Data Preprocessing of Agricultural IoT Based on Time Series Analysis

  • Yajie Ma
  • Jin JinEmail author
  • Qihui Huang
  • Feng Dan
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10954)


Large-scale agricultural internet of things will generate a large amount of data every moment. After a certain period of time, the amount of data can reach hundreds of millions. It is very meaningful to analyze and mine agricultural big data and replace artificial experience with analysis results. However, the agricultural production environment is complex, and the raw data collected include a variety of anomalies, which can not be directly followed by analysis and mining. In this paper, a data preprocessing method based on time series analysis is proposed, which can quickly and efficiently obtain the prediction model, and can be used to fill and replace the abnormal data. On this basis, we add data preprocessing layer to the traditional three-layer Internet of things system (IoT), which is located between the application layer and the transmission layer, and designs a four layer of Agricultural IoT system. The system not only realizes the basic functions of data acquisition, transmission and storage, but also provides better data sources for subsequent analysis.


Agricultural IoT Time series analysis Data preprocessing 


  1. 1.
  2. 2.
    Hubei Provincial Government. Accessed 23 Mar 2017
  3. 3.
    Han, J., Kamber, M.: Data Mining Concept and Techniques. Machinery Industry Press, Cambridge (2001)Google Scholar
  4. 4.
    Yan, R., Liu, Y., Gao, R.X.: Correlation dimension analysis: a non-linear time series analysis for data processing. Instrum. Meas. Mag. IEEE 13(6), 19–25 (2010)CrossRefGoogle Scholar
  5. 5.
    Shi, D.L.: Research and design of intelligent agriculture management system based on the internet of things. Appl. Mech. Mater. 687–691, 1868–1871 (2014)CrossRefGoogle Scholar
  6. 6.
    Fang, S., Xu, L.D., Zhu, Y., et al.: An integrated system for regional environmental monitoring and management based on internet of things. IEEE Trans. Industr. Inf. 10(2), 1596–1605 (2014)CrossRefGoogle Scholar
  7. 7.
    Wixted, A.J, Kinnaird, P., Larijani, H., et al.: Evaluation of LoRa and LoRaWAN for wireless sensor networks. Sensors. IEEE, pp. 1–3 (2017)Google Scholar
  8. 8.
    Silva, J.D.C., Rodrigues, J.J.P.C., Alberti, A.M., et al.: LoRaWAN—A low power WAN protocol for internet of things: a review and opportunities. In: International Multidisciplinary Conference on Computer and Energy Science. IEEE (2017)Google Scholar
  9. 9.
    Rojas, I., Pomares, H.: Time series analysis and forecasting. Contributions to Statistics (2016)Google Scholar
  10. 10.
    Shumway, R.H., Stoffer, D.S.: Time series analysis and its applications. Publ. Am. Stat. Assoc. 97(458), 656–657 (2013)Google Scholar
  11. 11.
    Liu, L., Luan, R.S., Yin, F., et al.: Predicting the incidence of hand, foot and mouth disease in Sichuan province, China using the ARIMA model. Epidemiol. Infect. 144(1), 144–151 (2016)CrossRefGoogle Scholar
  12. 12.
    Anghelache, C., Grabara, J., Manole, A.: Using the dynamic model ARMA to forecast the macroeconomic evolution. Romanian Statistical Review Supplement (2016)Google Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  1. 1.College of Information Science and EngineeringWuhan University of Science and TechnologyWuhanChina
  2. 2.Engineering Research Center for Metallurgical Automation and Detecting Technology, Ministry of EducationWuhanChina

Personalised recommendations