Matching Items (159)
Description
Video games often feature agents that the human player interacts with to overcome.
Designing these agents to cover every case of human interaction is difficult, and usually
imperfect, as human players are capable of learning to overcome these agents in unintended
ways. Artificial intelligence is a growing field that seeks to solve problems by simulating
learning in specific environments. The aim of this paper is to explore the applications that the
self play learning branch of artificial intelligence may pose on game development in the future,
and to attempt to implement a working version of a self play agent learning to play a Pokemon
battle. Originally designed Pokemon battle behavior is often suboptimal, getting stuck making
ineffective or incorrect choices, so training a self play model to learn the strategy and structure of
Pokemon battles from a clean slate would result in an organic agent that would outperform the
original behavior of the computer controlled agents. Though unsuccessful in my implementation,
this paper serves as a record of the exploration of this field, and a log of what worked and what
did not, in order to benefit any future person interested in the same topics.
Designing these agents to cover every case of human interaction is difficult, and usually
imperfect, as human players are capable of learning to overcome these agents in unintended
ways. Artificial intelligence is a growing field that seeks to solve problems by simulating
learning in specific environments. The aim of this paper is to explore the applications that the
self play learning branch of artificial intelligence may pose on game development in the future,
and to attempt to implement a working version of a self play agent learning to play a Pokemon
battle. Originally designed Pokemon battle behavior is often suboptimal, getting stuck making
ineffective or incorrect choices, so training a self play model to learn the strategy and structure of
Pokemon battles from a clean slate would result in an organic agent that would outperform the
original behavior of the computer controlled agents. Though unsuccessful in my implementation,
this paper serves as a record of the exploration of this field, and a log of what worked and what
did not, in order to benefit any future person interested in the same topics.
ContributorsCiudad, Erick Marcel (Author) / Meuth, Ryan (Thesis director) / Kobayashi, Yoshihiro (Committee member) / Computing and Informatics Program (Contributor) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2020-12
Description
Behavioral economics suggests that emotions can affect an individual’s decision making. Recent research on this idea’s application on large societies hints that there may exist some correlation or maybe even some causation relationship between public sentiment—at least what can be pulled from Twitter—and the movement of the stock market. One major result of consistent research on whether or not public sentiment can predict the movement of the stock market is that public sentiment, as a feature, is becoming more and more valid as a variable for stock-market-based machine learning models. While raw values typically serve as invaluable points of data, when training a model, many choose to “engineer” new features for their models—deriving rates of change or range values to improve model accuracy.
Since it doesn’t hurt to attempt to utilize feature extracted values to improve a model (if things don’t work out, one can always use their original features), the question may arise: how could the results of feature extraction on values such as sentiment affect a model’s ability to predict the movement of the stock market? This paper attempts to shine some light on to what the answer could be by deriving TextBlob sentiment values from Twitter data, and using Granger Causality Tests and logistic and linear regression to test if there exist a correlation or causation between the stock market and features extracted from public sentiment.
Since it doesn’t hurt to attempt to utilize feature extracted values to improve a model (if things don’t work out, one can always use their original features), the question may arise: how could the results of feature extraction on values such as sentiment affect a model’s ability to predict the movement of the stock market? This paper attempts to shine some light on to what the answer could be by deriving TextBlob sentiment values from Twitter data, and using Granger Causality Tests and logistic and linear regression to test if there exist a correlation or causation between the stock market and features extracted from public sentiment.
ContributorsYu, James (Author) / Meuth, Ryan (Thesis director) / Nakamura, Mutsumi (Committee member) / Computer Science and Engineering Program (Contributor, Contributor) / Barrett, The Honors College (Contributor)
Created2020-05
Description
The goal of our research is to highlight the reality of criminal justice professionals’ roles. We interviewed six criminal justice professionals from three different fields within the criminal justice profession. The professions we focused on included judges, lawyers and police officers. During each interview we showed the professionals a series of video clips from popular movies and television shows that portrayed individuals in their field. At the conclusion of each video, we asked the professionals to point out the realistic and overexaggerated aspects in the videos. Towards the very end of the interviews, we asked each professional a series of questions that corresponded with their specific field (See Appendix A). We received a lot of insight on what their jobs truly entail.
