The comparison of path loss model for the unmanned aerial vehicle (UAV) and Internet of Things (IoT) air-to-ground communication system was proposed for rural precision farming. Due to the uncertainty of propagation channel in rural precision farming environment, the comparison of path loss prediction was investigated by the conventional particle swarm optimization (PSO) algorithms: PSO (exponential or Exp), PSO (polynomial or Poly) and the machine learning algorithms: k-nearest neighbor (k-NN), and random forest, are exploited to accurate the path loss models on the basic of the measured dataset. Meanwhile, the empirical model in the rural precision farming was considered. By using the machine learning-based algorithms, the coefficient of determination (R-squared: R2) and root mean squared error (RMSE) were evaluated as highly accuracy and precision more than the conventional PSO algorithms. According to the results, the random forest method was able to perform more than other methods. It has the smallest prediction errors.

A challenge swarm unmanned aerial vehicles (swarm UAVs)-based wireless communication systems have been focused on channel modeling in various environments. In this paper, we present the characterized path loss air-to-air (A2A) channel modeling-based measurement and prediction model. The channel model was considered using A2A Two-Ray (A2AT-R) extended path loss modeling. The prediction model was considered using an artificial neural network (ANN) algorithm to train the measured dataset. To evaluate the measurement result, path loss models between the A2AT-R model and the prediction model are shown. We show that the prediction model using ANN is optimal to train the measured data for the A2A channel model. To discuss the result, the parametric prediction errors such as mean absolute error (MAE), root mean square error (RMSE), and R-square (R2), are performed.