Efficient Content-Based Audio Retrieval with Text Queries
Students: Jacob LogasThe goal of content-based audio retrieval is to find audio recordings based on acoustic features in place of user-generated tags. We improve accuracy using insights from state-of-the-art image querying techniques and a hierarchical representation of audio.
Facilitating Clinical Phenotype Development at Scale
Students: Christine Herlihy, Charity HiltonThis project aims to optimize an existing open-source platform for computational phenotyping, such that structured queries containing patient-level clinical selection criteria can be run more rapidly against a given database, without sacrificing accuracy.
Caching Statistical Queries: A Step Towards Automated Data Exploration
Students: Apaar ShankerExploratory statistical analysis of data requires repeated aggregation of data that precludes interactive analysis. We propose techniques for caching the results of queries to accelerate exploratory statistical analysis.
Towards Intelligent Data Profiling and Aggregation
Students: Nidhi Menon, Sneha VenkatachalamData scientists rely on data management systems for profiling data and conducting exploratory statistical analysis. This project focuses on techniques for accelerating these tasks.
Ranking Database Schema Smells
Students: Venkata Kishore Patcha, Varsha AcharDatabase applications often suffer from anti-patterns that limit their performance, security, and accuracy. This project aims to quantify the performance impact of various anti-patterns.
Fast Video Querying Framework
Students: Jaeho Bang, Siddharth BiswalVideo is rich in semantic information and is a rapidly expanding source of data at scale. This project aims to develop a system for accelerating video analytics.
Fixing Database Antipatterns
Students: Pooja Bhandary, Jennifer MaDatabase applications often suffer from anti-patterns that limit their performance, security, and accuracy. This project aims to find techniques for automatically fixing these anti-patterns.