We gathered qualitative data on criminal justice professionals because we wanted to debunk myths associated with their professions. Professions within the criminal justice field can be extremely dangerous and even life-threatening, therefore it is important that individuals looking to enter these professions are well-informed. With technology improving daily, more and more people have easy access to social media, news, and television shows. Some people rely solely on these platforms to receive information. Another key reason we chose qualitative methods is because we wanted our information to be applicable for criminal justice professionals themselves. Maureen McGough from the National Institute of Justice describes that for police officers, policy related research tends to be geared towards academics (McGough, 2019). We used qualitative methods to provide more actionable and relatable feedback. However, these platforms do not always reveal the full story. Our research reveals how television shows and movies are not always accurate in portraying the roles of criminal justice professionals.
Our findings revealed that there are both realistic and overexaggerated aspects in the portrayal of criminal justice professionals in television shows and movies. Some of the overexaggerated aspects include how nearly all the television shows and movies only captured action parts of criminal justice professionals’ roles. Which creates the illusion that these roles are all about action and never have dull moments. None of the scenes captured the research and paperwork that goes along with being a criminal justice professional. On the other hand, there were some aspects of television shows and movies that the professionals found realistic. These aspects include the unusual humor police officers use to cope with the pressures of their job and the tactics lawyers use to sway a jury.
Aside from the information we received about what was real and overexaggerated in television shows and movies, we also identified some of the aspects of criminal justice roles that are omitted from television shows and movies. The professionals we interviewed also shared some of the rewarding and fulfilling aspects of their roles that are often overlooked or just unknown to the public. With the valuable information we gathered from our thesis project, we created a website (See Appendix B). The website includes profiles on the criminal justice professionals we interviewed and a summary of our findings. The purpose of this website is to reach a larger audience, so that we can inform more people about the reality of criminal justice professionals’ roles. Individuals can use our website to learn more about what the role of a criminal justice professional entails and how to prepare.
We gathered qualitative data on criminal justice professionals because we wanted to debunk myths associated with their professions. Professions within the criminal justice field can be extremely dangerous and even life-threatening, therefore it is important that individuals looking to enter these professions are well-informed. With technology improving daily, more and more people have easy access to social media, news, and television shows. Some people rely solely on these platforms to receive information. Another key reason we chose qualitative methods is because we wanted our information to be applicable for criminal justice professionals themselves. Maureen McGough from the National Institute of Justice describes that for police officers, policy related research tends to be geared towards academics (McGough, 2019). We used qualitative methods to provide more actionable and relatable feedback. However, these platforms do not always reveal the full story. Our research reveals how television shows and movies are not always accurate in portraying the roles of criminal justice professionals.
Our findings revealed that there are both realistic and overexaggerated aspects in the portrayal of criminal justice professionals in television shows and movies. Some of the overexaggerated aspects include how nearly all the television shows and movies only captured action parts of criminal justice professionals’ roles. Which creates the illusion that these roles are all about action and never have dull moments. None of the scenes captured the research and paperwork that goes along with being a criminal justice professional. On the other hand, there were some aspects of television shows and movies that the professionals found realistic. These aspects include the unusual humor police officers use to cope with the pressures of their job and the tactics lawyers use to sway a jury.
Aside from the information we received about what was real and overexaggerated in television shows and movies, we also identified some of the aspects of criminal justice roles that are omitted from television shows and movies. The professionals we interviewed also shared some of the rewarding and fulfilling aspects of their roles that are often overlooked or just unknown to the public. With the valuable information we gathered from our thesis project, we created a website (See Appendix B). The website includes profiles on the criminal justice professionals we interviewed and a summary of our findings. The purpose of this website is to reach a larger audience, so that we can inform more people about the reality of criminal justice professionals’ roles. Individuals can use our website to learn more about what the role of a criminal justice professional entails and how to prepare.
