Low-income populations often have limited access to COVID-19 testing opportunities. This inspired Virufy, a non-profit organization, to develop a mobile-based solution that utilizes an artificial intelligence (AI) model to rapidly diagnose COVID-19 through a cough recording. To properly train this model, Virufy needs a large database of annotated cough recordings; however, the current method of annotating data is outdated and disorganized. To streamline their annotating process, we developed a web-based audio-annotating tool that heavily utilizes the open-source library Label Studio, which will enable the crowdsourcing of audio annotations on the cough samples and support Virufy in improving their AI model.

The Seattle Art Museum’s Historic Media Collection (HMC) is a collection of over 3,000 digitized audiovisual materials related to the museum’s educational programs and exhibitions. Our project’s goal was to develop an initial set of subject headings for these materials. We focused this initial set on Indigenous Art because Indigenous peoples’ identities are historically underrepresented or inaccurately described in controlled vocabularies. To accompany the list, we developed a framework and guide for the museum to use in creating inclusive and representative subject descriptors for other art areas and as part of the museum’s commitment to diversity, equity, and inclusion.

This project is to work towards a digital archive of the manuscripts, photos and other items. There is about 700 items within the collection, the main concept is to catalog them, and recommend the best practices for the archive. This opinion will establish a framework for the organization that can be perfected in the future and give an idea of the collection at hand. One of my goals for this project is to start the conversation about access to digital archives and the differences between the funding each library has access to.

Created an effective onboarding journey program in order to improve customers’ onboarding experience and reduce the Pill Club’s online platforms’ dropout rates. Conducted a market research study to understand the perspectives of users regarding online birth control and provide feedback on TPC’s current onboarding process. Proposed design changes to reduce information gaps that improved customer satisfaction, and conversion rates and retain existing customers. Close to half of our recommendations are in the pipeline and we estimate a 14-20% increase in user conversion rates, that would enable The Pill Club to make online birth control more user friendly.

Cybersecurity attacks are becoming increasingly complex, making it challenging for many Cybersecurity professionals to identify and respond to threats in a timely manner. Our sponsor, KPMG, aims to develop new cybersecurity tools that use machine learning (ML) and artificial intelligence (AI) to identify more risks and facilitate better risk-based decisions. CyberDawgs is an ML-based dashboard that helps identify suspicious user activity at scale by analyzing login patterns targeted by attackers across multiple features and entities. By analyzing large volumes of data quickly and providing real-time insights, CyberDawgs can enable cybersecurity professionals to respond to threats more effectively.

Government officials are currently searching for consumption-based greenhouse gas emissions analysis that is comprehensive, so that they can make educated carbon emission policy decisions for their city. Our sponsor, EcoDataLab, has created a Dashboard that allows city officials to understand their carbon emissions data through visualizations that would previously have been very complicated to comprehend. Our team transformed EcoDataLab’s platform by creating housing, transportation, and US data pages for their site that allow officials to make informed policy decisions in each respective area, while also making recommendations on their current platforms design and accessibility features.

Our project, Data Forensics, is part of our sponsor’s larger Data Afterlives project. The NSF asks researchers to make federally funded data available. We researched NSF awards to see if we could find data associated with these projects. Our findings demonstrate the challenges in finding data and how the accessibility of data varies depending on the NSF research area. We discuss the steps that we took in the course of our research, as well as why this research matters, particularly to information professionals and how national policy shapes the future of open research. We offer future avenues of research.

This case study focuses on non-standardized addresses in Kenya and their negative impact on delivery infrastructure. Through extensive research and stakeholder engagement workshops, our team developed a digital addressing minimal viable product. We utilized a user-centered design and design thinking approach to product development ensuring desirability, feasibility, and viability. The MVP includes features allowing users to provide delivery instructions for better driver context. This solution enhances customer experience by providing accurate doorstep deliveries, and improved location identification and communication. Once completely implemented, this Bawbab can enable doorstep delivery for 38M Kenyan residents.