2011 | OriginalPaper | Buchkapitel
A Relational Approach to Sensor Network Data Mining
verfasst von : Floriana Esposito, Teresa M. A. Basile, Nicola Di Mauro, Stefano Ferilli
Erschienen in: Information Retrieval and Mining in Distributed Environments
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
In this chapter a relational framework able to model and analyse the data observed by nodes involved in a sensor network is presented. In particular, we propose a powerful and expressive description language able to represent the spatio-temporal relations appearing in sensor network data along with the environmental information. Furthermore, a general purpose system able to elicit hidden frequent temporal correlations between sensor nodes is presented. The framework has been extended in order to take into account interval-based temporal data by introducing some operators based on a temporal interval logic. A preliminary abstraction step with the aim of segmenting and labelling the real-valued time series into similar subsequences is performed exploiting a kernel density estimation approach. The prposed framework has been evaluated on real world data collected from a wireless sensor network.