Matching Items (43)
Description
Graph theory is a critical component of computer science and software engineering, with algorithms concerning graph traversal and comprehension powering much of the largest problems in both industry and research. Engineers and researchers often have an accurate view of their target graph, however they struggle to implement a correct, and efficient, search over that graph.
To facilitate rapid, correct, efficient, and intuitive development of graph based solutions we propose a new programming language construct - the search statement. Given a supra-root node, a procedure which determines the children of a given parent node, and optional definitions of the fail-fast acceptance or rejection of a solution, the search statement can conduct a search over any graph or network. Structurally, this statement is modelled after the common switch statement and is put into a largely imperative/procedural context to allow for immediate and intuitive development by most programmers. The Go programming language has been used as a foundation and proof-of-concept of the search statement. A Go compiler is provided which implements this construct.
To facilitate rapid, correct, efficient, and intuitive development of graph based solutions we propose a new programming language construct - the search statement. Given a supra-root node, a procedure which determines the children of a given parent node, and optional definitions of the fail-fast acceptance or rejection of a solution, the search statement can conduct a search over any graph or network. Structurally, this statement is modelled after the common switch statement and is put into a largely imperative/procedural context to allow for immediate and intuitive development by most programmers. The Go programming language has been used as a foundation and proof-of-concept of the search statement. A Go compiler is provided which implements this construct.
ContributorsHenderson, Christopher (Author) / Bansal, Ajay (Thesis advisor) / Lindquist, Timothy (Committee member) / Acuna, Ruben (Committee member) / Arizona State University (Publisher)
Created2018
Description
UVLabel was created to enable radio astronomers to view and annotate their own data such that they could then expand their future research paths. It simplifies their data rendering process by providing a simple user interface to better access sections of their data. Furthermore, it provides an interface to track trends in their data through a labelling feature.
The tool was developed following the incremental development process in order to quickly create a functional and testable tool. The incremental process also allowed for feedback from radio astronomers to help guide the project's development.
UVLabel provides both a functional product, and a modifiable and scalable code base for radio astronomer developers. This enables astronomers studying various astronomical interferometric data labelling capabilities. The tool can then be used to improve their filtering methods, pursue machine learning solutions, and discover new trends. Finally, UVLabel will be open source to put customization, scalability, and adaptability in the hands of these researchers.
The tool was developed following the incremental development process in order to quickly create a functional and testable tool. The incremental process also allowed for feedback from radio astronomers to help guide the project's development.
UVLabel provides both a functional product, and a modifiable and scalable code base for radio astronomer developers. This enables astronomers studying various astronomical interferometric data labelling capabilities. The tool can then be used to improve their filtering methods, pursue machine learning solutions, and discover new trends. Finally, UVLabel will be open source to put customization, scalability, and adaptability in the hands of these researchers.
ContributorsLa Place, Cecilia (Author) / Bansal, Ajay (Thesis advisor) / Jacobs, Daniel (Thesis advisor) / Acuna, Ruben (Committee member) / Arizona State University (Publisher)
Created2019
Description
Capturing the information in an image into a natural language sentence is
considered a difficult problem to be solved by computers. Image captioning involves not just detecting objects from images but understanding the interactions between the objects to be translated into relevant captions. So, expertise in the fields of computer vision paired with natural language processing are supposed to be crucial for this purpose. The sequence to sequence modelling strategy of deep neural networks is the traditional approach to generate a sequential list of words which are combined to represent the image. But these models suffer from the problem of high variance by not being able to generalize well on the training data.
The main focus of this thesis is to reduce the variance factor which will help in generating better captions. To achieve this, Ensemble Learning techniques have been explored, which have the reputation of solving the high variance problem that occurs in machine learning algorithms. Three different ensemble techniques namely, k-fold ensemble, bootstrap aggregation ensemble and boosting ensemble have been evaluated in this thesis. For each of these techniques, three output combination approaches have been analyzed. Extensive experiments have been conducted on the Flickr8k dataset which has a collection of 8000 images and 5 different captions for every image. The bleu score performance metric, which is considered to be the standard for evaluating natural language processing (NLP) problems, is used to evaluate the predictions. Based on this metric, the analysis shows that ensemble learning performs significantly better and generates more meaningful captions compared to any of the individual models used.
considered a difficult problem to be solved by computers. Image captioning involves not just detecting objects from images but understanding the interactions between the objects to be translated into relevant captions. So, expertise in the fields of computer vision paired with natural language processing are supposed to be crucial for this purpose. The sequence to sequence modelling strategy of deep neural networks is the traditional approach to generate a sequential list of words which are combined to represent the image. But these models suffer from the problem of high variance by not being able to generalize well on the training data.
