Correlation approximate entropy and its application to data fault detection in sensor networks

被引：0
|
作者：
Zhang Z. [1 ]
Li S. [1 ]
Li Z. [1 ]
机构：
[1] School of Computer Science and Technology, Northwestern Polytechnical University, Xi'an
来源：
Huazhong Keji Daxue Xuebao (Ziran Kexue Ban)/Journal of Huazhong University of Science and Technology (Natural Science Edition) | 2016年 / 44卷 / 02期
关键词：
Correlation approximate entropy; Correlation information entropy; Data fault detection; Fuzzy approximate entropy; Wireless sensor network;
D O I：
10.13245/j.hust.160218
中图分类号：
学科分类号：
摘要：
Fuzzy approximate entropy (FuzzyEn) is heavily dependent on parameter selection and its computational complexity is large when measuring the time series regularity. To solve this problem, a novel method called correlation approximate entropy (CoApEn) was proposed and it was applied to data fault detection in sensor networks. CoApEn employed the correlation information entropy to measure the strength of multivariable correlation. And it is the negative natural logarithm of the conditional probability that the multivariable system keeps the correlation when the number of variables is increased from M to M+1. Compared with FuzzyEn, the number of parameters that CoApEn dependent on reduces from 4 to 2 and the computational complexity is decreased. Finally collected sensor data was used to perform experiments on CoApEn and it was compared with other feature generated methods. The experimental results show that CoApEn can outperform other compared methods significantly and reduce the time spent on generating feature greatly. © 2016, Editorial Board of Journal of Huazhong University of Science and Technology. All right reserved.
引用
收藏
页码：86 / 91
页数：5
相关论文
共 19 条
  • [1] Mo L., He Y., Liu Y., Et al., Canopy closure estimates with GreenOrbs: sustainable sensing in the forest, Proceedings of the 7th ACM Conference on Embedded Networked Sensor Systems, pp. 99-112, (2009)
  • [2] Ma J., Zhou X., Li S., Et al., Connecting agriculture to the internet of things through sensor networks, Proc of 2011 IEEE International Conferences on Internet of Things and Cyber, Physical and Social Computing, pp. 184-187, (2011)
  • [3] Tavakoli A., Kansal A., Nath S., On-line sensing task optimization for shared sensors, Proceedings of the 9th ACM/IEEE International Conference on Information Processing in Sensor Networks, pp. 47-57, (2010)
  • [4] Tolle G., Polastre J., Szewczyk R., Et al., A macroscope in the redwoods, Proceedings of the 3rd International Conference on Embedded Networked Sensor Systems, pp. 51-63, (2005)
  • [5] Sharma A.B., Golubchik L., Govindan R., Sensor faults: detection methods and prevalence in real-world datasets, ACM Transactions on Sensor Networks, 6, 3, pp. 1-39, (2010)
  • [6] Szewczyk R., Mainwaring A., Polastre J., Et al., An analysis of a large scale habitat monitoring application, Proceedings of the 2nd International Conference on Embedded Networked Sensor Systems, pp. 214-226, (2004)
  • [7] Ni K., Ramanathan N., Chehade M.N.H., Et al., Sensor network data fault types, ACM Transactions on Sensor Networks, 5, 3, pp. 1-29, (2009)
  • [8] Warriach E.U., Aiello M., Tei K., A machine learning approach for identifying and classifying faults in wireless sensor networks, Proceedings of 15th IEEE International Conference on Computational Science and Engineering, pp. 618-625, (2012)
  • [9] Pincus S.M., Approximate entropy as a measure of system complexity, Proceedings of the National Academy of Sciences, 88, 6, pp. 2297-2301, (1991)
  • [10] Pincus S.M., Goldberger A.L., Physiological time-series analysis: what does regularity quantify?, American Journal of Physiology, 266, pp. 1643-1656, (1994)
12