Physical Sciences and Mathematics Commons^™

Implementing Impact: A Lesson On Mysql Databases And Accessibility, Abigayle Peterson, Yasmine Elglaly

WWU Honors College Senior Projects

15% of the world’s people have a disability that could potentially hinder their access to digital information such as bank portals and medical insurance. Digital accessibility, the practice of creating user-friendly technology, helps mitigate these challenges. Despite this fact, college Computer Science (CS) programs fail to recognize the importance of including digital accessibility courses as a degree requirement. Consequently, these CS graduates lack sufficient knowledge to build accessible software when they enter the technology industry, leading to potential company lawsuits for the unethical design of technology. Our research aims to bridge the gap between accessibility knowledge and the CS college …

Toying With Adapted Toys, Joshua King

WWU Honors College Senior Projects

My project is a design for an adapted toy that occupational therapists (OT) can use when working with kids. OTs are people who help others to be able to do daily tasks that they need to do to live their lives. This can look like helping a person who has been injured or has a disability to accomplish tasks like getting dressed or feeding themselves. It can also involve helping school children to improve their writing or to use assistive technology. My project started out as an idea from my mom who is an OT and was using a coffee …

By The Campfire: How Representation In Video Games Can Be Improved, Hunter Smith

WWU Honors College Senior Projects

By the Campfire is a video game designed with accurate and thorough representation in mind from the start of development. Its purpose is to showcase the ways in which the player character in a video game can accurately represent anyone who plays it, and that the non-player characters in a video game can be generated in a way that diverse groups can be represented without harmfully misrepresenting them. This project includes a document that explains the process by which this game was created and why certain choices were made when implementing the games systems. The document details a survey that …

Interactive Learning With Plankton: Constructing Kiosks For The Sea Discovery Center, Sierra Schuster

WWU Honors College Senior Projects

This project involved creating two interactive kiosks for the SEA Discovery Center to better engage visitors on their plankton exhibits. HTML, CSS, and ReactJS were used to construct web apps that could be launched in Chromium’s Kiosk Mode upon system boot time so that the application would automatically run, preventing visitors to the Center from gaining access to the computer beyond the main program. They are hosted externally on Western Washington University’s Cyber Range and are run on the kiosk machine by Raspberry Pi 4s that access it via a URL. The informational kiosk was designed to give visitors an …

Evaluating Domain Specific Llm Performance Within Economics Using The Novel Econqa Dataset, Tate Van Patten

WWU Honors College Senior Projects

This paper describes a novel dataset, EconQA, constructed to assess the performance of large language models within multiple choice economics questions. I present results from 10 experiments, varying prompts and model choices. Results challenge previous findings that prompt choice makes a large impact on quality of response. Using the GPT 3.5 Turbo model, observed performance levels ranged from 70-77% for all prompt choices, with the no prompt baseline scoring 73%. When prompted to use Chain-of-Thought reasoning with examples, performance was highest at 76%. Contrary to previous research, performance on mathematical questions when prompted with Chain-of-Thought was high. This paper closes …

Databases And Deliberation, Britany Orozco, Quentin Jensen

WWU Honors College Senior Projects

This paper describes the process taken to build a digital form-collection system in a business context. By starting with the motivation for the project, we can gather the requirements necessary to complete before we can consider the project complete. From there, we start discussing the client-server-database architecture principles that must be reviewed before we can design our database. Database design fundamentals are reviewed, such as what a schema or entity relationship diagram is, and those fundamentals are used to design the database. Next, we show how a development environment is chosen. With the environment set up, we then discuss how …

Double Trouble: Applying Deep Learning To Ebs Systems, Noah Reneau, Hidemi Mitani Shen, Nicholas Chandler, Ian Pourlotfali

WWU Honors College Senior Projects

Eclipsing binaries (EB) are fundamental stellar laboratories that can be detected via long-term photometric monitoring. Analyzing the orbital motion of these EBs offers a unique ability to directly measure the parameters of both stars in the system, including masses, radii, and effective temperatures, without relying on theoretical models. Nonetheless, this process is non-trivial, and arriving to a correct solution for a given system can often take significant time. In the ongoing work, we are developing deep learning models capable of providing fast and accurate predictions of these fundamental parameters in these EBs, which will enable the characterization of an increasingly …

From Filth It Rises Presentation, Griffin Hartz

WWU Honors College Senior Projects

This project contains the design, development, and partial implementation of a survival horror game made in Unity engine. The highlight of the game's design is the machine learning agents used to create the game's enemy AI, developed with Unity's MLagents system. In the game, the player controls a construction worker who traveled into a sewer to pursue a missing coworker. They eventually find their way into a crumbling undercity where their coworker was trapped, and soon become hunted by the mutant monster that killed their coworker. Their goal is to escape the ruins without being preyed upon by the mutant …

Digital Archaeology: Detection Of Archaeological Structures Using Convolutional Neural Networks On Aerial Lidar Data, Katie Larue

WWU Honors College Senior Projects

Archaeology is a field that is mostly done by hand. Archaeologists explore remote and unknown areas of the world to find undiscovered civilizations that will give us any idea about how people lived in the past. To speed up this process, Airborne light detection and ranging or LiDAR systems have been used to great effect to speed up this processing. However, we still require domain experts to annotate this information to confirm structures. Deep learning has the potential to speed up this process and the following presentation is a basic overview of machine learning, popular types of deep learning models, …

Software As A Tool Not A Master, Dalton Leif Lange

WWU Honors College Senior Projects

Modern Software takes advantage of users, by designing their software to prey upon the user. Through a historical analysis this paper hopes to better understand what has been done in the past to protect user's liberties, and what we can do going forward to ensure that software can be used as a tool, and not a master.

