Matching Items (125)
Filtering by
- Creators: Barrett, The Honors College
Description
Developed a business product with a team of CS students.
ContributorsPerri, Cole Thomas (Co-author) / Hernandez, Maximilliano (Co-author) / Schneider, Kaitlin (Co-author) / Call, Andy (Thesis director) / Hunt, Neil (Committee member) / School of Accountancy (Contributor) / Watts College of Public Service & Community Solut (Contributor) / WPC Graduate Programs (Contributor) / Barrett, The Honors College (Contributor)
Created2021-05
Description
Multi-task learning (MTL) aims to improve the generalization performance (of the resulting classifiers) by learning multiple related tasks simultaneously. Specifically, MTL exploits the intrinsic task relatedness, based on which the informative domain knowledge from each task can be shared across multiple tasks and thus facilitate the individual task learning. It is particularly desirable to share the domain knowledge (among the tasks) when there are a number of related tasks but only limited training data is available for each task. Modeling the relationship of multiple tasks is critical to the generalization performance of the MTL algorithms. In this dissertation, I propose a series of MTL approaches which assume that multiple tasks are intrinsically related via a shared low-dimensional feature space. The proposed MTL approaches are developed to deal with different scenarios and settings; they are respectively formulated as mathematical optimization problems of minimizing the empirical loss regularized by different structures. For all proposed MTL formulations, I develop the associated optimization algorithms to find their globally optimal solution efficiently. I also conduct theoretical analysis for certain MTL approaches by deriving the globally optimal solution recovery condition and the performance bound. To demonstrate the practical performance, I apply the proposed MTL approaches on different real-world applications: (1) Automated annotation of the Drosophila gene expression pattern images; (2) Categorization of the Yahoo web pages. Our experimental results demonstrate the efficiency and effectiveness of the proposed algorithms.
ContributorsChen, Jianhui (Author) / Ye, Jieping (Thesis advisor) / Kumar, Sudhir (Committee member) / Liu, Huan (Committee member) / Xue, Guoliang (Committee member) / Arizona State University (Publisher)
Created2011
Description
Sparsity has become an important modeling tool in areas such as genetics, signal and audio processing, medical image processing, etc. Via the penalization of l-1 norm based regularization, the structured sparse learning algorithms can produce highly accurate models while imposing various predefined structures on the data, such as feature groups or graphs. In this thesis, I first propose to solve a sparse learning model with a general group structure, where the predefined groups may overlap with each other. Then, I present three real world applications which can benefit from the group structured sparse learning technique. In the first application, I study the Alzheimer's Disease diagnosis problem using multi-modality neuroimaging data. In this dataset, not every subject has all data sources available, exhibiting an unique and challenging block-wise missing pattern. In the second application, I study the automatic annotation and retrieval of fruit-fly gene expression pattern images. Combined with the spatial information, sparse learning techniques can be used to construct effective representation of the expression images. In the third application, I present a new computational approach to annotate developmental stage for Drosophila embryos in the gene expression images. In addition, it provides a stage score that enables one to more finely annotate each embryo so that they are divided into early and late periods of development within standard stage demarcations. Stage scores help us to illuminate global gene activities and changes much better, and more refined stage annotations improve our ability to better interpret results when expression pattern matches are discovered between genes.
ContributorsYuan, Lei (Author) / Ye, Jieping (Thesis advisor) / Wang, Yalin (Committee member) / Xue, Guoliang (Committee member) / Kumar, Sudhir (Committee member) / Arizona State University (Publisher)
Created2013
Description
This project explores how modern mobile technology can be used to provide support for domestic violence victims. The goal of the project is to create a proof-of-concept iOS mobile application that maintains a discreet safety front and provides domestic violence victims with resources and safety planning. The design and implementation are disguised as a hair salon app to maintain a low profile on the user’s phone. The HairHelp app features quick exit navigation, a secure database to store a user’s private and personal documents in case of emergency, and a checklist of safety planning measures. The steps taken in this project serve as the foundation for a larger project in the long term.
ContributorsShovkovy, Sophia (Author) / Balasooriya, Janaka (Thesis director) / Wilkey, Douglas (Committee member) / Computer Science and Engineering Program (Contributor, Contributor) / Barrett, The Honors College (Contributor)
Created2021-05
Description
HackerHero is an educational game designed to teach children, especially those from marginalized backgrounds, computation thinking skills needed for STEAM fields. It also teaches children about social injustice. This project was focused on creating an audio visualization for an AI character within the HackerHero game. The audio visualization consisted of a static silhouette of a face and a wave-like form to represent the mouth. Audio content analysis was performed on audio sampled from the character’s voice lines. Pitch and amplitude derived from the analysis was used to animate the character’s visual features such as it’s brightness, color, and mouth movement. The mouth’s movement and color was manipulated with the audio’s pitch. The lights of Wave were controlled by the amplitude of the audio. Design considerations were made to accommodate those with visual disabilities such as color blindness and epilepsy. Overall the final audio visualization satisfied the project sponsor and built upon existing audio visualization work. User feedback will be a necessity for improving the audio visualization in the future.
