Using deep belief network to construct the agricultural information system based on Internet of Things

To study the impact of the agricultural information system based on the Internet of Things (IoT) on the income of agricultural products, an agricultural information system was constructed based on the agricultural IoT technology, and its impact on the income of agricultural products was discussed through the deep belief network. First, the relevant theories of agricultural IoT were introduced. Then, an agricultural information system based on agricultural IoT technology was constructed, and a deep belief network model was proposed. The vegetable prices and influencing factors were collected. The data were distributed in the range of 0–1 after normalization. The collinearity between the data was eliminated through principal component analysis. Then, the principal component analysis of vegetable prices and influencing factors from 2015 to 2019 was performed. A total of 96 sample data of calibration set and 24 sample data of test machine were collected. The optimal number of hidden layers of the deep belief network model and the number of nodes contained in the hidden layer were obtained through experiments. The results show that the first, second, and third hidden layers have 8, 6, and 10 nodes, respectively; the prediction accuracy of the deep belief network model is more accurate than that of the BP neural network and wavelet neural network. Besides, the absolute value of the prediction error of the deep belief model is within 0.1, which has good prediction accuracy. In short, the deep belief model has a good development prospect in agricultural product price forecasting, and it can provide relevant reference for the establishment and research of other agricultural product price forecasting models.