Barrett, The Honors College Thesis/Creative Project Collection
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 - 10 of 11
Filtering by
- All Subjects: Innovation
- All Subjects: deep learning
Description
Emotion recognition in conversation has applications within numerous domains such as affective computing and medicine. Recent methods for emotion recognition jointly utilize conversational data over several modalities including audio, video, and text. However, state-of-the-art frameworks for this task do not focus on the feature extraction and feature fusion steps of this process. This thesis aims to improve the state-of-the-art method by incorporating two components to better accomplish these steps. By doing so, we are able to produce improved representations for the text modality and better model the relationships between all modalities. This paper proposes two methods which focus on these concepts and provide improved accuracy over the state-of-the-art framework for multimodal emotion recognition in dialogue.
ContributorsRawal, Siddharth (Author) / Baral, Chitta (Thesis director) / Shah, Shrikant (Committee member) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2020-05
Description
The purpose of this project was to interview eleven Hubert H. Humphrey Fellows at the Walter Cronkite School at Arizona State University through a podcast series titled “The Global Journalist Roundtable”. During a two month period, I interviewed the eleven Fellows and through a keyword analysis of the transcripts of each interview, I determined several themes which according to the Fellows were important aspects of global media. Those themes were education, innovation, social media as a disrupter to news verifiability, polarization, censorship, the importance of truthful news, and leadership. The reason for interviewing the Humphrey Fellows specifically was due to my sheer curiosity, respect, and admiration for them as professionals in the global media industry.
ContributorsEverett, William (Author) / Silcock, William (Thesis director) / Barrett, Marianne (Committee member) / Walter Cronkite School of Journalism & Mass Comm (Contributor) / Barrett, The Honors College (Contributor)
Created2020-05
Description
Accurate pose initialization and pose estimation are crucial requirements in on-orbit space assembly and various other autonomous on-orbit tasks. However, pose initialization and pose estimation are much more difficult to do accurately and consistently in space. This is primarily due to not only the variable lighting conditions present in space, but also the power requirements mandated by space-flyable hardware. This thesis investigates leveraging a deep learning approach for monocular one-shot pose initialization and pose estimation. A convolutional neural network was used to estimate the 6D pose of an assembly truss object. This network was trained by utilizing synthetic imagery generated from a simulation testbed. Furthermore, techniques to quantify model uncertainty of the deep learning model were investigated and applied in the task of in-space pose estimation and pose initialization. The feasibility of this approach on low-power computational platforms was also tested. The results demonstrate that accurate pose initialization and pose estimation can be conducted using a convolutional neural network. In addition, the results show that the model uncertainty can be obtained from the network. Lastly, the use of deep learning for pose initialization and pose estimation in addition with uncertainty quantification was demonstrated to be feasible on low-power compute platforms.
ContributorsKailas, Siva Maneparambil (Author) / Ben Amor, Heni (Thesis director) / Detry, Renaud (Committee member) / Economics Program in CLAS (Contributor) / School of Mathematical and Statistical Sciences (Contributor) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2020-05
Description
Spotify, one of the most popular music streaming services, has many
algorithms for recommending new music to users. However, at the
core of their recommendations is the collaborative filtering algorithm,
which recommends music based on what other people with similar
tastes have listened to [1]. While this can produce highly relevant
content recommendations, it tends to promote only popular content
[2]. The popularity bias inherent in collaborative-filtering based
systems can overlook music that fits a user’s taste, simply because
nobody else is listening to it. One possible solution to this problem is
to recommend music based on features of the music itself, and
recommend songs which have similar features. Here, a method for
extracting high-level features representing the mood of a song is
presented, with the aim of tailoring music recommendations to an
individual's mood, and providing music recommendations with
diversity in popularity.
algorithms for recommending new music to users. However, at the
core of their recommendations is the collaborative filtering algorithm,
which recommends music based on what other people with similar
tastes have listened to [1]. While this can produce highly relevant
content recommendations, it tends to promote only popular content
[2]. The popularity bias inherent in collaborative-filtering based
systems can overlook music that fits a user’s taste, simply because
nobody else is listening to it. One possible solution to this problem is
to recommend music based on features of the music itself, and
recommend songs which have similar features. Here, a method for
extracting high-level features representing the mood of a song is
presented, with the aim of tailoring music recommendations to an
individual's mood, and providing music recommendations with
diversity in popularity.
