Traffic Events Modeling for Structural Health Monitoring
Since 2008, a sensor network deployed on a major Dutch highway bridge has been monitoring various structural and environmental parameters, including strain, vibration and climate, at different locations along the infrastructure. The aim of the InfraWatch project is to model the structural health of the bridge by analyzing the large quantities of data that the sensors produce. This paper focus on the identification of traffic events (passing cars/trucks, congestion, etc.). We approach the problem as a time series subsequence clustering problem. As it is known that such a clustering method can be problematic on certain types of time series, we verified known problems on the InfraWatch data. Indeed, some of the undesired phenomena occurred in our case, but to a lesser extent than previously suggested. We introduce a new distance measure that discourages this observed behavior and allows us to identify traffic events reliably, even on large quantities of data.
KeywordsSensor Network Strain Measurement Structural Health Monitoring Strain Data Subsequence Cluster
Unable to display preview. Download preview PDF.
- 1.Fujimaki, R., Hirose, S., Nakata, T.: Theoretical analysis of subsequence time-series clustering from a frequency-analysis viewpoint. In: Proceedings of SDM 2008, pp. 506–517 (2008)Google Scholar
- 2.Höppner, F.: Time series abstraction methods - a survey. In: Informatik bewegt: Informatik 2002 - 32. Jahrestagung der Gesellschaft für Informatik e.v. (GI), pp. 777–786. GI (2002)Google Scholar
- 5.Knobbe, A., Blockeel, H., Koopman, A., Calders, T., Obladen, B., Bosma, C., Galenkamp, H., Koenders, E., Kok, J.: InfraWatch: Data management of large systems for monitoring infrastructural performance. In: Cohen, P.R., Adams, N.M., Berthold, M.R. (eds.) IDA 2010. LNCS, vol. 6065, pp. 91–102. Springer, Heidelberg (2010)CrossRefGoogle Scholar
- 6.White, T.: Hadoop, The Definite Guide. O’Reilly, Sebastopol (2009)Google Scholar