iSchool Capstone

2023

Project Logo

Habitat

With 1 million species on the brink of extinction, it’s clear that the endangered animal crisis is becoming increasingly severe each day. By providing high school and college students with the appropriate resources, they can be the leaders of change needed to protect our ecosystems. Habitat is a website designed with the intention of guiding students by providing them with personalized resources based on their hobbies, that they can easily integrate into their lifestyles. With this project, we strive to help students realize the urgency of the crisis and make sustainable changes to make a positive impact on our ecosystems.
Project Logo

Interactive Data Visualization for Distributed Acoustic Sensing

Geohazards in the Pacific Northwest cause significant annual financial losses. To address this, the University of Washington's Photonic Sensing Facility (PSF) collects seismic data using advanced Distributed Acoustic Sensing technology. Their primary objective is to develop a user-friendly web application for widespread data access and visualization. The target audience includes researchers, public scientists, geohazard enthusiasts, and educators. This initiative aims to enhance geohazard monitoring, mitigate risks, and promote knowledge sharing. PSF's efforts contribute to addressing the pressing issue of geohazards monitoring while facilitating collaboration and informed decision-making.
Project Logo

NetPrism: Developing a Machine Learning Model for Predicting Product Prices

NetPrism develops software for understanding e-commerce trends. Our capstone project addresses the common problem of uncertainty in determining the best time to purchase a product. To solve this issue, we developed a Machine Learning model that leverages thousands of historical price data points to accurately predict the price of a product in the next 30 days. Our Price Prediction model provides graphical price predictions that enable individuals to make informed purchasing decisions, leading to more effective allocation of resources and less overspending. Our project demonstrates the utility of data analytics in bettering everyday finances.
Project Logo

NewImpact: Streamlining Access to Data for Tri-Sector Innovation

NewImpact is a non-profit that provides resources for tri-sector innovation. Given the amount of organizations in existence it can be difficult for innovators to know where to start looking for information fitting their needs. To address this, we partnered with our sponsor to improve and redesign a wiki tool that serves as a free online directory of datasets, organizations and resources. Our platform allows users to search and filter for relevant information, explore geo-mapped resources, and export and share their findings. We hope this tool will provide opportunities for people to explore and solve real world problems!
Project Logo

NOVA - An AI Powered NIST CSF Education And Management Tool

Small to medium-sized companies face a significant challenge, as they are disproportionately targeted for cybersecurity threats and data breaches. To address this issue, we have developed Nova, an easy-to-use, effective, and affordable chatbot. The impact of Nova is twofold: it empowers clients to navigate and implement the NIST framework, address their cybersecurity needs, and educate themselves through tailored guidance.
Project Logo

Open Data Portal Metric Performance Dashboard

Open Data Portal Metric Performance Dashboard aims to enhance the transparency and accessibility of Washington State's open data program, data.wa.gov, through the design and implementation of a performance indicator dashboard. This project involves building robust data pipelines for automatic data updates, defining and calculating precise metrics, and visualizing these metrics using Tyler's built-in tool. Furthermore, a GitHub repository will be established for efficient code maintenance and dashboard documentation. The outcome will be a comprehensive, user-friendly platform showcasing the performance and value of Data.Wa's public data assets.
Project Logo

Pallet Shelter: Collecting Data To Enhance Village Models Aimed At Addressing Homelessness

Pallet Shelter addresses unsheltered homelessness by constructing transitional shelter villages. To gather data on their impact, we developed a solution for collecting anonymized information from village residents. This measures the effectiveness of non-congregate village models in addressing residents' health, well-being, and homelessness journey. Google Forms surveys capture resident and service partner experiences, while a staff dashboard enables data analysis. Our solution provides insights into non-congregate villages' effectiveness by gathering data from residents and staff, enhancing our understanding. A project proposal was created to ensure Pallet is on the right track to obtaining constant data they want to enhance our solution.
Project Logo

Project Anemone

Starfish Space worked with our team to redesign their data platform. Starfish Space engineers and analysts interact with hundreds of files with many different data visualizations every day without a modern, easy-to-use platform to organize and navigate their data. Anemone is an updated data visualization platform enabling Starfish Space employees to read and analyze satellite mission data faster to support future satellite missions with more efficiency and customizability.
Project Logo

Real-time Speech Emotion Detection

This project focuses on the development of conversational analytics and AI solutions for Seasalt.ai, aimed at analyzing real-world speech data for insights. Multiple Machine Learning models were implemented, with Convolutional Neural Networks (CNN) demonstrating the highest accuracy improvement of approximately 67%. The CNN model effectively identifies emotions from audio data clips, enhancing conversational analytics within Seasalt.ai's product SeaMeet. Extensive experiments and evaluations have been conducted to validate the effectiveness of the CNN-based approach, showcasing its potential for real-time applications such as affective computing, virtual assistants, and emotion-aware human-computer interaction.
Project Logo

See-weed: Detecting Storefront Advertising of Age-restricted Retailers

The youth across King County are rampantly being exposed to age-restricted products like Marijuana, Tobacco, Vapes etc. To address the issue, we partnered with King County and built a computer vision model that analyzes the storefront images of age-restricted retailers and categorizes them into different groups based on advertisement aggressiveness or intensity. The advertisement intensity groups are classified as ‘High’, ‘Medium’, and ‘Low’. The results will help recommend suitable actions to create a safer advertising space. This will also enable various regulatory bodies to create awareness among the youth and bring necessary policy reforms to prevent unhealthy advertising.