ContributorsGomez, Luis Angel (Author) / Kevin, Burger (Thesis director) / Alberto, Hernández (Committee member) / Arts, Media and Engineering Sch T (Contributor) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2020-05
Description
In shotgun proteomics, liquid chromatography coupled to tandem mass spectrometry
(LC-MS/MS) is used to identify and quantify peptides and proteins. LC-MS/MS produces mass spectra, which must be searched by one or more engines, which employ
algorithms to match spectra to theoretical spectra derived from a reference database.
These engines identify and characterize proteins and their component peptides. By
training a convolutional neural network on a dataset of over 6 million MS/MS spectra
derived from human proteins, we aim to create a tool that can quickly and effectively
identify spectra as peptides prior to database searching. This can significantly reduce search space and thus run time for database searches, thereby accelerating LCMS/MS-based proteomics data acquisition. Additionally, by training neural networks
on labels derived from the search results of three different database search engines, we
aim to examine and compare which features are best identified by individual search
engines, a neural network, or a combination of these.
(LC-MS/MS) is used to identify and quantify peptides and proteins. LC-MS/MS produces mass spectra, which must be searched by one or more engines, which employ
algorithms to match spectra to theoretical spectra derived from a reference database.
These engines identify and characterize proteins and their component peptides. By
training a convolutional neural network on a dataset of over 6 million MS/MS spectra
derived from human proteins, we aim to create a tool that can quickly and effectively
identify spectra as peptides prior to database searching. This can significantly reduce search space and thus run time for database searches, thereby accelerating LCMS/MS-based proteomics data acquisition. Additionally, by training neural networks
on labels derived from the search results of three different database search engines, we
aim to examine and compare which features are best identified by individual search
engines, a neural network, or a combination of these.
ContributorsWhyte, Cameron Stafford (Author) / Suren, Jayasuriya (Thesis director) / Gil, Speyer (Committee member) / Patrick, Pirrotte (Committee member) / School of Mathematical and Statistical Sciences (Contributor, Contributor) / Barrett, The Honors College (Contributor)
Created2020-05
Description
In recent years, the development of new Machine Learning models has allowed for new technological advancements to be introduced for practical use across the world. Multiple studies and experiments have been conducted to create new variations of Machine Learning models with different algorithms to determine if potential systems would prove to be successful. Even today, there are still many research initiatives that are continuing to develop new models in the hopes to discover potential solutions for problems such as autonomous driving or determining the emotional value from a single sentence. One of the current popular research topics for Machine Learning is the development of Facial Expression Recognition systems. These Machine Learning models focus on classifying images of human faces that are expressing different emotions through facial expressions. In order to develop effective models to perform Facial Expression Recognition, researchers have gone on to utilize Deep Learning models, which are a more advanced implementation of Machine Learning models, known as Neural Networks. More specifically, the use of Convolutional Neural Networks has proven to be the most effective models for achieving highly accurate results at classifying images of various facial expressions. Convolutional Neural Networks are Deep Learning models that are capable of processing visual data, such as images and videos, and can be used to identify various facial expressions. The purpose of this project, I focused on learning about the important concepts of Machine Learning, Deep Learning, and Convolutional Neural Networks to implement a Convolutional Neural Network that was previously developed by a recommended research paper.
ContributorsFrace, Douglas R (Author) / Demakethepalli Venkateswara, Hemanth Kumar (Thesis director) / McDaniel, Troy (Committee member) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2020-05
Description
This paper examines the fundamental problem statement of: How can the hotel & resort industry resist and overcome the new competitive challenge that the sharing economy and Airbnb have imposed on it? This wasn’t a problem up until this past decade, as hotels had long been the world’s main solution for individuals looking for a place to stay in exchange for a fee. That has changed nowadays as the rise of the sharing economy has created a new, fast-growing demand for Airbnb in the hospitality industry. We have witnessed powerful companies die as a result of not taking disruptive technology seriously, as seen with Blockbuster and Kodak; however, we have also seen impressive reactions to disruptive technology in other cases such as Walmart and Alibaba that use it to enhance the customer experience. Hotels arose from humble beginnings and progressively became more than just a place to sleep. This is evidenced by the progression from 16th century humble inns to large luxury hotels in the 19-20th century to many hotels being significant tourist attractions themselves nowadays. While some factors such as security, hygiene, and consistency currently remain on the hotel industry’s side, the main factors fueling the growth of Airbnb are closely tied to consumer preferences and Airbnb’s ability to create unique, authentic experiences. A questionnaire with 756 responses from ASU students was conducted for this project’s primary research. The results concluded that this demographic travels often, slightly prefers hotels over Airbnb, and values location, convenience, and cost the most. Results were consistent with findings discussed in literature, since the bulk of respondents said they look at Airbnb for low-cost options and hotels for high-end options. Hotels reign supreme in the high-end market and benefit from their location and convenience factors, but Airbnb might have an opportunity to leverage their attractive capabilities while also incorporating some of hotels’ best aspects. This can cause the preference of hotels over Airbnb to diminish further going forward. Hotels can combat Airbnb in multiple ways. One is for hotel chains to customize more hotels to fit the local destination like Airbnb rather than keeping a more standardized vibe and design across all locations. Another is to continue focusing on creating unmatched service experiences in the high-end market that are hard for Airbnb to replicate. A third one is to implement more competitive pricing relative to Airbnb during peak seasons across different cities. Finally, given the increased awareness on hygiene and health that the COVID-19 crisis will likely bring after the pandemic, hotels should put greater emphasis on their hygiene factor when conducting publicity efforts, since this remains in favor of hotels rather than Airbnb and can attract customers who are still reeling with fear from the pandemic. All of this can help hotels to retain their crucial competencies while leveraging Airbnb’s competencies to create an incredible customer experience that is the best of both worlds. All of it prevent the hotel industry from going down a darker path than it has gone through before.
