Path Attenuation of Prediction Wireless Sensor Network Signal in Corn Field Based on the Generalized Regression Neural Network

Abstract

In order to solve the problem whether the wireless sensor network (WSN) nodes are quickly and reasonably arranged in the corn field, this paper proposes the prediction of wireless signal path loss in the corn field on the basis of generalized regression neural network. In this test, this paper takes carrier frequency of 433 MHz and 2.4GHz. According to the features of radio transmission, the corn is divided into three different growth period to measure the path attenuation. Attenuation value is the output Expectation value. Six influenced factors, namely the growth period, the transmitter antenna height, receiver antenna height, antenna gain , the carrier frequency and communication distance, are the input vectors. According to this, the GRNN prediction model is established.