Abstract
The Failure Detection algorithm based on Fuzzy Neural Network (FDD-FNN) method is proposed for effective detection of Wireless Sensor Network (WSN) system failures. In this method, the failure detection method for WSN and the minimum deviation optimization model based on the principle component analysis-Bayes discriminant analysis (PCA-BDA) and feature information entropy are proposed, input layer, fuzzy layer, fuzzy rule layer and ambiguity layer are designed, and the algorithm processes is introduced. Finally, the effects of key factors of FDD-FNN were investigated using simulations and its performance was compared with those of conventional algorithms. The results indicated excellent adaptability of FDD-FNN.
Similar content being viewed by others
References
Hu, R., Dong, X., & Wang, D. (2015). Defense mechanism against node replication attacks and sybil attacks in wireless sensor networks. Acta Electronica Sinica, 43(4), 743–752.
Fei, H., Xiao, F., & Li, G. (2017). An anomaly detection method of wireless sensor network based on multi-modals sata stream. Chinese Journal of Computers, 40(8), 1829–1842.
Li, Y., Jia, Z., & Xie, S. (2014). Partial dynamic reconfigurable WSN node with power and area efficiency. Journal of Computer Research and Development, 51(1), 173–179.
Chang, F., Cui, J., & Wang, L. (2017). A traceable and anonymous authentication scheme based on elliptic curve for wireless sensor network. Journal of Computer Research and Development., 54(9), 2011–2020.
Wang, G., Zeng, P., & Xiao, J. (2012). Link quality realtime evaluation algorithm oriented to industry wireless sensor network. Journal of Chinese Computer System, 33(5), 1079–1082.
Chen, Y., Wu, K., & Li, X. (2013). A kind of outlier mining algorithm based on information entropy. Control and Decision, 28(6), 867–872.
He, D., Li, R., & Zhu, J. (2013). Plastic bearing fault diagnosis based on a two-step data mining approach. IEEE Transactions on Industrial Electronics, 60(8), 3429–3440.
Zhao, W., Zhang, Q., Kuang, C., et al. (2015). Optimal design for diagnosis strategy based on multi-valued test. Computer Measurement & Control, 23(12), 3936–3939.
Lu, Q., & Chu, Y. (2013). Fault data optimization mining algorithm based on theory of prediction decision homomorphism. Computer Science, 40(7), 232–235.
Qiu, X., & Libo, L. (2016). Sequential fault diagnosis with isolation rate requirement using different evolution algorithm. Journal of Data Acquisition and Processing, 31(6), 1132–1140.
Yang, Y., & Qiu, W. (2017). Fuzzy session association rule mining algorithm based on time decay model. Application Research of Computers, 34(1), 128–131.
Houyan, L. (2017). A fuzzy association rule mining algorithm based on master–slave architecture and GA. Control Engineering of China, 24(2), 276–282.
Chen, J., Lin, X., Zheng, H., et al. (2017). A novel cluster center fast determination clustering algorithm. Applied Soft Computing, 57, 539–555.
Yang, Y. (2016). Improved K-means dynamic clustering algorithm based on information entropy. Journal of Chongqing University of Posts and Telecommunications (Natural Science Edition), 28(2), 254–259.
Zheng, H., & Chenken, P. (2017). An incremental dynamic clustering method based on the representative points and the density peaks. Journal of ZheJiang University of Technology, 45(4), 427–433.
de Souza, C. E., & Coutinho, D. (2014). Robust stability and control of uncertain linear discrete-time periodic systems with time-delay. Automatica, 50(2), 431–441.
Ricks, B., & Mengshoel, O. J. (2014). Diagnosis for uncertain dynamic and hybrid domains using Bayesian networks and arithmetic circuits. International Journal of Approximate Reasoning, 55(5), 1207–1234.
Hu, R., Xu, W., & Gan, L. (2013). Incremental sequential learning for fuzzy neural networks. PR&AI, 26(8), 794–800.
Guo, Y., & Wang, L. (2011). A hybrid wavelet neural network blind equalization algorithm based on fuzzy controlling. Acta Electronica Sinica, 39(4), 975–980.
Sheng, J., Qi, B., Yang, Z., et al. (2013). Access selection algorithm for heterogeneous wireless networks based on rough set and analytic hierarchy process. Computer Application and Software, 30(2), 133–140.
Acknowledgements
This work is supported by Special Funds of Applied Science and Technology Research and Development of Guangdong Province, China (Grant No. 2015B010128015).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Xu, B., Zhang, X. & Liu, L. The Failure Detection Method of WSN Based on PCA-BDA and Fuzzy Neural Network. Wireless Pers Commun 102, 1657–1667 (2018). https://doi.org/10.1007/s11277-017-5225-9
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11277-017-5225-9