Abstract
The quality of information communication is the key guarantee for the normal operation of a system. Information filtering techniques and methods are important for system failure detection. Kalman filtering is a widely used method of optimal estimation as it is easy to computer programming and data can be updated and processed in real time. In this paper, the financial information system is taken for application of Kalman filtering in detecting the failure. Dynamic detecting models are established as the integration of a process model and a discriminant model. The process model is used to describe a dynamic process of financial failure and the discriminant model is used to describe discriminant rules. A real-time detection method is developed based on Kalman filtering and a general n-step-ahead forecasting algorithm is improved in order for the prospective forecast. The dynamic forecasting and detecting process is implemented through computer programming using the data of China’s communications industries. The results have proved the accuracy and advance of detecting financial failure in such case.
Similar content being viewed by others
References
Sun, J., & Li, H. (2009). Financial failure prediction using grey case-based reasoning optimized by genetic algorithm. Science Research Management, 30(2), 119–125.
Li, H., Li, C. J., Wu, X. J., et al. (2014). Statistics-based wrapper for feature selection: An implementation on financial failure identification with support vector machine. Applied Soft Computing, 19, 57–67.
Lin, F. Y., Liang, D., Yeh, C. C., et al. (2014). Novel feature selection methods to financial failure prediction. Expert Systems with Applications, 41, 2472–2483.
Kalman, R. E. (1960). A new approach to linear filtering and prediction problems. Journal of Basic Engineering, 82, 35–45.
Arnold, T., Bertus, M., & Godbey, J. M. (2008). A simplified approach to understanding the Kalman filter technique. Engineering Economist, 53(2), 140–155.
Shi, Y., & Fang, H. Z. (2010). Kalman filter-based identification for systems with randomly missing measurements in a network environment. International Journal of Control, 83(3), 538–551.
Li, Y., Rehtanz, C., Ruberg, S., et al. (2012). Assessment and choice of input signals for multiple HVDC and FACTS wide-area damping controllers. IEEE Transactions on Power Systems, 27(4), 1969–1977.
Rincón, F. D., Esposito, M., de Araújo, P. H. H., et al. (2013). Calorimetric estimation employing the unscented Kalman filter for a batch emulsion ploymerization reactor. Macromolecular Reaction Engineering, 7(1), 24–35.
Heij, C., Dijk, D. V., & Grognen, P. J. F. (2011). Real-time macroeconomic forecasting with leading indicators: An empirical comparison. International Journal of Forecasting, 27, 466–481.
Sun, X. L., Tian, Y. Z., & Wang, W. B. (2010). A financial distress state space dynamic model based on Kalman filtering. Journal of Systems and Management, 19(4), 408–414.
Sun, X. L. (2013). Dynamic early warning model based on a financial failure state space: An empirical study in China. China Soft Science, 4, 140–147.
Q. Zhuang, L.H. Chen, (2014). Dynamic prediction of financial failure based on Kalman filtering. Discrete Dynamics in Nature and Society, 1-10.
Li, L. J., Liu, J., & Sun, S. M. (2016). Study on the propagation and control of financial failure on the perception of supply chain. Chinese Journal of Management Science, 24(6), 46–51.
Acknowledgements
The authors acknowledge the National Natural Science Foundation of China (Grant: 71602188), the Key program of National Social Science Foundation of China (Grant: 15ZDB167).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Zhuang, Q. A Real-Time Detection Method of System Failure Based on Kalman Filtering. Wireless Pers Commun 102, 1461–1469 (2018). https://doi.org/10.1007/s11277-017-5205-0
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11277-017-5205-0