ContributorsLynch-Howell, Deja (Co-author) / Roldan, Joshua (Co-author) / DeCarolis, Claudine (Thesis director) / Robinson, Kevin (Committee member) / School of Criminology and Criminal Justice (Contributor) / Department of Information Systems (Contributor, Contributor) / Barrett, The Honors College (Contributor)
Created2019-05
Description
As modern advancements in medical technology continue to increase overall life expectancy, hospitals and healthcare systems are finding new and more efficient ways of storing extensive amounts of patient healthcare information. This progression finds people increasingly dependent on hospitals as the primary providers of medical data, ranging from immunization records to surgical history. However, the benefits of carrying a copy of personal health information are becoming increasingly evident. This project aims to create a simple, secure, and cohesive application that stores and retrieves user health information backed by Google’s Firebase cloud infrastructure. Data was collected to both explore the current need for such an application, and to test the usability of the product. The former was done using a multiple-choice survey distributed through social media to understand the necessity for a patient-held health file (PHF). Subsequently, user testing was performed with the intent to track the success of our application in meeting those needs. According to the data, there was a trend that suggested a significant need for a healthcare information storage device. This application, allowing for efficient and simple medical information storage and retrieval, was created for a target audience of those seeking to improve their medical information awareness, with a primary focus on the elderly population. Specific correlations between the frequency of physician visits and app usage were identified to target the potential use cases of our app. The outcome of this project succeeded in meeting the significant need for increased patient medical awareness in the healthcare community.
ContributorsUpponi, Rohan Sachin (Co-author) / Somayaji, Vasishta (Co-author) / McDaniel, Troy (Thesis director) / Meuth, Ryan (Committee member) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2019-05
Description
A common design of multi-agent robotic systems requires a centralized master node, which coordinates the actions of all the agents. The multi-agent system designed in this project enables coordination between the robots and reduces the dependence on a single node in the system. This design change reduces the complexity of the central node, and makes the system more adaptable to changes in its topology. The final goal of this project was to have a group of robots collaboratively claim positions in pre-defined formations, and navigate to the position using pose data transmitted by a localization server.
Planning coordination between robots in a multi-agent system requires each robot to know the position of the other robots. To address this, the localization server tracked visual fiducial markers attached to the robots and relayed their pose to every robot at a rate of 20Hz using the MQTT communication protocol. The robots used this data to inform a potential fields path planning algorithm and navigate to their target position.
This project was unable to address all of the challenges facing true distributed multi-agent coordination and needed to make concessions in order to meet deadlines. Further research would focus on shoring up these deficiencies and developing a more robust system.
Planning coordination between robots in a multi-agent system requires each robot to know the position of the other robots. To address this, the localization server tracked visual fiducial markers attached to the robots and relayed their pose to every robot at a rate of 20Hz using the MQTT communication protocol. The robots used this data to inform a potential fields path planning algorithm and navigate to their target position.
This project was unable to address all of the challenges facing true distributed multi-agent coordination and needed to make concessions in order to meet deadlines. Further research would focus on shoring up these deficiencies and developing a more robust system.
ContributorsThibeault, Quinn (Author) / Meuth, Ryan (Thesis director) / Chen, Yinong (Committee member) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2019-05
Description
For our creative project, we initially wanted to work on a web application that would allow people with busy schedules to easily create and share events while also discovering other events that may interest them. With that in mind, we created the Group Event Planner App, a full stack project that lays down a foundation for all of our goals while focusing primarily on the proposed recommendation algorithms that enable its users to discover events that are likely to pique their interest. The development of our recommendation algorithms took inspiration from existing implementations, such as those at Amazon, YouTube, and Netflix, and resulted in a creative amalgamation.
