A multisensor system in coal mine is composed of a dozen even dozens of gas monitoring sensors. There is coupling in sensors of the gas monitoring systems. And it is interesting. The paper focuses on two topics about correlation analysis for multisensor system. One is about multisensor correlation analysis. Correlation information entropy and condition number of matrix were used. The other is about how to effective find out all combinations correlation sensors in a multisensor system. A theorem was proposed in this paper. Based on the theorem, an algorithm which can find out all combinations of correlative sensors from a multisensor system is proposed. Proposed algorithm can not only find out all combinations of correlation sensors effectively, but obtain the maximum combination of correlation sensors. Through experiment on a real gas monitoring dataset in coal mine, the results of experiments show that performances of proposed algorithm are excellent.
[1]
Philip S. Yu,et al.
Local Correlation Tracking in Time Series
,
2006,
Sixth International Conference on Data Mining (ICDM'06).
[2]
Yi Shen,et al.
A quantitative method to evaluate the performance of hyperspectral data fusion
,
2002,
IMTC/2002. Proceedings of the 19th IEEE Instrumentation and Measurement Technology Conference (IEEE Cat. No.00CH37276).
[3]
Yi Shen,et al.
A fast method to evaluate the performances of image fusion techniques and its error analysis
,
2003,
Proceedings of the 20th IEEE Instrumentation Technology Conference (Cat. No.03CH37412).
[4]
Cyrus Shahabi,et al.
On the stationarity of multivariate time series for correlation-based data analysis
,
2005,
Fifth IEEE International Conference on Data Mining (ICDM'05).