Research Posters Archive

Real-Time Change Point Detection in Molecular Dynamics Streaming Data

Authors: Vijayalakshmi Saravanan (University of South Dakota) and Shinjae Yoo, Hubertus Van Dam, Christopher Kelly, Thomas Flynn, Perry Siehien, Kalyan Muppudojo, and Aniket Kumar Ramesh (Brookhaven National Laboratory)

Abstract: The uniform sampling of molecular dynamics (MD) simulations may not accurately capture crucial scientific events. Deep learning approaches are being developed to detect these events within streaming data but can take significant resources on large datasets (PB+). To address these limitations, we propose a solution based on streaming manifold learning, specifically the Kernel CUSUM (KCUSUM) algorithm. By leveraging KCUSUM, we can overcome the limitations of uniform sampling in MD simulations, as it compares incoming data with samples from a reference distribution. It utilizes a statistic derived from the Maximum Mean Discrepancy (MMD) non-parametric testing framework. This algorithm has been tested in various use cases, demonstrating its ability to significantly reduce data rates without missing important scientific events.

Best Poster Finalist (BP): no

Poster: PDF
Poster summary: PDF


Back to Poster Archive Listing