Matching Items (15)
Filtering by
- All Subjects: Natural Language Processing
- Creators: Computer Science and Engineering Program
- Member of: Theses and Dissertations
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
An application called "Productivity Heatmap" was created with this project with the goal of allowing users to track how productive they are over the course of a day and week, input through scheduled prompts separated by 30 minutes to 4 hours, depending on preference. The result is a heat map colored according to a user's productivity at particular times of each day during the week. The aim is to allow a user to have a visualization on when he or she is best able to be productive, given that every individual has different habits and life patterns. This application was made completely in Google's Android Studio environment using Java and XML, with SQLite being used for database management. The application runs on any Android device, and was designed to be a balance of providing useful information to a user while maintaining an attractive and intuitive interface. This thesis explores the creation of a functional mobile application for mass distribution, with a particular set of end users in mind, namely college students. Many challenges in the form of learning a new development environment were encountered and overcome, as explained in the report. The application created is a core functionality proof-of-concept of a much larger personal project in creating a versatile and useful mobile application for student use. The principles covered are the creation of a mobile application, meeting requirements specified by others, and investigating the interest generated by such a concept. Beyond this thesis, testing will be done, and future enhancements will be made for mass-market consumption.
ContributorsWeser, Matthew Paul (Author) / Nelson, Brian (Thesis director) / Balasooriya, Janaka (Committee member) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2016-05
Description
In this paper, I introduce the fake news problem and detail how it has been exacerbated<br/>through social media. I explore current practices for fake news detection using natural language<br/>processing and current benchmarks in ranking the efficacy of various language models. Using a<br/>Twitter-specific benchmark, I attempt to reproduce the scores of six language models<br/>demonstrating their effectiveness in seven tweet classification tasks. I explain the successes and<br/>challenges in reproducing these results and provide analysis for the future implications of fake<br/>news research.
ContributorsChang, Ariz Bay (Author) / Liu, Huan (Thesis director) / Tahir, Anique (Committee member) / Computer Science and Engineering Program (Contributor, Contributor) / Barrett, The Honors College (Contributor)
Created2021-05
Description
Natural Language Processing and Virtual Reality are hot topics in the present. How can we synthesize these together in order to make a cohesive experience? The game focuses on users using vocal commands, building structures, and memorizing spatial objects. In order to get proper vocal commands, the IBM Watson API for Natural Language Processing was incorporated into our game system. User experience elements like gestures, UI color change, and images were used to help guide users in memorizing and building structures. The process to create these elements were streamlined through the VRTK library in Unity. The game has two segments. The first segment is a tutorial level where the user learns to perform motions and in-game actions. The second segment is a game where the user must correctly create a structure by utilizing vocal commands and spatial recognition. A standardized usability test, System Usability Scale, was used to evaluate the effectiveness of the game. A survey was also created in order to evaluate a more descriptive user opinion. Overall, users gave a positive score on the System Usability Scale and slightly positive reviews in the custom survey.
ContributorsOrtega, Excel (Co-author) / Ryan, Alexander (Co-author) / Kobayashi, Yoshihiro (Thesis director) / Nelson, Brian (Committee member) / Computing and Informatics Program (Contributor) / School of Art (Contributor) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2018-05
Description
The goal of this research study was to empirically study the effects of a project based learning activity. The effectiveness of this study was benchmarked according to two results: the effectiveness in communicating the scope and impact of engineering, and the effectiveness in increasing interest in computer systems engineering (CSE). This research report presents an analysis of the effects of making engineering education socially relevant, interesting and accessible. High school students participated in a learning experience in which they designed flood evacuation systems that could warn a city of incoming floods. Both pre-assessments and post-assessments were implemented to capture students' awareness of engineering tasks and their interest levels in engineering tasks. Data on students' perceptions of specific engineering tasks were analyzed quantitatively through Wilcoxon signed-rank testing and determined that the program had significant positive effects on developing more accurate conceptions of engineering tasks. The results relating to student interest in CSE indicated that there was an increased level of interest in CSE engineering tasks after the program. There was a 14% increase in number of students who found engineering tasks interesting from 64% to 78%. However, as participants self-selected to participate in this learning experience, many students had positive perceptions of engineering tasks prior to engaging in the learning experience. This study was successful and met both of its primary goals of enhancing awareness and interest in engineering in this particular group of high school students.
ContributorsRidhwaan, Syed (Author) / Ganesh, Tirupalavanam (Thesis director) / Shrake, Scott (Committee member) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2017-05
Description
The purpose of this project was to implement and analyze a new proposed rootkit that claims a greater level of stealth by hiding in cache. Today, the vast majority of embedded devices are powered by ARM processors. To protect their processors from attacks, ARM introduced a hardware security extension known as TrustZone. It provides an isolated execution environment within the embedded device that enables us to run various memory integrity and malware detection tools to identify possible breaches in security to the normal world. Although TrustZone provides this additional layer of security, it also adds another layer of complexity, and thus comes with its own set of vulnerabilities. This new rootkit identifies and exploits a cache incoherence in the ARM device as a result of TrustZone. The newly proposed rootkit, called CacheKit, takes advantage of this cache incoherence to avoid memory introspection from tools in secure world. We implement CacheKit on the i.MX53 development board, which features a single ARM Cortex A8 processor, to analyze the limitations and vulnerabilities described in the original paper. We set up the Linux environment on the computer to be able to cross-compile for the development board which will be running the FreeScale android 2.3.4 platform with a 2.6.33 Linux kernel. The project is implemented as a kernel module that once installed on the board can manipulate cache as desired to conceal the rootkit. The module exploits the fact that in TrustZone, the secure world does not have access to the normal world cache. First, a technique known as Cache-asRAM is used to ensure that the rootkit is loaded only into cache of the normal world where it can avoid detection from the secure world. Then, we employ the cache maintenance instructions and resisters provided in the cp15 coprocessor to keep the code persistent in cache. Furthermore, the cache lines are mapped to unused I/O address space so that if cache content is flushed to RAM for inspection, the data is simply lost. This ensures that even if the rootkit were to be flushed into memory, any trace of the malicious code would be lost. CacheKit prevents defenders from analyzing the code and destroys any forensic evidence. This provides attackers with a new and powerful tool that is excellent for certain scenarios that were previously thought to be secure. Finally, we determine the limitations of the prototype to determine possible areas for future growth and research into the security of networked embedded devices.
