2012 | OriginalPaper | Chapter
High-Level Event Detection in Spatially Distributed Time Series
Authors : Avinash Rude, Kate Beard
Published in: Geographic Information Science
Publisher: Springer Berlin Heidelberg
Activate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
This paper presents an approach for the detection of high-level events from spatially distributed time series. The objective is to detect spatially evolving high-level events as aggregate patterns of primitive events. The approach starts with a segmentation of time series into primitive events as building blocks for high-level events. A high-level event ontology is then used to specify the composition of high-level events of interest in terms of initiating, body forming, and terminating primitive events. We illustrate the approach first with simulated time series data to identify traffic congestion events and then with real data to identify storm events from sensor time series collected as part of an ocean observing system deployed in the Gulf of Maine. Detected storm events are compared against NCDC reported storm events as an evaluation of the approach.