EventNet
Algorithm for the detection of “events of interest” in time series
Description:
Identifying and detecting “events of interest” is a common problem in time series processing. We propose an end-to-end event detection algorithm, based on deep learning, that directly works with events as learning targets, stepping away from ad-hoc postprocessing schemes (as are custom in classical approaches). Our event detection framework can easily be extended to other event detection problems in signal processing, since the deep learning backbone does not depend on any task-specific features.
More Information:
Originates from the AI-Driven Data Science research challenge (FAIR 2019–2023).
Responsible Research Lead: Alexander Bertrand
Authors: Nick Seeuws
Programming Language: Python
Categories: Time series, Supervised Learning