search for




 

Sensor anomaly detection system in greenhouse-type smart farm using environmental data
Journal of the Korean Data & Information Science Society 2021;32:1237-48
Published online November 30, 2021;  https://doi.org/10.7465/jkdi.2021.32.6.1237
© 2021 Korean Data and Information Science Society.

Cheol Won Lee1 · Su-Yong An2 · Jae-Young Kim3 · Hyeongtae Ahn4

123Department of Smart Farm Application Research, Electronics and Telecommunications Research Institute
4Department of Computer Engineering, Kumoh National Institute of Technology
Correspondence to: 1 Researcher, Electronics and Telecommunications Research Institute (ETRI), Daegu 42995, Korea.
2 Senior researcher, Electronics and Telecommunications Research Institute (ETRI), Daegu 42995, Korea.
3 Principal researcher, Electronics and Telecommunications Research Institute (ETRI), Daegu 42995, Korea.
4 Corresponding author: Assistant professor, Kumoh National Institute of Technology (KIT), Gumi 39177, Korea. E-mail: anten@kumoh.ac.kr
This work was supported by the Electronics and Telecommunications Research Institute (ETRI) Grant through the research operation support project (Artificial intelligence-based smart farm integrated solution technology development) under Grant 21ZD1150.
Received August 10, 2021; Revised September 16, 2021; Accepted September 25, 2021.
This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
Abstract
With the recent 4th industrial revolution, in the agricultural sector, the supply of greenhouse-type smart farm, which combines the existing information and communication technologies with cutting-edge technologies such as big data, artificial intelligence, and the Internet of Things, is spreading. The greenhouse-type smart farm measures the current greenhouse environment by using sensors, identifies the necessary greenhouse control based on this information, and executes environmental control through actuators. However, if a measurement error occurs in a sensor, it causes incorrect environmental control and inhibits crop growth. Therefore, reliability of the sensor measurement values is essential in greenhouse-type smart farms. When an abnormality occurs in the sensor measurement value, it should be possible to quickly detect it. This study generates a predictive model for sensor measurement values by learning environmental data, such as measurement values of various sensors and state information of actuators, collected from a greenhouse-type smart farm utilizing multiple regression analysis. Based on the prediction model, we propose a system to verify the reliability of the sensor by comparing the predicted value of the sensor with the actual measured value.
Keywords : Anomaly detection, environmental data, multiple regression analysis, smart farm.