2018 Research
Computer Science
JONATHAN BRANHAM
Title: Evaluation of Texture as an Input of Spatial Context for Machine Learning Mapping of Wildland Fire Effects
Thesis Adviser: Dr. Barry Myers, Dr. Dale Hamilton
A variety of machine learning algorithms have been used to map wildland fire effects, but previous attempts to map post-fire effects have been conducted using relatively low-resolution satellite imagery. Small unmanned aircraft systems (sUAS) provide opportunities to acquire imagery with much higher spatial resolution than is possible with satellites or manned aircraft. This effort investigates improvements achievable in the accuracy of post-fire effects mapping with machine learning algorithms that use hyperspatial (sub-decimeter) drone imagery. Spatial context using a variety of texture metrics were also evaluated to determine the inclusion of spatial context as an additional input to the analytic tools along with the three-color bands. This analysis shows that the addition of texture as an additional fourth input increases classifier accuracy when mapping post-fire effects.
GREG SMITH
Title: Training Data Selector
Thesis Adviser: Dr. Dale Hamilton
Gathering training data for a machine learning classifier can be a painstaking slow and tedious task. Not only must the user ensure the data being gathered in accurate, but they must also gather enough data to successfully train the classifier. The Training Data Selector (TDS) solves these problems. This tool provides accurate training data for analytics as diverse as wildland fire management and pathology. The TDS allows the user to draw on data in any web browser, label that data, and then extract and export the pixel data. This application utilizes human expertise without compromising computer processing power.
As well as providing a quick and clean solution to extracting information from data to be used in various supervised classifiers, the TDS application was built and designed for users who are inexperienced with computer applications and therefore provides a simple, easy, and intuitive interface for all users on all platforms. The TDS provides the greatest flexibility, power, and availability to extract the selected data the user chooses for training a supervised classifier.
JOSHUA GAMBILL
Title: Training Data Selector
Thesis Adviser: Dr. Barry Myers
A web-based application that provides teachers assistants with an online alternative to submitting timesheets. This application gives teachers assistants the ability to enter, save, and upload hours worked through a server hosted on the Computer Science Department servers. Teachers are given the ability to view registered students and their respective hours. System Admins are given the ability to see the registered students, their time sheets, registered teachers, and their students. The front end of this application was developed using Sublime Text with HTML, CSS, and JavaScript to display the user interface for different levels of user as well as a login page. The database was developed using MySQL hosted on a XAMPP server to store time sheets, registered users, and passwords. The server uses phpMyAdmin as an administration tool to manage all information uploaded to the server. The front end website was connected using PHP scripts written with the functionality to give users different information upload options based off of user type. The server is scheduled to be implemented on the Computer Science Department servers but is currently implemented on a desktop personal computer.
MATLYN KNOTT
Title: Automation of the Nampa Family Justice Center
Thesis Adviser: Dr. Barry Myers
The city of Nampa offers help for victims of family violence, and sexual assault, through the Family Justice Center. Every year, there are hundreds of people in Canyon County that are petitioning for a no contact order of some kind, against someone who might be physically, emotionally, or mentally abusing them. They are expected to go to the court room, possibly act as an attorney for themselves, figure the entire justice system out, and sit in the same room as the respondent, who often happens to be their abuser. The Family Justice Center has offered a service to these petitioners that provides an advocate to go with the petitioner. The advocate is there for support, but to also collect data about these hearings. In the past, this data has been collected by pen and paper, but the purpose of this project was to create a database system to collect and store this information about the court cases. Throughout this project, I collected information about the system, designed the database system and started the implementation of this database.
JAYDEN WEAVER
Title: Posture Analysis (Sublux)
Thesis Adviser: Dr. Barry Myers
According to the American Chiropractic Association, 31 million Americans experience low-back pain at any given time. Sublux, an Android application written in Java, aims to reduce this number by putting a valuable tool in the average person’s hand. This tool analyzes photos of a user and returns the results so that adjustments to the user’s posture can be improved as needed through chiropractic therapy. The end result of the project is a fully functional Android application that successfully analyzes a user’s posture through photos. The photo is then displayed alongside the results of the analysis for the user to review. While Sublux is fully functional, there may be issues analyzing some photos due to lighting, backdrops and background items, or changes in textures. Sublux recommends good lighting and a solid background for best results, but also contains code to combat any photos that are subpar. The code to combat this is not perfect, however, and will need to be improved in future versions. The source code will be available at github.com/jayden2013/sublux, and an APK will be available for download at jayden2013.github.io/sublux.