文献类型： 外文期刊

作者： Wang, Ya-Nan ¹ ;

作者机构： 1.Beijing Acad Agr & Forestry Sci, Beijing Res Ctr Informat Technol Agr, Beijing 100097, Peoples R China

2.Natl Engn Res Ctr Informat Technol Agr, Beijing 100097, Peoples R China

3.Minist Agr, Key Lab Agriinformat, Beijing 100097, Peoples R China

4.Beijing Engn Res Ctr Agr Internet Things, Beijing 100097, Peoples R China

关键词： Wireless sensor networks;Abnormal;Standard score;Moving range.

期刊名称：PROCEEDINGS OF THE 2ND ANNUAL INTERNATIONAL CONFERENCE ON ELECTRONICS, ELECTRICAL ENGINEERING AND INFORMATION SCIENCE (EEEIS 2016)

ISSN： 2352-5401

年卷期： 2016 年 117 卷

页码：

收录情况： SCI

摘要： 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.