Semantic preprocessing for mining sensor streams from heterogeneous environments

TLDR: An ontology-based data preprocessing scheme, which is composed of two main phases: (i) session identification and (ii) error detection, which can find out not only relationships between sensor streams but also temporal dynamics of a data stream.

Abstract: ? A number of heterogeneous sensor streams have been efficiently pre-processed for better services. Many studies have tried to employ data mining methods to discover useful patterns and knowledge from data streams on sensor networks. However, it is difficult to apply such data mining methods to the sensor streams intermixed from heterogeneous sensor networks. In this paper, to improve the performance of conventional data mining methods, we propose an ontology-based data preprocessing scheme, which is composed of two main phases: (i) session identification and (ii) error detection. The ontology can provide and describe semantics of data measured by each sensor. Thus, by comparing the semantics, we can find out not only relationships between sensor streams but also temporal dynamics of a data stream. To evaluate the proposed method, we have collected sensor streams from in our building during 30days. By using two well-known data mining methods (i.e., co-occurrence pattern and sequential pattern), the results from raw sensor streams and ones from sensor streams with preprocessing were compared with respect to two measurements recall and precision.