Cadence: A Practical Time-series Partitioning Algorithm for Unlabeled IoT Sensor Streams

1 code implementation • 6 Dec 2021 • Tahiya Chowdhury, Murtadha Aldeer, Shantanu Laghate, Jorge Ortiz

We show that by learning a representation specifically with the segmentation objective based on maximum mean discrepancy (MMD), our algorithm can robustly detect time-series events across different applications.

Activity Recognition Change Point Detection +2