ContributorsNguyen, Joshep D (Author) / Chavez-Echaegaray, Helen (Thesis director) / Waggoner, Trae (Committee member) / Department of Psychology (Contributor) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2021-05
Description
A primary goal in computer science is to develop autonomous systems. Usually, we provide computers with tasks and rules for completing those tasks, but what if we could extend this type of system to physical technology as well? In the field of programmable matter, researchers are tasked with developing synthetic materials that can change their physical properties \u2014 such as color, density, and even shape \u2014 based on predefined rules or continuous, autonomous collection of input. In this research, we are most interested in particles that can perform computations, bond with other particles, and move. In this paper, we provide a theoretical particle model that can be used to simulate the performance of such physical particle systems, as well as an algorithm to perform expansion, wherein these particles can be used to enclose spaces or even objects.
ContributorsLaff, Miles (Author) / Richa, Andrea (Thesis director) / Bazzi, Rida (Committee member) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor) / School of Mathematical and Statistical Sciences (Contributor)
Created2015-05
Description
Investment real estate is unique among similar financial instruments by nature of each property's internal complexities and interaction with the external economy. Where a majority of tradable assets are static goods within a dynamic market, real estate investments are dynamic goods within a dynamic market. Furthermore, investment real estate, particularly commercial properties, not only interacts with the surrounding economy, it reflects it. Alive with tenancy, each and every commercial investment property provides a microeconomic view of businesses that make up the local economy. Management of commercial investment real estate captures this economic snapshot in a unique abundance of untapped statistical data. While analysis of such data is undeniably valuable, the efforts involved with this process are time consuming. Given this unutilized potential our team has develop proprietary software to analyze this data and communicate the results automatically though and easy to use interface. We have worked with a local real estate property management and ownership firm, Reliance Management, to develop this system through the use of their current, historical, and future data. Our team has also built a relationship with the executives of Reliance Management to review functionality and pertinence of the system we have dubbed, Reliance Dashboard.
ContributorsBurton, Daryl (Co-author) / Workman, Jack (Co-author) / LePine, Marcie (Thesis director) / Atkinson, Robert (Committee member) / Barrett, The Honors College (Contributor) / Department of Finance (Contributor) / Department of Management (Contributor) / Computer Science and Engineering Program (Contributor)
Created2015-05
Description
The objective of this research is to determine an approach for automating the learning of the initial lexicon used in translating natural language sentences to their formal knowledge representations based on lambda-calculus expressions. Using a universal knowledge representation and its associated parser, this research attempts to use word alignment techniques to align natural language sentences to the linearized parses of their associated knowledge representations in order to learn the meanings of individual words. The work includes proposing and analyzing an approach that can be used to learn some of the initial lexicon.
ContributorsBaldwin, Amy Lynn (Author) / Baral, Chitta (Thesis director) / Vo, Nguyen (Committee member) / Industrial, Systems (Contributor) / Barrett, The Honors College (Contributor) / Computer Science and Engineering Program (Contributor)
Created2015-05
Description
Bots tamper with social media networks by artificially inflating the popularity of certain topics. In this paper, we define what a bot is, we detail different motivations for bots, we describe previous work in bot detection and observation, and then we perform bot detection of our own. For our bot detection, we are interested in bots on Twitter that tweet Arabic extremist-like phrases. A testing dataset is collected using the honeypot method, and five different heuristics are measured for their effectiveness in detecting bots. The model underperformed, but we have laid the ground-work for a vastly untapped focus on bot detection: extremist ideal diffusion through bots.
ContributorsKarlsrud, Mark C. (Author) / Liu, Huan (Thesis director) / Morstatter, Fred (Committee member) / Barrett, The Honors College (Contributor) / Computing and Informatics Program (Contributor) / Computer Science and Engineering Program (Contributor) / School of Mathematical and Statistical Sciences (Contributor)
Created2015-05
Description
This paper presents work that was done to create a system capable of facial expression recognition (FER) using deep convolutional neural networks (CNNs) and test multiple configurations and methods. CNNs are able to extract powerful information about an image using multiple layers of generic feature detectors. The extracted information can be used to understand the image better through recognizing different features present within the image. Deep CNNs, however, require training sets that can be larger than a million pictures in order to fine tune their feature detectors. For the case of facial expression datasets, none of these large datasets are available. Due to this limited availability of data required to train a new CNN, the idea of using naïve domain adaptation is explored. Instead of creating and using a new CNN trained specifically to extract features related to FER, a previously trained CNN originally trained for another computer vision task is used. Work for this research involved creating a system that can run a CNN, can extract feature vectors from the CNN, and can classify these extracted features. Once this system was built, different aspects of the system were tested and tuned. These aspects include the pre-trained CNN that was used, the layer from which features were extracted, normalization used on input images, and training data for the classifier. Once properly tuned, the created system returned results more accurate than previous attempts on facial expression recognition. Based on these positive results, naïve domain adaptation is shown to successfully leverage advantages of deep CNNs for facial expression recognition.
ContributorsEusebio, Jose Miguel Ang (Author) / Panchanathan, Sethuraman (Thesis director) / McDaniel, Troy (Committee member) / Venkateswara, Hemanth (Committee member) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2016-05