PATH and MSR® Global Health developed the SafiStation™, an innovative and easy-to-use device that generates chlorine for infection prevention and water treatment in low-resource health care facilities. PATH is preparing to conduct a field test of up to 50 SafiStation devices across three countries to evaluate device performance, impact, and usability. We created a web-based dashboard to combine data automatically collected by the device with digital surveys in order to visualize chlorine production and cost savings. The dashboard will help PATH efficiently and effectively monitor the device in the field and make conclusions about the best market for the SafiStation.

Our capstone sponsor is PitchBook, a company that provides financial database and platform for Private Equity and Venture Capital professionals. While VC’s today have access to millions of data points, determining the hard-to-grasp “market sentiment” is still difficult. Various heuristics can be deployed to test sentiment, including financial news data. We built SentiSage, a working prototype which provides VC and PE professionals with sentiment analysis on news data and presents insights through visualizations and a user interface. Because of SentiSage, our users can better access the data points and trends they need when making crucial decisions in a volatile market.

In 2015, Washington State Public Defenders were taking over 1000 cases a month and spending an inadequate 36 minutes per case. Current legal processes do not support the variety of clients defenders must serve, such as the low income populations where permanent residence affects legal information delivery. By automating reminders of critical dates and visualizing long-term history, our client-case management system, Shield , allows public defenders to focus on protecting the public interest without getting caught up in tedious workflows

Amazon's Strategic Recruitment Team (SRT) handles their Executive level hiring for Machine learning (ML) experts. The current challenge with their hiring procedure is that it needs a lot of manual effort to browse through Google Scholar/other academic websites to know about a ML expert’s research. We proposed an academic perspective solution which provides Amazon’s SRT with a portal displaying their well sought ML expert's collaboration network, conference research trends and his affiliations. Our solution makes it easier for recruiters to initiate networking with ML experts at Top conferences as it provides vital information about the candidate.

Have you ever wondered whether your own experiences playing a game were mirrored by others? I have. Many months later and hours of research & cursing...here we are. This project explores the relationship between Tabletop Roleplaying Games (TRPG's) and Social Dynamics. This was done by conducting interviews and an online survey discussing gamer demographics, gameplay, and social dynamics. Analysis of this self-reported data will help to bridge the current information gap regarding the social dynamics of TRPG's. It will also be the first step in discussing the benefits of playing TRPG's on social behavior skill development.

Synapse Solutions is an online platform that provides researchers with a tool to work with and analyze electroencephalogram (EEG) data.

As the fastest growing city in the nation, Seattle's transportation infrastructure is under tremendous stress. As an interested citizen, information about our transportation system can be confusing and difficult to find. TransitSphere, built in partnership with the Seattle Department of Transportation, is an easy, interactive way to discover how Seattle's transportation assets work together to keep us moving. This tool gives citizens the how, what, and why of our city's transportation infrastructure management, and can serve as an introduction to a part of their government that they may not be familiar with.

When timing and insight is the key to success in the venture capital world, being able to scan through large amount of information, extract insights, detect emerging spaces, and stay ahead of the game provides a competitive edge. The project showcases a solution with an end to end natural language processing backed text mining pipeline and a standalone front-end prototype. Derived from recent news articles, the project solution allows users to actively tune in and keep track of emerging spaces and trends of interests on the sponsor platform.

It is estimated that only 86% of children worldwide receive the complete three doses of major vaccines, despite global coverage. Identifying data gaps in vaccination coverage will deepen understanding of the barriers for these left-out communities and ultimately support better vaccination access around the world. This project models vaccination recall, caregiver provided data used when a child’s vaccination card is not available. Recall is only 53% accurate, yet UNICEF vaccination coverage statistics are calculated using this unreliable data. We use machine-learning techniques to model conditions of caregivers without cards, supporting card loss prevention and more accurate vaccination coverage data.

As a bridging tool, this Access undergraduate award database is designed to compile academic raw data retrieved from central student information system to be in align with current university standards on student awards/scholarships, to effectively sort, filter, and select potential candidates for 25 pre-academic session awards provided by the Department of Chemical & Biological Engineering and APSC. With only a few clicks, the access interface would enable users to shortlist students in orders based on various award criteria. Also, this database is linked with a departmental SharePoint site to get all the data synced and communicated among the award committee.