Zhang Rihong, Li Xiaomin
College of Mechanical and Electrical Engineering, Zhongkai University of Agriculture and Engineering, Guangzhou 510225, China.
Sensors (Basel). 2021 Nov 11;21(22):7502. doi: 10.3390/s21227502.
In the context of smart agriculture, high-value data sensing in the entire crop lifecycle is fundamental for realizing crop cultivation control. However, the existing data sensing methods are deficient regarding the sensing data value, poor data correlation, and high data collection cost. The main problem for data sensing over the entire crop lifecycle is how to sense high-value data according to crop growth stage at a low cost. To solve this problem, a data sensing framework was developed by combining edge computing with the Internet of Things, and a novel data sensing strategy for the entire crop lifecycle is proposed in this paper. The proposed strategy includes four phases. In the first phase, the crop growth stage is divided by Gath-Geva (GG) fuzzy clustering, and the key growth parameters corresponding to the growth stage are extracted. In the second phase, based on the current crop growth information, a prediction method of the current crop growth stage is constructed by using a Tkagi-Sugneo (T-S) fuzzy neural network. In the third phase, based on Deng's grey relational analysis method, the environmental sensing parameters of the corresponding crop growth stage are optimized. In the fourth phase, an adaptive sensing method of sensing nodes with effective sensing area constraints is established. Finally, based on the actual crop growth history data, the whole crop life cycle dataset is established to test the performance and prediction accuracy of the proposed method for crop growth stage division. Based on the historical data, the simulation data sensing environment is established. Then, the proposed algorithm is tested and compared with the traditional algorithms. The comparison results show that the proposed strategy can divide and predict a crop growth cycle with high accuracy. The proposed strategy can significantly reduce the sensing and data collection times and energy consumption and significantly improve the value of sensing data.
在智慧农业的背景下，整个作物生命周期中的高价值数据感知是实现作物种植控制的基础。然而，现有的数据感知方法在感知数据价值、数据相关性差以及数据收集成本高方面存在不足。整个作物生命周期数据感知的主要问题是如何以低成本根据作物生长阶段感知高价值数据。为了解决这个问题，通过将边缘计算与物联网相结合开发了一种数据感知框架，并在本文中提出了一种全新的整个作物生命周期数据感知策略。所提出的策略包括四个阶段。在第一阶段，通过Gath-Geva（GG）模糊聚类划分作物生长阶段，并提取与该生长阶段对应的关键生长参数。在第二阶段，基于当前作物生长信息，利用Tkagi-Sugneo（T-S）模糊神经网络构建当前作物生长阶段的预测方法。在第三阶段，基于邓氏灰色关联分析方法，优化相应作物生长阶段的环境感知参数。在第四阶段，建立具有有效感知面积约束的传感节点自适应感知方法。最后，基于实际作物生长历史数据，建立整个作物生命周期数据集，以测试所提出的作物生长阶段划分方法的性能和预测准确性。基于历史数据，建立模拟数据感知环境。然后，对所提出的算法进行测试并与传统算法进行比较。比较结果表明，所提出的策略能够高精度地划分和预测作物生长周期。所提出的策略可以显著减少感知和数据收集次数以及能源消耗，并显著提高感知数据的价值。
