Integration of classification algorithms and control chart techniques for monitoring multivariate processes

Abstract

We propose new multivariate control charts that can effectively deal with massive amounts of complex data through their integration with classification algorithms. We call the proposed control chart the ‘Probability of Class (PoC) chart’ because the values of PoC, obtained from classification algorithms, are used as monitoring statistics. The control limits of PoC charts are established and adjusted by the bootstrap method. Experimental results with simulated and real data showed that PoC charts outperform Hotelling's T ² control charts. Further, a simulation study revealed that a small proportion of out-of-control observations are sufficient for PoC charts to achieve the desired performance.

Keywords:

• data mining
• Hotelling's T ²
• multivariate statistical process control
• supervised classification method

Acknowledgements

We thank the editor and referees for their constructive comments and suggestions, which greatly improved the quality of the paper. This work was supported by National Research Foundation of Korea Grant 20100003811.