Open Access iconOpen Access

ARTICLE

crossmark

Sensor Location Optimisation Design Based on IoT and Geostatistics in Greenhouse

Yang Liu1,3, Xiaoyu Liu2,3, Xiu Dai1, Guanglian Xun1, Ni Ren1,*, Rui Kang1,4, Xiaojuan Mao1

1 Information Center, Jiangsu Academy of Agricultural Sciences, Nanjing, 210014, China
2 Jiangsu Vocational College of Agriculture and Forestry, Jurong, 212400, China
3 Key Laboratory of Agro-Environment in Downstream of Yangtze Plain, Ministry of Agriculture and Rural Affairs/Institute of Agricultural Resources and Environment, Jiangsu Academy of Agricultural Sciences, Nanjing, 210014, China
4 U. S. National Poultry Research Center, Agricultural Research Service, United States Department of Agriculture, Athens, GA 30605, USA

* Corresponding Author: Ni Ren. Email: email

Intelligent Automation & Soft Computing 2022, 33(3), 1653-1663. https://doi.org/10.32604/iasc.2022.017049

Abstract

Environmental parameters such as air temperature (T) and air relative humidity (RH) should be intensively monitored in a greenhouse in real time. In most cases, one set of sensors is installed in the centre of a greenhouse. However, as the microclimate of a greenhouse is always heterogeneous, the sensor installation location is crucial for practical cultivation. In this study, the T and RH monitoring performance of different sensors were compared. Two types of real-time environmental sensors (Air Temperature and Humidity sensor and Activity Monitoring sensor, referred as ATH and AM) were selected and calibrated by reliable non-real-time sensors (Honest Observer By Onset sensor, referred as HOBO). The results showed that T and RH were variable in a small greenhouse area (128 m2). ATH had better T and RH monitoring performance than AM using HOBO as a reference (R2 = 0.968 and 0.938 for T; 0.594 and 0.538 for RH, respectively, for ATH and AM). In terms of cost, it is more efficient to use more sets of AMs (15 sets were used in this case study) to establish an intensive monitoring system based on the Internet of Things (IoT) compared with that of ATH. Then, the optimal sensor installation location was decided using geostatistics. Based on a simulated monitoring data set, the optimal sensor installation location was determined to be 1.57 m away from the physical centre of the monitoring area. By combining IoT with geostatistics, this study offers a method for effective monitoring of environmental parameters in a practical greenhouse system with a three-step procedure.

Keywords


Cite This Article

Y. Liu, X. Liu, X. Dai, G. Xun, N. Ren et al., "Sensor location optimisation design based on iot and geostatistics in greenhouse," Intelligent Automation & Soft Computing, vol. 33, no.3, pp. 1653–1663, 2022.



cc This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
  • 1031

    View

  • 547

    Download

  • 0

    Like

Share Link