Indel Mapping, Lilu Martin

WWU Honors College Senior Projects

Insertion and deletion mutations (InDels) are an understudied dynamic of protein structure. Little real world data exists for these types of mutations. Computational modeling can help fill in these gaps and support researchers in obtaining and analyzing data. In this paper, we present a unique approach to gathering exhaustive data on InDel mutations to create heat maps and other visualizations useful in analysis. Every possible InDel in a set of proteins is modelled in silico, rigidity data is obtained for all of those computational InDels, and the rigidity data of each is then compared to that of the wildtype, providing …

Coach Otto: Creating A Program To Program Weightlifting, Haylee Rawdin

WWU Honors College Senior Projects

This paper contains the software documentation for an app called Coach Otto. Coach Otto is an app that assists coaches in creating individualized Olympic Weightlifting programs for their athletes. The documentation for Coach Otto explores the product in the context of user-centered design. Through the use of a PR/FAQ, User Personas, User Journeys, and User Stories, the document explores who the users are, what challenges they face, and how Coach Otto aims to address those challenges.

Dark Patterns: How Interaction Design Turned To Deception, Ian Bansenauer

WWU Honors College Senior Projects

This essay examines the influence of human computer interaction design history on the current practice of deceptive “dark patterns” in interface design. It traces the design evolution of the computer from its initial use as a mathematical tool to the creation of the internet, and towards the current focus on user retention and profitability through the rise of growth hacking and deceptive design practices. Examples of past and current research on interaction design and dark patterns are used to determine that design choices have a measurable effect on user actions. After reviewing the types of dark patterns and their modes …

Exploring Methods Of Collecting Accessibility Feedback, Selah Bellscheidt

WWU Honors College Senior Projects

Accessibility, the practice of making a website or application easily usable and understandable by people with disabilities, is essential to ensuring that all users are able to participate equally in using the Web. However, currently many websites have accessibility issues. This study interviews 11 software developers and designers to learn about the methods that they use to collect accessibility feedback during the development and maintenance of websites and mobile applications. The research revealed a lack of standardized accessibility education at the post-secondary level, as well as a myriad of methods used to obtain accessibility feedback from automatic accessibility checkers to …

Reflections On Setting Up The Cyber Range Intrusion Detection System, William Pearson

WWU Honors College Senior Projects

A short reflection on the project to set up an Intrusion Detection System for the Cyber Range at Western Washington University Poulsbo.

Characterizing The Behavior Of Mutated Proteins With Emcap: The Energy Minimization Curve Analysis Pipeline, Matthew Lee, Bodi Van Roy, Filip Jagodzinski

WWU Honors College Senior Projects

Studies of protein mutants in wet laboratory experiments are expensive and time consuming. Computational experiments that simulate the motions of protein with amino acid substitutions can complement wet lab experiments for studying the effects of mutations. In this work we present a computational pipeline that performs exhaustive single-point amino acid substitutions in silico. We perform energy minimization as part of molecular dynamics (MD) of our generated mutant proteins, and the wild type, and log the energy potentials for each step of the simulations. We motivate several metrics that rely on the energy minimization curves of the wild type and mutant, …

Vikingbot: The Starcraft Artificial Intelligence, Tyler Barger, Daniel Peterson

Scholars Week

VikingBot is an automated AI that plays StarCraft by using a combination of machine learning and artificial intelligence. High level strategies are planned using the Brown-UMBC Reinforcement Learning and Planning (BURLAP), library which implements planning algorithms and provides interfaces for defining a domain and models of that domain for planning. For the planning, we used the BURLAP implementation of the sparse sampling algorithm because the time complexity is independent of the size of the state space, and we have to plan quickly in real time. SARSA reinforcement learning is used for a machine learning model that controls combat units. Various …

Nimbleknow User Documentation, Camille Estee Ottaway

WWU Honors College Senior Projects

NimbleKnow User Documentation is an Honors Project by Camille Ottaway

NimbleKnow is a simple web application that teachers can use to pose questions which students can then answer using their basic smartphones or tablets. In order to accommodate ESL learners our application includes translation features. Having a user-friendly classroom technology can promote more engagement and collaboration between students and faculty alike in a classroom environment.

Smart Home Simulation In The Virtual World, Thomas Jones-Moore, David Son

Scholars Week

The goal of this project is to produce a 'smart home' by using IoT and RFID like things in the virtual world to help solve problems. Some of these problems can be CPR training, etc. Used as an evaluation platform of suggested hardware to get a desired (or best fit) set of smart objects, or combinations with computer vision. Cost model to determine best fit based on: accuracy, lowest cost, easiest deployment, etc.