ContributorsValenzuela Gallardo, Juan (Author) / Eaton, John (Thesis director) / Mokwa, Michael (Committee member) / Department of Management and Entrepreneurship (Contributor) / Department of Marketing (Contributor) / Barrett, The Honors College (Contributor)
Created2020-05
Description
Less than a full year ago, Cronkite News at ASU’s Walter Cronkite School launched ‘Cronkite News to Go’ (CN2GO). An innovative new way to deliver news content to those in Arizona, and across the country. This Barrett, Creative Project, focuses on the Best Practices for how to build a CN2GO Flash Briefing from start to finish. The booklet inclusion incorporates a number of step-by-step checklists for creating audio content, with the hope that it's something any Cronkite News reporter would be able to pick-up and learn from. This booklet also addresses the importance of CN2GO. It describes how these audio briefings are a great example of innovation, as well as a fantastic learning tool for future audio reporters.
This project also discusses possible solutions for how to maintain CN2GO long into the future. As old students graduate, and new ones join the team, this project will need to be sustained. The presentation portion of this Creative Project describes a number of potential improvements that could possibly be made to CN2GO, in order to better the entire process. These improvements are suggestions compiled from the personal experiences of student journalists tasked with creating CN2GO’s weekly. The presentation also includes a section devoted to how Cronkite News’ Flash Briefings can be continued over breaks in the school year. Spring breaks, Winter breaks, holidays, for example. These suggestions were made drawing from experimentation that was done with the CN2GO format in collaboration with this project.
The central purpose for this project was to take an existing idea and see how it can be prolonged and sustained far into the future. It can be used as an evolving learning tool for many iterations of Cronkite News reporters and producers to come.
This project also discusses possible solutions for how to maintain CN2GO long into the future. As old students graduate, and new ones join the team, this project will need to be sustained. The presentation portion of this Creative Project describes a number of potential improvements that could possibly be made to CN2GO, in order to better the entire process. These improvements are suggestions compiled from the personal experiences of student journalists tasked with creating CN2GO’s weekly. The presentation also includes a section devoted to how Cronkite News’ Flash Briefings can be continued over breaks in the school year. Spring breaks, Winter breaks, holidays, for example. These suggestions were made drawing from experimentation that was done with the CN2GO format in collaboration with this project.
The central purpose for this project was to take an existing idea and see how it can be prolonged and sustained far into the future. It can be used as an evolving learning tool for many iterations of Cronkite News reporters and producers to come.
ContributorsHrkal, Jonathan Jonah (Author) / Babits, Sadie (Thesis director) / Alam, Adnan (Committee member) / School of Politics and Global Studies (Contributor) / Walter Cronkite School of Journalism & Mass Comm (Contributor) / Barrett, The Honors College (Contributor)
Created2020-05
Description
Barrett Honors Thesis
Abstract
Noah Zweiback
The 21st century has brought significant changes to American consumers through technological advancements, social medias, and changing public sentiments. The sport industry in particular has been largely unable to capitalize on these changes due to the traditional nature of sports.
Keyball™ is the new 21st century sport specifically designed to have the greatest spectator appeal in this modern age. With focus on athleticism, parity, theatrical/emotional engagements, and community impact, Keyball™ aims to create a fan experience that is not achievable by other professional sports leagues. By design, there is high skillset carryover from other sports, ensuring tremendous talent will always be available, and fans of many different sports will find Keyball™ attractive to watch and follow.
