Matching Items (43)
Filtering by

Clear all filters

148193-Thumbnail Image.png
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

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
135660-Thumbnail Image.png
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

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
135605-Thumbnail Image.png
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 ma

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
136678-Thumbnail Image.png
Description
When planning a road trip today, there are solutions that let the user know what comes along their route, but the user is often presented with too much information, which can overwhelm the user. They are provided suggestions all along the route, not just at those times when they would

When planning a road trip today, there are solutions that let the user know what comes along their route, but the user is often presented with too much information, which can overwhelm the user. They are provided suggestions all along the route, not just at those times when they would be needed. RoutePlanner simply takes all that information and only presents that data to the user, that they would need at a particular time. Gas station suggestions would show when the gas tank range is going to be hit soon, and restaurant suggestions would only be shown around lunch time. The iOS app takes in the users origin and destination and provides the user the route as given by GoogleMaps, and then various stop suggestions at their given time. Each route that is obtained, is broken down into a number of steps, which are basically a connection of coordinate points. These coordinate point collections are used to point to a location at a certain distance or duration away from the origin. Given a coordinate, we query the APIs for places of interest and move to the next stop, until the end of the route.
ContributorsDamania, Harsh Abhay (Author) / Balasooriya, Janaka (Thesis director) / Faucon, Christophe (Committee member) / Barrett, The Honors College (Contributor) / Computer Science and Engineering Program (Contributor)
Created2014-12
136604-Thumbnail Image.png
Description
As technology's influence pushes every industry to change, healthcare professionals must move to a more connected model. The nearly ubiquitous presence of smartphones presents a unique opportunity for physicians to collect and process data from their patients more frequently. The Mayo Clinic, in partnership with the Barrett Honors College, has

As technology's influence pushes every industry to change, healthcare professionals must move to a more connected model. The nearly ubiquitous presence of smartphones presents a unique opportunity for physicians to collect and process data from their patients more frequently. The Mayo Clinic, in partnership with the Barrett Honors College, has designed and developed a prototype smartphone application targeting palliative care patients. The application collects symptom data from the patients and presents it to the doctors. This development project serves as a proof-of-concept for the application, and shows how such an application might look and function. Additionally, the project has revealed significant possibilities for the future of the application.
ContributorsGaney, David Howard (Author) / Balasooriya, Janaka (Thesis director) / Lipinski, Christopher (Committee member) / Barrett, The Honors College (Contributor) / Department of Psychology (Contributor) / Computer Science and Engineering Program (Contributor)
Created2015-05
136440-Thumbnail Image.png
Description
The face of computing is constantly changing. Wearable computers in the form of glasses or watches are becoming more and more common. These devices have very small screens (measured in millimeters), and users often interact with them through voice input and audio feedback. Weather is one of the most regularly

The face of computing is constantly changing. Wearable computers in the form of glasses or watches are becoming more and more common. These devices have very small screens (measured in millimeters), and users often interact with them through voice input and audio feedback. Weather is one of the most regularly checked app category on smart devices, but weather results on these devices are often limited to raw data, canned responses, or sentence templates with numbers plugged in. The goal for this project was to build a system that could generate weather forecast text, which could then be read to a user through text-to-speech. By using methods in language generation, the system can generate weather forecast text in millions of different ways. This is all computed locally, and it covers every possible weather case. In order to generate natural weather forecast texts, the system retrieved raw weather data from a weather API and created the text through six methods: content determination, document structuring, sentence aggregation, lexical choice, referring expression generation, and text realization. Content determination is the process of deciding on what information to include in a computer generated text. The document structuring phase deals with the order and structure of the information. Sentence aggregation is the merging of similar sentences to improve readability and to reduce redundancy. Lexical choice is the process of putting words to concepts. Referring expression generation is the process of identifying objects, regions, time periods, and locations within a text. Finally text realization involves creating sentences with proper syntax, morphology, and orthography. Through these six stages, a system was developed that could generate unique weather forecast text from raw data accurately and efficiently. It was built for iOS devices with Apple's new programming language, Swift, and it will be ported to the Apple Watch when the API is fully opened to developers.
ContributorsJorgensen, Jacob Paul (Author) / Baral, Chitta (Thesis director) / Faucon, Christophe (Committee member) / Barrett, The Honors College (Contributor) / Computer Science and Engineering Program (Contributor)
Created2015-05
148244-Thumbnail Image.png
Description

