Targeted Event Detection

TL;DR

This paper introduces a method for creating targeted event detectors that leverage labeled training data to identify the onset of interesting events in multivariate data streams, aiming for rapid and accurate detection.

Contribution

It presents a novel approach to designing event detectors that are specifically tuned to the characteristics of interesting events using supervised training data.

Findings

Effective detection of interesting events in data streams

Reduced false alarms by focusing on relevant changes

Improved detection speed compared to generic methods

Abstract

We consider the problem of event detection based upon a (typically multivariate) data stream characterizing some system. Most of the time the system is quiescent - nothing of interest is happening - but occasionally events of interest occur. The goal of event detection is to raise an alarm as soon as possible after the onset of an event. A simple way of addressing the event detection problem is to look for changes in the data stream and equate `change' with `onset of event'. However, there might be many kinds of changes in the stream that are uninteresting. We assume that we are given a segment of the stream where interesting events have been marked. We propose a method for using these training data to construct a `targeted' detector that is specifically sensitive to changes signaling the onset of interesting events.