Performance Annotation Framework, Quentin Jensen, Chloe Dawson

Scholars Week

Large scale applications developers have many tools at their disposal to optimize and verify their software. One of which is Caliper, an annotation-based performance measurement tool. Caliper is very powerful and versatile, however, can be cumbersome to apply to complex applications. To solve this problem, we have created a framework to automatically prepare an application for performance measurement. This framework provides a layer of abstraction between the user and the source-code annotations and library linking. As a result, the process of measuring the performance of an application can be fully automated away – a huge step towards automatic software optimization.

A Simulation Platform For Generation Of Synthetic Videos For Human Activity Recognition, Gary Plunkett

Scholars Week

The field of human activity recognition from video data has recently made great strides. However, the large amount of labelled data needed to train activity recognition models remains a common bottleneck. We introduce a simulation platform to procedurally generate synthetic videos of household activities, which randomizes portions of the virtual scene like camera position, human model, and interaction motion to introduce video variation.

A Day In The Life Of A Supercomputer, William Clem, Sean Mcculloch

Scholars Week

We are developing an interactive dashboard for visualizing the statistics of how users interact with nodes of a supercomputer. The intended purpose of the dashboard is to periodically provide with the overview of the load and bandwidth utilization of the nodes of a large supercomputer and details of each node and job as selected by the user. The dashboard will be interactive which will enable users to zoom in on interesting parts of the visualizations to investigate in details.

Connection: An Autism-Focused Dating App, Cyrena Johnson

Scholars Week

30% of US internet users 18-29 use dating apps to find partners. Meanwhile, only 9% of adults with autism are married—and there are no popular dating apps designed for ASDs. We propose the app Connection, a dating app designed for the autistic community. Using queries and informal analysis, we created possible features and prototype displays for Connection to show its future application.

This Is Not A Brain, Allison Wusterbarth

WWU Honors College Senior Projects

An exploration of machine learning and its ethical consequences.

(Slides for the discussion are at the end of the file.)

Exploring The Differences Between Human And Machine Translation, Connor Freitas, Yudong Liu

WWU Honors College Senior Projects

Chinese second language learners of English often use Machine Translators (MT) to translate personal and professional messages from their first language to English. MT’s are not perfect and have historically create messages that lack the cohesiveness and authenticity of natively written English. This paper describes our attempts to quantify the differences between human translation and machine translation in a specific scope with that hope that both MTs and post editing systems can be benefited through awareness of common error and differences between human and machine translations. In order to achieve this we implemented existing algorithms designed to identify common errors …

Constrained Sequence Alignment, Kyle Daling

WWU Honors College Senior Projects

Constrained Sequence Alignment: A new algorithm designed to help biologists produce better alignment for protein sequences.

Red Beetl: Recipe Encoder Decoder Beer Translator Lstm, Grace Ermi, Ellyn Ayton

Graduate Student Symposium

The number of craft breweries has exploded in last decade: there are around a dozen breweries in Bellingham alone. Each brewery must assemble a lineup of beers, but this process of designing new beers usually relies on some combination of brewer instinct and trial and error. Because brewing beer involves complicated biological and chemical processes, the mapping from recipe to the beer it will produce is non-trivial to predict. In this project, we consider mapping between representations of beer in three distinct domains. In one view, a beer can be described by a recipe, which specifies the particular hop, malt …

Recognition, Internalization, Growth: Intuitive Design For Archival Representation, Jaime L. Ganzel

Graduate Student Symposium

Although there is a pressing need for archival description and access systems to be more intuitive and user-friendly, the uniqueness of archival records presents significant barriers to establishing simplistic and standardized conventions for the representation of archival materials. Indecipherable finding aids and access tools prevent new and inexperienced researchers from accessing the unique information and documentation held in archives. This article aims to help open the archival record to new and non-traditional archival users, support individual development of archival literacy skills, and cultivate a greater level of archival awareness in our society by developing a usable model for archivists to …

Predicting Computer Science Students’ Online Help-Seeking Tendencies, Qiang Hao, Brad Barnes, Robert Maribe Branch, Ewan Wright

Computer Science Faculty and Staff Publications

This study investigated how computer science students seek help online in their learning and what factors predict their online help-seeking behaviors. Online help-seeking behaviors include online searching, asking teachers online for help, and asking peers online for help. 207 students from a large university in the southeastern United States participated in the study. It was revealed that computer science students tended to search online more frequently than ask people online for help. Five factors, including epistemological belief, interest, learning proficiency level, prior knowledge of the learning subject, and problem difficulty, were explored as potential predictors in this study. It was …

Executive Summary: Western Libraries Beta Website Usability, Rebecca M. Marrall, Nora K. Burmeister, Jon Dillon

Usability & Design Working Group Documents

This brief report provides an overview of the Fall Quarter 2016 usability sessions on the Western Libraries beta website. The purpose of this report is to inform Libraries and Learning Commons personnel of our next steps with the beta website. There were 36 participants over the course of five two hour sessions.