The main focus of this thesis is to reduce the variance factor which will help in generating better captions. To achieve this, Ensemble Learning techniques have been explored, which have the reputation of solving the high variance problem that occurs in machine learning algorithms. Three different ensemble techniques namely, k-fold ensemble, bootstrap aggregation ensemble and boosting ensemble have been evaluated in this thesis. For each of these techniques, three output combination approaches have been analyzed. Extensive experiments have been conducted on the Flickr8k dataset which has a collection of 8000 images and 5 different captions for every image. The bleu score performance metric, which is considered to be the standard for evaluating natural language processing (NLP) problems, is used to evaluate the predictions. Based on this metric, the analysis shows that ensemble learning performs significantly better and generates more meaningful captions compared to any of the individual models used.
ContributorsKatpally, Harshitha (Author) / Bansal, Ajay (Thesis advisor) / Acuna, Ruben (Committee member) / Gonzalez-Sanchez, Javier (Committee member) / Arizona State University (Publisher)
Created2019
Description
In this project, the use of deep neural networks for the process of selecting actions to execute within an environment to achieve a goal is explored. Scenarios like this are common in crafting based games such as Terraria or Minecraft. Goals in these environments have recursive sub-goal dependencies which form a dependency tree. An agent operating within these environments have access to low amounts of data about the environment before interacting with it, so it is crucial that this agent is able to effectively utilize a tree of dependencies and its environmental surroundings to make judgements about which sub-goals are most efficient to pursue at any point in time. A successful agent aims to minimizes cost when completing a given goal. A deep neural network in combination with Q-learning techniques was employed to act as the agent in this environment. This agent consistently performed better than agents using alternate models (models that used dependency tree heuristics or human-like approaches to make sub-goal oriented choices), with an average performance advantage of 33.86% (with a standard deviation of 14.69%) over the best alternate agent. This shows that machine learning techniques can be consistently employed to make goal-oriented choices within an environment with recursive sub-goal dependencies and low amounts of pre-known information.
ContributorsKoleber, Derek (Author) / Acuna, Ruben (Thesis director) / Bansal, Ajay (Committee member) / W.P. Carey School of Business (Contributor) / Software Engineering (Contributor) / Barrett, The Honors College (Contributor)
Created2018-05
Description
Young adults do not know basic emergency preparedness skills. Although there are materials out there such as printed and online materials form Center for Disease Control, it is unlikely that college-age people will take the time to read them. Some individuals have addressed the issue of young adults not wanting to read materials by creating a fun interactive game in the San Francisco area, but since the game must be played in person, a solution like that can only reach so far. Studies suggest that virtual worlds are effective in teaching people new skills, so I have created a virtual world that will teach people basic emergency preparedness skills in a way that is memorable and appealing to a college-age audience. The logic used to teach players the concepts of emergency preparedness is case-based reasoning. Case-based reasoning is the process of solving new problems by remembering similar solutions in the past. By creating a simulation emergency situation in a virtual world, young adults are more likely to know what to do in the case of an actual emergency.
ContributorsTeplik, Julie Rachel (Author) / Craig, Scotty (Thesis director) / Amresh, Ashish (Committee member) / WPC Graduate Programs (Contributor) / Software Engineering (Contributor) / Barrett, The Honors College (Contributor)
Created2017-05
Description
As robotics technology advances, robots are being created for use in situations where they collaborate with humans on complex tasks. For this to be safe and successful, it is important to understand what causes humans to trust robots more or less during a collaborative task. This research project aims to investigate human-robot trust through a collaborative game of logic that can be played with a human and a robot together. This thesis details the development of a game of logic that could be used for this purpose. The game of logic is based upon a popular game in AI research called ‘Wumpus World’. The original Wumpus World game was a low-interactivity game to be played by humans alone. In this project, the Wumpus World game is modified for a high degree of interactivity with a human player, while also allowing the game to be played simultaneously by an AI algorithm.
