Welcome to the InfoSci Platform
Internet of Things-Based Agricultural Mechanization Using Neural Network Extreme Learning on Rough Set

Internet of Things-Based Agricultural Mechanization Using Neural Network Extreme Learning on Rough Set

Jian Chen, Xiaohua Chen, Qingyan Zeng, Ishbir Singh, Amit Sharma
Copyright: © 2021 |Volume: 12 |Issue: 2 |Pages: 15
ISSN: 1947-3192|EISSN: 1947-3206|EISBN13: 9781799861591|DOI: 10.4018/IJAEIS.20210401.oa2
Cite Article Cite Article

MLA

Chen, Jian, et al. "Internet of Things-Based Agricultural Mechanization Using Neural Network Extreme Learning on Rough Set." IJAEIS vol.12, no.2 2021: pp.15-29. http://doi.org/10.4018/IJAEIS.20210401.oa2

APA

Chen, J., Chen, X., Zeng, Q., Singh, I., & Sharma, A. (2021). Internet of Things-Based Agricultural Mechanization Using Neural Network Extreme Learning on Rough Set. International Journal of Agricultural and Environmental Information Systems (IJAEIS), 12(2), 15-29. http://doi.org/10.4018/IJAEIS.20210401.oa2

Chicago

Chen, Jian, et al. "Internet of Things-Based Agricultural Mechanization Using Neural Network Extreme Learning on Rough Set," International Journal of Agricultural and Environmental Information Systems (IJAEIS) 12, no.2: 15-29. http://doi.org/10.4018/IJAEIS.20210401.oa2

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

Recently, the basic functioning of monitoring in internet of things (IoT) is to apply the monitored data to the database for the regular analysis through mobile or computer platform. The purpose of this article is to highlight the application scope of IoT knowledge and to present the model of agricultural IoT for prediction by studying the influence of IoT technology towards modern agriculture. In order to explore the uncertain characteristics of the development of agricultural mechanization, the evaluation index system is simplified through the existing rough set theory. The neural network model is established with five random provinces and cities in 31 provinces and municipalities as test samples. By comparing the data of the neural network model established before and after the reduction, the results show that the index coefficient is reduced by about 60% based on the fixed information before and after the reduction. The simulation evaluation accuracy established by the artificial neural network model is 100%, which is consistent with the results of the original index system.