As artificial intelligence and machine learning continue to evolve, the need for efficient search and retrieval mechanisms for unstructured data has grown exponentially. Traditional relational databases, optimized for structured queries, struggle with the high-dimensional nature of modern AI-generated embeddings. This challenge has led to the rise of vector databases, specialized systems designed to store, index, and retrieve data based on similarity rather than exact matching.

This symposium explores the fundamental concepts of vector databases, their key components—such as vector embeddings, indexing techniques, and similarity search algorithms—and their advantages over traditional databases. We discuss how vector search operates using distance metrics like cosine similarity and Euclidean distance and compare the roles of vector databases and standalone vector indexes.

This project presents an interactive forecasting tool for Influenza-like Illness (ILI) trends using historical CDC data and machine learning models. Built with Python and Streamlit, the app enables users to visualize yearly ILI patterns, compare predictive models, and forecast future cases based on recent trends. Three models — Linear Regression, Random Forest, and XGBoost — were evaluated using Root Mean Squared Error (RMSE) and R² Score. Surprisingly, Linear Regression achieved the best performance with an RMSE of 0.106 and R² of 0.960, indicating that simple models can be effective for this type of time-series data. The app also includes features for dynamic forecasting and CSV export, making it a practical tool for public health analysis and planning.

Our client, Trailspur Capital Partners, is a real estate investment company based in Texas. We assist the company by building a database about commercial / industrial real estate to manage the market more easily and better decision-making. The business requires both the Geographic data from the County’s officials and the properties listings with vacancies information. Our goal is to design a database that can handle the aggregate data coming from both sources, which includes arranging and categorizing the properties, coming with several built-in functions namely identifying listings / vacancy changes, before deploying everything to the server. Our frontend, built with Vite and Vue, provides a smooth and interactive user experience while on the backend, we utilize AWS Lambda with Python to automate essential tasks, including downloading official county appraisal data, performing spatial merges using GIS functions, and managing our Supabase database. After successfully aggregating real estate data from both sources into a structured database, which enables easier tracking of property status changes, the platform efficiently processes and visualizes real-time property listings, allowing our client to analyze market trends and make data-driven investment decisions. Our project enhances real estate market intelligence for Trailspur Capital Partners. The system’s automated functions minimize manual workload and improve the accuracy of property tracking, providing a scalable solution for future expansion.

Cognitive Behavioral Therapy often relies on patients consistently completing therapeutic homework, regularly assigned by their therapist. A leading cause of Cognitive Behavioral Therapy failure for patients is non-compliance with their assigned therapeutic homework. About 20%-50% of patients fail to complete assignments due to inconvenience, a lack of clear instructions, or forgetting to finish the assignment. MENDmate is an online platform designed to solve this problem by providing a streamlined user experience for homework assignment and completion. MENDmate allows providers to assign homework to their patients and monitor their progress. It also provides patients with the ability to track and complete their homework assignments. Additional features of MENDmate include a learning library that gives patients an opportunity to learn about mental illness and practice coping techniques, a journal that allows patients to record their experiences and daily mood and anxiety assessments. MENDmate also tracks and reports the patient's data trends such as completed assignment, mood level, and anxiety level, which allows both the therapist and the patient to keep track of their progress over time.

Fort Worth PsychWorks, a leading psychiatry office, provides comprehensive neuropsychological and psychological assessments for patients across all age groups. Currently, after administering a variety of cognitive and behavioral tests, psychiatrists must manually input the resulting data into report templates, a process that is both labor-intensive and inefficient. This manual approach can take between 45 minutes to two hours per report, detracting from the time available for direct patient care and reducing the clinic’s overall operational efficiency.
To address this challenge, our senior design project introduces an automated report generation system named the PsychWorks Report Generation System. This software solution empowers psychiatrists to select or customize templates tailored to individual patient needs, add or remove specific tests, and automatically generate detailed report text, tables, and charts based on input scores. By maintaining the flexibility of the existing Excel-based system while significantly reducing the time and effort required for report creation, the PsychReport Automator enhances the user experience for clinic staff, boosts the potential for billable hours, and ultimately supports improved patient outcomes.