In this experiment, a haptic glove with vibratory motors on the fingertips was tested against the standard HTC Vive controller to see if the additional vibrations provided by the glove increased immersion in common gaming scenarios where haptic feedback is provided. Specifically, two scenarios were developed: an explosion scene containing

In this experiment, a haptic glove with vibratory motors on the fingertips was tested against the standard HTC Vive controller to see if the additional vibrations provided by the glove increased immersion in common gaming scenarios where haptic feedback is provided. Specifically, two scenarios were developed: an explosion scene containing a small and large explosion and a box interaction scene that allowed the participants to touch the box virtually with their hand. At the start of this project, it was hypothesized that the haptic glove would have a significant positive impact in at least one of these scenarios. Nine participants took place in the study and immersion was measured through a post-experiment questionnaire. Statistical analysis on the results showed that the haptic glove did have a significant impact on immersion in the box interaction scene, but not in the explosion scene. In the end, I conclude that since this haptic glove does not significantly increase immersion across all scenarios when compared to the standard Vive controller, it should not be used at a replacement in its current state.

ContributorsGriffieth, Alan P (Author) / McDaniel, Troy (Thesis director) / Selgrad, Justin (Committee member) / Computing and Informatics Program (Contributor) / School of Mathematical and Statistical Sciences (Contributor) / Economics Program in CLAS (Contributor) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2021-05
148262-Thumbnail Image.png
Description

This thesis is based on bringing together three different components: non-Euclidean geometric worlds, virtual reality, and environmental puzzles in video games. While all three exist in their own right in the world of video games, as well as combined in pairs, there are virtually no examples of all three together.

This thesis is based on bringing together three different components: non-Euclidean geometric worlds, virtual reality, and environmental puzzles in video games. While all three exist in their own right in the world of video games, as well as combined in pairs, there are virtually no examples of all three together. Non-Euclidean environmental puzzle games have existed for around 10 years in various forms, short environmental puzzle games in virtual reality have come into existence in around the past five years, and non-Euclidean virtual reality exists mainly as non-video game short demos from the past few years. This project seeks to be able to bring these components together to create a proof of concept for how a game like this should function, particularly the integration of non-Euclidean virtual reality in the context of a video game. To do this, a Unity package which uses a custom system for creating worlds in a non-Euclidean way rather than Unity’s built-in components such as for transforms, collisions, and rendering was used. This was used in conjunction with the SteamVR implementation with Unity to create a cohesive and immersive player experience.

ContributorsVerhagen, Daniel William (Author) / Kobayashi, Yoshihiro (Thesis director) / Nelson, Brian (Committee member) / Computer Science and Engineering Program (Contributor, Contributor) / Barrett, The Honors College (Contributor)
Created2021-05
130875-Thumbnail Image.png
Description
This project produced a dual-medium (traditional screen & virtual reality) virtual environment of Barnhardt Canyon, in Payson, Arizona. The project showcases two different approaches to developing a virtual environment with both being centered by 360 degree content. The virtual environment allows a user to explore the area in a much

This project produced a dual-medium (traditional screen & virtual reality) virtual environment of Barnhardt Canyon, in Payson, Arizona. The project showcases two different approaches to developing a virtual environment with both being centered by 360 degree content. The virtual environment allows a user to explore the area in a much more immersive way than offered by traditional media. Future uses of the project could include research on the educational efficacy of virtual reality content, or the project could be used as a teaching tool in geoscience classes.
ContributorsRuberto, James Richard (Author) / Semken, Steven (Thesis director) / Reynolds, Stephen (Committee member) / Proctor, Sian (Committee member) / Computer Science and Engineering Program (Contributor, Contributor) / Barrett, The Honors College (Contributor)
Created2020-12
131274-Thumbnail Image.png
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

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