Segregating event streams and noise with a Markov renewal process model

TL;DR

This paper introduces a novel method for clustering timestamped event data into multiple sequences with varying rates, effectively distinguishing signal from noise using a Markov renewal process model, demonstrated on synthetic and real bird tracking data.

Contribution

It develops a new inference approach for identifying multiple, varying-rate Markov renewal processes amidst noise, surpassing fixed-rate assumptions of prior methods.

Findings

Successfully clustered synthetic event streams.

Effectively tracked bird singing sources.

Distinguished signal from noise in complex data.

Abstract

We describe an inference task in which a set of timestamped event observations must be clustered into an unknown number of temporal sequences with independent and varying rates of observations. Various existing approaches to multi-object tracking assume a fixed number of sources and/or a fixed observation rate; we develop an approach to inferring structure in timestamped data produced by a mixture of an unknown and varying number of similar Markov renewal processes, plus independent clutter noise. The inference simultaneously distinguishes signal from noise as well as clustering signal observations into separate source streams. We illustrate the technique via a synthetic experiment as well as an experiment to track a mixture of singing birds.