ContributorsGutierrez Barnett, Mauricio Antonio (Author) / Zhao, Ziming (Thesis director) / Doupe, Adam (Committee member) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2016-12
Description
The software element of home and small business networking solutions has failed to keep pace with annual development of newer and faster hardware. The software running on these devices is an afterthought, oftentimes equipped with minimal features, an obtuse user interface, or both. At the same time, this past year has seen the rise of smart home assistants that represent the next step in human-computer interaction with their advanced use of natural language processing. This project seeks to quell the issues with the former by exploring a possible fusion of a powerful, feature-rich software-defined networking stack and the incredible natural language processing tools of smart home assistants. To accomplish these ends, a piece of software was developed to leverage the powerful natural language processing capabilities of one such smart home assistant, the Amazon Echo. On one end, this software interacts with Amazon Web Services to retrieve information about a user's speech patterns and key information contained in their speech. On the other end, the software joins that information with its previous session state to intelligently translate speech into a series of commands for the separate components of a networking stack. The software developed for this project empowers a user to quickly make changes to several facets of their networking gear or acquire information about it with just their language \u2014 no terminals, java applets, or web configuration interfaces needed, thus circumventing clunky UI's or jumping from shell to shell. It is the author's hope that showing how networking equipment can be configured in this innovative way will draw more attention to the current failings of networking equipment and inspire a new series of intuitive user interfaces.
ContributorsHermens, Ryan Joseph (Author) / Meuth, Ryan (Thesis director) / Burger, Kevin (Committee member) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2016-12
Description
The Internet of Things has spread Wi-Fi connectivity to household and business devices everywhere. It is important that we understand IoT's risks and capabilities as its popularity continues to grow, and that we recognize new and exciting uses for it. In this project, the ESP8266 Wi-Fi controller, powered by a lithium battery, is used to transmit messages from a user's browser or mobile phone to an OLED display. The ESP8266 is a system on a chip (SOC) which boasts impressive features such as full TCP/IP stack, 1 MB of flash memory, and a 32-bit CPU. A web server is started on the ESP8266 which listens at a specific port and relays any strings from the client back to the display, acting as a simple notification system for a busy individual such as a professor. The difficulties with this project stemmed from the security protocol of Arizona State University's Wi-Fi network and from the limitations of the Wi-Fi chip itself. Several solutions are suggested, such as utilizing a personal cellular broadband router and polling a database for stored strings through a service such as Data.Sparkfun.com.
ContributorsKovatcheva, Simona Kamenova (Author) / Burger, Kevin (Thesis director) / Meuth, Ryan (Committee member) / Computer Science and Engineering Program (Contributor) / School of International Letters and Cultures (Contributor) / Barrett, The Honors College (Contributor)
Created2016-12
Description
This research lays down foundational work in the semantic reconstruction of linguistic politeness in English-to-Japanese machine translation and thereby advances semantic-based automated translation of English into other natural languages. I developed a Java project called the PoliteParser that is intended as a plug-in to existing semantic parsers to determine whether verbs in dialogue in an English corpus should be conjugated into the plain or the polite honorific form when translated into Japanese. The PoliteParser bases this decision off of semantic information about the social relationships between the speaker and the listener, the speaker's personality, and the circumstances of the utterance. Testing undergone during the course of this research demonstrates that the PoliteParser can achieve levels of accuracy 31 percentage points higher than that of statistical translation systems when integrated with a semantic parser and 54 percentage points higher when used with pre-parsed data.
ContributorsGuiou, Jared Tyler (Author) / Baral, Chitta (Thesis director) / Tanno, Koji (Committee member) / School of International Letters and Cultures (Contributor) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2016-12
Description
Medical records are increasingly being recorded in the form of electronic health records (EHRs), with a significant amount of patient data recorded as unstructured natural language text. Consequently, being able to extract and utilize clinical data present within these records is an important step in furthering clinical care. One important aspect within these records is the presence of prescription information. Existing techniques for extracting prescription information — which includes medication names, dosages, frequencies, reasons for taking, and mode of administration — from unstructured text have focused on the application of rule- and classifier-based methods. While state-of-the-art systems can be effective in extracting many types of information, they require significant effort to develop hand-crafted rules and conduct effective feature engineering. This paper presents the use of a bidirectional LSTM with CRF tagging model initialized with precomputed word embeddings for extracting prescription information from sentences without requiring significant feature engineering. The experimental results, run on the i2b2 2009 dataset, achieve an F1 macro measure of 0.8562, and scores above 0.9449 on four of the six categories, indicating significant potential for this model.
ContributorsRawal, Samarth Chetan (Author) / Baral, Chitta (Thesis director) / Anwar, Saadat (Committee member) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2018-05