Ph.D. Candidate |
TODS: An Automated Time Series Outlier Detection System We build TODS, an automated Time Series Outlier Detection System for research and industrial applications. It currently supports 70 primitives, including data processing, time series processing, feature analysis, detection algorithms, and a reinforcement module. TODS is a highly modular system that supports easy pipeline construction.
|
BED: A Real-Time Object Detection System for Edge Devices
|