ContributorsBoateng, Andrew Owusu (Author) / Sodemann, Angela (Thesis director) / Martin, Thomas (Committee member) / Software Engineering (Contributor) / Engineering Programs (Contributor) / Barrett, The Honors College (Contributor)
Created2018-05
Description
Effective communication and engineering are not a natural pairing. The incongruence is because engineering students are focused on making, designing and analyzing. Since these are the core functions of the field there is not a direct focus on developing communication skills. This honors thesis explores the role and expectations for student engineers within the undergraduate engineering education experience to present and communicate ideas. The researchers interviewed faculty about their perspective on students' abilities with respect to their presentation skills to inform the design of a workshop series of interventions intended to make engineering students better communicators.
ContributorsAlbin, Joshua Alexander (Co-author) / Brancati, Sara (Co-author) / Lande, Micah (Thesis director) / Martin, Thomas (Committee member) / Industrial, Systems and Operations Engineering Program (Contributor) / Software Engineering (Contributor) / Barrett, The Honors College (Contributor)
Created2018-05
Description
Optical Communications are at a high point of interest by the space engineering community. After successful projects like the Lunar Laser Communications Demonstration (LLCD), NASA has become interested in augmenting their current Deep Space Network (DSN) with optical communication links. One such link is Deep Space Optical Communications (DSOC) which will be launching with the Psyche mission. To gain a full understanding of the advantages of this network, this thesis will go over the history and benefits of optical communications both on Earth and in space. This thesis will then go in depth on NASAs DSOC project through an algorithmic implementation of the communications channel.
ContributorsHorton, Paul Alexander (Author) / Mauskopf, Philip (Thesis director) / Sandy, Douglas (Committee member) / Martin, Thomas (Committee member) / Software Engineering (Contributor) / College of Integrative Sciences and Arts (Contributor) / Barrett, The Honors College (Contributor)
Created2018-05
Description
Class instructors at Arizona State University monitor students’ attendance for classes in which attendance is either mandatory or encouraged. Class monitoring can be done using traditional systems such as sign sheets and roll calls. From my initial observations while attending a class which utilized a sign sheet for class attendance monitoring, I thought the process took long and was inefficient. As a result, I created an automated system that would replace the traditional systems and improve the class monitoring process. Thus, this study aims to determine whether the automated system reduced the time it takes to monitor class attendance, and whether it was efficient.
To examine the above question, the automated system was deployed to 2 classes at Arizona State University. Additionally, surveys were distributed to 2 instructors and 33 students and they were asked to respond to questions relating to class attendance and the monitoring systems which were being used alternatively with the newly-created automated system. Analysis of the responses demonstrated that use of an automated system reduced the time it takes students to mark their presence, and thus increase the time used for other class activities. The results also indicate that the design of the automated system affects the overall time it takes to monitor attendance. On this basis, it is recommended that instructors utilize an automated system to monitor class attendance. Further research is needed to study the time it takes instructors to set up different monitoring systems in order to ascertain that an automated system reduces the overall time it takes to monitor attendance compared to other traditionally used systems.
ContributorsCyubahiro, Tresor (Author) / Heinrichs, Robert (Thesis director) / Mehlhase, Alexandra (Committee member) / Software Engineering (Contributor) / Barrett, The Honors College (Contributor)
Created2019-05
Description
The spread of fake news (rumors) has been a growing problem on the internet in the past few years due to the increase of social media services. People share fake news articles on social media sometimes without knowing that those articles contain false information. Not knowing whether an article is fake or real is a problem because it causes social media news to lose credibility. Prior research on fake news has focused on how to detect fake news, but efforts towards controlling fake news articles on the internet are still facing challenges. Some of these challenges include; it is hard to collect large sets of fake news data, it is hard to collect locations of people who are spreading fake news, and it is difficult to study the geographic distribution of fake news. To address these challenges, I am examining how fake news spreads in the United States (US) by developing a geographic visualization system for misinformation. I am collecting a set of fake news articles from a website called snopes.com. After collecting these articles I am extracting the keywords from each article and storing them in a file. I then use the stored keywords to search on Twitter in order to find out the locations of users who spread the rumors. Finally, I mark those locations on a map in order to show the geographic distribution of fake news. Having access to large sets of fake news data, knowing the locations of people who are spreading fake news, and being able to understand the geographic distribution of fake news will help in the efforts towards addressing the fake news problem on the internet by providing target areas.
ContributorsNgweta, Lilian Mathias (Author) / Liu, Huan (Thesis director) / Wu, Liang (Committee member) / Software Engineering (Contributor) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2018-05