Outlier detection method based on standard scores

DOI

10.2991/eeeis-16.2017.124How to use a DOI?

Keywords

Wireless sensor networks; Abnormal; Standard score; Moving range

Abstract

Agricultural monitoring data is the basis of environmental early warning, however, abnormal data is inevitable in the monitoring process. Aiming at the problem that the data of wireless sensor network is abnormal, an outlier detection method is proposed, in order to achieve the purpose of accurate calibration data. The method is optimized by using the theory of MovingRange and standard scores, which greatly reduces the time complexity and space complexity of the algorithm. Real application results show that the abnormal data detected by this method are basically consistent with the actual situation and the accuracy is over 90%. The experimental results suggest that this method can effectively complete the detection of abnormal data which is mass and the deviation of the characteristics is not obvious.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Ya-Nan Wang
PY  - 2016/12
DA  - 2016/12
TI  - Outlier detection method based on standard scores
BT  - Proceedings of the 2nd Annual International Conference on Electronics, Electrical Engineering and Information Science (EEEIS 2016)
PB  - Atlantis Press
SP  - 1012
EP  - 1017
SN  - 2352-5401
UR  - https://doi.org/10.2991/eeeis-16.2017.124
DO  - 10.2991/eeeis-16.2017.124
ID  - Wang2016/12
ER  -