• DocumentCode
    1571782
  • Title

    A multiple linear regression data predicting method using correlation analysis for wireless sensor networks

  • Author

    Yan Xiaozhen ; Xie Hong ; Tong, Wang

  • Author_Institution
    Coll. of Inf. & Commun. Eng., Harbin Eng. Univ., Harbin, China
  • Volume
    2
  • fYear
    2011
  • Firstpage
    960
  • Lastpage
    963
  • Abstract
    For there are too many drawbacks like excessive input variables, high computational complexity and low efficiency in evaluation methods of missing data for wireless sensor network, A Multiple-Regression evaluation method based on correlation analysis was proposed in this paper. First, the sensor data of the wireless sensor networks was correlatively analyzed, and most correlation sensor data was explored. Then the sensor data was used as input of the multiple linear Regression model and evaluation method. In the experimental stage, the sensor temperature data of actual wireless sensor network has been used to test this method. Experiment results show that the scheme is efficient with low prediction error, thus it owns practical value and can be used to evaluate the missing data in wireless sensor networks.
  • Keywords
    communication complexity; correlation methods; regression analysis; wireless sensor networks; computational complexity; correlation analysis; correlation sensor data; multiple linear regression data predicting method; multiple linear regression model; multiple-regression evaluation method; prediction error; sensor temperature data; wireless sensor networks; Accuracy; Computational modeling; Correlation; Predictive models; correlation analysis; data prediction; multiple linear regression; wireless sensor network;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Cross Strait Quad-Regional Radio Science and Wireless Technology Conference (CSQRWC), 2011
  • Conference_Location
    Harbin
  • Print_ISBN
    978-1-4244-9792-8
  • Type

    conf

  • DOI
    10.1109/CSQRWC.2011.6037116
  • Filename
    6037116