ContributorsRussell, Preston (Co-author) / Sonnier, Connor (Co-author) / Chen, Yinong (Thesis director) / Meuth, Ryan (Committee member) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2020-05
Description
One of the major sources of authentication is through the use of username and password systems. Ideally, each password is a unique identifier known by a single individual. In reality however, exposed passwords from past data breaches reveal vulnerabilities that are traceable to passwords created today. Vulnerabilities include repetitions of characters, words, character sequences, and phrases that are used in a password. This project was observed in English to highlight the vulnerabilities that can come from utilizing the English language. However, the vulnerabilities highlighted in this project can also be applicable in languages across the world. It was observed that through the common types of digital attacks, brute force attack and dictionary attack work effectively against weak passwords. Brute force attack revealed that a user could expose an alphanumeric password of length eight in as little as one and a half days. In addition, dictionary attacks revealed that an alphanumeric password of length eight can be exposed in a shorter amount of time if the password contains a single long word or phrase thought to be secure. During this attack analysis, it found that passwords become significantly more secure in the utilization of alphanumeric passwords of minimal length of eight. In addition, the password must also not be a particular phrase or word with simplistic characteristics for adequate strength against dictionary attack. The solution to using username and password systems is to create a password utilizing as many characters as possible while still retaining memorability. If creating a password of this type is not feasible, there is a need to use technological solutions to keep the current system of username and passwords as secure as possible under daily life. Otherwise, there will be a need to replace the username and password system altogether before it becomes insecure by technology.
ContributorsTipton, Tony T (Co-author) / Tipton, Tony (Co-author) / Meuth, Ryan (Thesis director) / Tirupalavanam, Ganesh (Committee member) / Computer Science and Engineering Program (Contributor, Contributor) / Barrett, The Honors College (Contributor)
Created2020-05
Description
Immunotherapy is an effective treatment for cancer which enables the patient's immune system to recognize tumor cells as pathogens. In order to design an individualized treatment, the t cell receptors (TCR) which bind to a tumor's unique antigens need to be determined. We created a convolutional neural network to predict the binding affinity between a given TCR and antigen to enable this.
ContributorsCai, Michael Ray (Author) / Lee, Heewook (Thesis director) / Meuth, Ryan (Committee member) / Computer Science and Engineering Program (Contributor, Contributor) / Barrett, The Honors College (Contributor)
Created2020-12
Description
The original version of Helix, the one I pitched when first deciding to make a video game
for my thesis, is an action-platformer, with the intent of metroidvania-style progression
and an interconnected world map.
The current version of Helix is a turn based role-playing game, with the intent of roguelike
gameplay and a dark fantasy theme. We will first be exploring the challenges that came
with programming my own game - not quite from scratch, but also without a prebuilt
engine - then transition into game design and how Helix has evolved from its original form
to what we see today.
for my thesis, is an action-platformer, with the intent of metroidvania-style progression
and an interconnected world map.
The current version of Helix is a turn based role-playing game, with the intent of roguelike
gameplay and a dark fantasy theme. We will first be exploring the challenges that came
with programming my own game - not quite from scratch, but also without a prebuilt
engine - then transition into game design and how Helix has evolved from its original form
to what we see today.
ContributorsDiscipulo, Isaiah K (Author) / Meuth, Ryan (Thesis director) / Kobayashi, Yoshihiro (Committee member) / School of Mathematical and Statistical Sciences (Contributor) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2020-05
Description
RecyclePlus is an iOS mobile application that allows users to be knowledgeable in the realms of sustainability. It gives encourages users to be environmental responsible by providing them access to recycling information. In particular, it allows users to search up certain materials and learn about its recyclability and how to properly dispose of the material. Some searches will show locations of facilities near users that collect certain materials and dispose of the materials properly. This is a full stack software project that explores open source software and APIs, UI/UX design, and iOS development.
ContributorsTran, Nikki (Author) / Ganesh, Tirupalavanam (Thesis director) / Meuth, Ryan (Committee member) / Watts College of Public Service & Community Solut (Contributor) / Department of Information Systems (Contributor) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2020-05