Distributed Anomaly Detection Method in Wireless Sensor Networks Based on Temporal-Spatial QSSVM

  • Zhili Chen
  • Huarui WuEmail author
  • Huaji Zhu
  • Yisheng Miao
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 905)


In Wireless Sensor Networks (WSNs), abnormal sensing data is easily generated due to factors such as the harsh working environment, sensor faults and external events. In order to enhance the detection rate of abnormal data and reduce the false positive rate, we propose a distributed anomaly detection method using one-class quarter-sphere support vector machine (QSSVM) based on temporal-spatial fusion in WSNs. Firstly, according to the synthetic data, the temporal-spatial QSSVM model is trained to determine the relevant parameters. Secondly, the trained QSSVM model is used to classify the streaming data in WSNs, and the abnormal data types are classified into noise, faults and events. Finally, the method decides whether to update the classification model based on whether the new sample has an effect on the boundary of the hypersphere. The experimental results illustrate that the proposed method has a detection rate of 96% compared with other three methods, and the false positive rate is only 14%.


Anomaly detection QSSVM Temporal-spatial Wireless sensor networks 



This work was supported by Natural Science Foundation of China (61471067, 61571051) and Beijing Natural Science Foundation (4172024, 4172026).


  1. 1.
    Zhang, Y., Meratnia, N., Havinga, P.: Outlier detection techniques for wireless sensor networks: a survey. IEEE Commun. Surv. Tutor. 12(2), 159–170 (2010)CrossRefGoogle Scholar
  2. 2.
    Ayadi, A., Ghorbel, O., Obeid, A.M., Abid, M.: Outlier detection approaches for wireless sensor networks: a survey. Comput. Netw. 129, 319–333 (2017)CrossRefGoogle Scholar
  3. 3.
    Fei, H., Xiao, F., Li, G.H., Sun, L.J.: An anomaly detection method of wireless sensor network based on multi-modals data stream. Chin. J. Comput. 40(8), 1829–1842 (2017). (in Chinese)Google Scholar
  4. 4.
    Sadik, S., Gruenwald, L.: Online outlier detection for data streams. In: IDEAS 2011, Proceedings of the 15th Symposium on International Database Engineering & Applications, pp. 88–96, 2011Google Scholar
  5. 5.
    Gil, P., Martins, H., Januário, F.: Detection and accommodation of outliers in wireless sensor networks within a multi-agent framework. Appl. Soft Comput. 42, 204–214 (2016)CrossRefGoogle Scholar
  6. 6.
    Yao, H.Q., Cao, H., Li, J.: Comprehensive outlier detection in wireless sensor network with fast optimization algorithm of classification model. Int. J. Distrib. Sens. Netw. 11(7), 1–20 (2015)CrossRefGoogle Scholar
  7. 7.
    Cheng, P., Zhu, M.H.: Lightweight anomaly detection for wireless sensor networks. Int. J. Distrib. Sens. Netw. 11(8), 1–8 (2015)Google Scholar
  8. 8.
    Rajasegarar, S., Leckie, C., Bezdek, J.C., Palaniswami, M.: Centered hyperspherical and hyperellipsoidal one-class support vector machines for anomaly detection in sensor networks. IEEE Trans. Inf. Forensics Secur. 5(3), 518–533 (2010)CrossRefGoogle Scholar
  9. 9.
    Zhang, Y., Meratnia, N., Havinga, P.: An online outlier detection technique for wireless sensor networks using unsupervised quarter-sphere support vector machine. In: 2008 International Conference on Intelligent Sensors, Sensor Networks and Information Processing, pp. 151–156 (2008)Google Scholar
  10. 10.
    Zhang, Y., Meratnia, N., Havinga, P.: Adaptive and online one-class support vector machine-based outlier detection techniques for wireless sensor networks. In: International Conference on Advanced Information Networking and Applications Workshops, pp. 990–995 (2009)Google Scholar
  11. 11.
    Xie, M., Hu, J.K., Guo, S.: Segment-based anomaly detection with approximated sample covariance matrix in wireless sensor networks. IEEE Trans. Parallel Distrib. Syst. 26(2), 574–583 (2015)CrossRefGoogle Scholar
  12. 12.
    Garg, S., Batra, S.: A novel ensembled technique for anomaly detection. Int. J. Commun. Syst. 30(11), 1–16 (2017)CrossRefGoogle Scholar
  13. 13.
    Li, M.: Study on algorithms for outlier detection in wireless sensor networks. Jiangsu University (2010)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Zhili Chen
    • 1
    • 2
  • Huarui Wu
    • 3
    Email author
  • Huaji Zhu
    • 3
  • Yisheng Miao
    • 3
  1. 1.National Engineering Research Center for Information Technology in AgricultureBeijingChina
  2. 2.College of Information and Electrical EngineeringChina Agricultural UniversityBeijingChina
  3. 3.Beijing Research Center for Information Technology in Agriculture, Beijing Academy of Agriculture and Forestry SciencesBeijingChina

Personalised recommendations