely considered to be one of the most difficult. Many Computer Science concepts have strong visual components that make them easier to understand. Binary trees, Dijkstra's algorithm, pointers, and even more basic concepts such as arrays all have very strong visual components. Not only that, but resources for them are abundantly available online. Automata Theory, on the other hand, is the first Computer Science course students encounter that has a significant focus on deep theory. Many
of the concepts can be difficult to visualize, or at least take a lot of effort to do so. Furthermore, visualizers for finite state machines are hard to come by. Because I thoroughly enjoyed learning about Automata Theory and parsers, I wanted to create a program that involved the two. Additionally, I thought creating a program for visualizing automata would help students who struggle with Automata Theory develop a stronger understanding of it.

ContributorsSmith, Andrew (Author) / Burger, Kevin (Thesis director) / Meuth, Ryan (Committee member) / Barrett, The Honors College (Contributor) / School of Mathematical and Statistical Sciences (Contributor)
Created2021-12
Description

Among classes in the Computer Science curriculum at Arizona State University, Automata Theory is widely considered to be one of the most difficult. Many Computer Science concepts have strong visual components that make them easier to understand. Binary trees, Dijkstra's algorithm, pointers, and even more basic concepts such as arrays

Among classes in the Computer Science curriculum at Arizona State University, Automata Theory is widely considered to be one of the most difficult. Many Computer Science concepts have strong visual components that make them easier to understand. Binary trees, Dijkstra's algorithm, pointers, and even more basic concepts such as arrays all have very strong visual components. Not only that, but resources for them are abundantly available online. Automata Theory, on the other hand, is the first Computer Science course students encounter that has a significant focus on deep theory. Many
of the concepts can be difficult to visualize, or at least take a lot of effort to do so. Furthermore, visualizers for finite state machines are hard to come by. Because I thoroughly enjoyed learning about Automata Theory and parsers, I wanted to create a program that involved the two. Additionally, I thought creating a program for visualizing automata would help students who struggle with Automata Theory develop a stronger understanding of it.

ContributorsSmith, Andrew (Author) / Burger, Kevin (Thesis director) / Meuth, Ryan (Committee member) / Barrett, The Honors College (Contributor) / School of Mathematical and Statistical Sciences (Contributor)
Created2021-12
161175-Thumbnail Image.png
Description

This thesis explores how large scale cyber exercises work in the 21st century, going in-depth on Exercise Cyber Shield, the Department of Defense’s largest unclassified cyber defense exercise run by the Army National Guard. It highlights why these cyber exercises are so relevant, going over several large scale cyber attacks

This thesis explores how large scale cyber exercises work in the 21st century, going in-depth on Exercise Cyber Shield, the Department of Defense’s largest unclassified cyber defense exercise run by the Army National Guard. It highlights why these cyber exercises are so relevant, going over several large scale cyber attacks that have occurred in the past year and the impact they caused. This research aims to illuminate the intricacies around cyber exercise assessment involving manual vs automated scoring systems; this is brought back to work on creating an automated scoring engine for Exercise Cyber Shield. This thesis provides an inside look behind the scenes of the operations of the largest unclassified cyber defense exercise in the United States, including conversations with the Exercise Officer-In-Charge of Cyber Shield as well as a cyber exercise expert working on assessment of Exercise Cyber Shield, and the research also includes information from past final reports for Cyber Shield. Issues that these large scale cyber exercises have faced over the years are brought to light, and attempts at solutions are discussed.

ContributorsZhao, Henry (Author) / Chavez Echeagaray, Maria Elena (Thesis director) / Rhodes, Brad (Committee member) / Barrett, The Honors College (Contributor) / Computer Science and Engineering Program (Contributor) / School of Mathematical and Statistical Sciences (Contributor)
Created2021-12
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
Description
As Big Data becomes more relevant, existing grouping and clustering algorithms will need to be evaluated for their effectiveness with large amounts of data. Previous work in Similarity Grouping proposes a possible alternative to existing data analytics tools, which acts as a hybrid between fast grouping and insightful clustering. We,

As Big Data becomes more relevant, existing grouping and clustering algorithms will need to be evaluated for their effectiveness with large amounts of data. Previous work in Similarity Grouping proposes a possible alternative to existing data analytics tools, which acts as a hybrid between fast grouping and insightful clustering. We, the SimCloud Team, proposed Distributed Similarity Group-by (DSG), a distributed implementation of Similarity Group By. Experimental results show that DSG is effective at generating meaningful clusters and has a lower runtime than K-Means, a commonly used clustering algorithm. This document presents my personal contributions to this team effort. The contributions include the multi-dimensional synthetic data generator, execution of the Increasing Scale Factor experiment, and presentations at the NCURIE Symposium and the SISAP 2019 Conference.
ContributorsWallace, Xavier Guillermo (Author) / Silva, Yasin (Thesis director) / Kuai, Xu (Committee member) / School for the Future of Innovation in Society (Contributor) / School of Mathematical and Natural Sciences (Contributor) / Barrett, The Honors College (Contributor)
Created2019-12
132263-Thumbnail Image.png
Description
Karate is a Japanese martial art that originated approximately a century ago, with heavy influence from Chinese martial arts at the time. Although it was originally created as a form of self-defense, many today practice it for sport. Organizations such as the World Karate Federation (WKF) and USA Karate establish

Karate is a Japanese martial art that originated approximately a century ago, with heavy influence from Chinese martial arts at the time. Although it was originally created as a form of self-defense, many today practice it for sport. Organizations such as the World Karate Federation (WKF) and USA Karate establish rules for competitions as well as host tournaments for practitioners of all ages and skill levels to participate in. Dojos will often host small, local tournaments for their students to practice and sharpen their competition skills. Smaller tournaments often do not have the same tools and technologies that larger tournaments do. Sign-ups are typically done in-person and payments are cash-only, which can be inconvenient for those who are extremely busy or forgetful. Another issue with hosting local tournaments is that the software used to run the timer is a desktop application, called Karate Semaphore. In the case of technical difficulties, installing the software on another machine can be extremely time-consuming and delay the progression of the tournament. Not to mention, Karate Semaphore was created following the 2012 WKF rules—meaning it is currently out of date, as it does not contain any features supporting new rules.
For my creative project, I designed a website through which smaller, local tournament registration and management are possible. Users can register for tournaments through the registration page. Registered users can check their registration is successful by viewing a table of all competitors. If the list of competitors is too long, they can filter results based on search criteria. Tournament management will be possible via a functioning timer following WKF rules which keeps track of both the match’s score as well as time.
ContributorsRuan, Shirley (Author) / Sarwat, Mohamed (Thesis director) / Chen, Yinong (Committee member) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2019-05