The professional sports industry has been dominated by only a few players for the past century. Due to the traditional nature of sports, innovation is hard to implement in professional leagues. Tackle football is A. incredibly dangerous, causing broken bones, torn ligaments and tendons, and serious brain damage (concussions, CTE) at high rates. B. Football is low scoring and C. the pace of play is very slow. Basketball by nature A. overwhelmingly rewards height or verticality. It also B. lacks physicality and C. parity (NBA level). D. The foul system is flawed and easily exploited, dampening the end of games.
Keyball™ is positioned to A. be much more violent than basketball/soccer/baseball, while being significantly safer than tackle football. In addition, B. the speed of play is much faster than football, similar to a soccer/basketball live play style. C. Keyball™ is high scoring (like basketball, unlike football and soccer) and features much more dynamic/exciting scoring opportunities than traditional team sports. Keyball™ D. unifies the highly entertaining skillsets of soccer players (foot skill) with basketball/football players (explosiveness & hand coordination). E. Keyball™ has inherent double meaning that alludes to gambling (Keyball™ Wager) yet still promotes charity, selflessness, and American values (capitalism, sportsmanship, teamwork).
Abstract
Noah Zweiback
The 21st century has brought significant changes to American consumers through technological advancements, social medias, and changing public sentiments. The sport industry in particular has been largely unable to capitalize on these changes due to the traditional nature of sports.
Keyball™ is the new 21st century sport specifically designed to have the greatest spectator appeal in this modern age. With focus on athleticism, parity, theatrical/emotional engagements, and community impact, Keyball™ aims to create a fan experience that is not achievable by other professional sports leagues. By design, there is high skillset carryover from other sports, ensuring tremendous talent will always be available, and fans of many different sports will find Keyball™ attractive to watch and follow.
The professional sports industry has been dominated by only a few players for the past century. Due to the traditional nature of sports, innovation is hard to implement in professional leagues. Tackle football is A. incredibly dangerous, causing broken bones, torn ligaments and tendons, and serious brain damage (concussions, CTE) at high rates. B. Football is low scoring and C. the pace of play is very slow. Basketball by nature A. overwhelmingly rewards height or verticality. It also B. lacks physicality and C. parity (NBA level). D. The foul system is flawed and easily exploited, dampening the end of games.
Keyball™ is positioned to A. be much more violent than basketball/soccer/baseball, while being significantly safer than tackle football. In addition, B. the speed of play is much faster than football, similar to a soccer/basketball live play style. C. Keyball™ is high scoring (like basketball, unlike football and soccer) and features much more dynamic/exciting scoring opportunities than traditional team sports. Keyball™ D. unifies the highly entertaining skillsets of soccer players (foot skill) with basketball/football players (explosiveness & hand coordination). E. Keyball™ has inherent double meaning that alludes to gambling (Keyball™ Wager) yet still promotes charity, selflessness, and American values (capitalism, sportsmanship, teamwork).
ContributorsZweiback, Noah B (Writer of accompanying material) / Denning, Michael (Thesis director) / Eaton, John (Committee member) / Department of Management and Entrepreneurship (Contributor) / Department of Finance (Contributor) / Barrett, The Honors College (Contributor)
Created2019-12
Description
Innovation Space is Arizona State University’s capstone style project in which upper division students gain real experience in the startup and product development world by solving real-world problems. These problems were presented to my team by sponsor; LG Electronics. Innovation Space uniquely offered an interdisciplinary glance into “real life” in the months before college graduation. Students are placed on teams with designers, engineers, sustainability majors, and business majors to better reflect the real world. As a business student of this program, I was able to gain and share knowledge from my teammates’ distinct backgrounds; as well as gain the interdisciplinary experience that is key to a college education, specifically to a business student. LG Electronics, our sponsor, brought our team the task of expanding their product line in their “wind comfort” business unit. LG Electronics has created a lighter, more efficient motor for a fan; likely as an answer to their dominating fan competitor, Dyson. LG Electronics wanted to see what our team could do to alter the way people cool their homes, and we responded with three original ideas: a modular, non-centralized A/C unit; a hands-free hair dryer; and a portable 360 degree fan. Our team developed the latter product, and named it Torus. The product was developed over the course of August 2018 to May 2019, ending in a working prototype formally presented to the sponsor and industry professionals. On top of this project, I was directed to also analyze the Innovation Space program for its benefits and drawbacks to a business degree from the W.P. Carey School of Business.
ContributorsSkogebo, Hannah Michelle (Author) / Trujillo, Rhett (Thesis director) / Hedges, Craig (Committee member) / Department of Information Systems (Contributor) / School of International Letters and Cultures (Contributor) / Barrett, The Honors College (Contributor)
Created2019-12