No abstract

A binocular stereovision system has been developed to estimate growth variables of a transplant population. In the present study, the image analysis system was improved by adopting a three-layered artificial neural network model (ANN model) based on a backpropagation algorithm. Inputs of the ANN model were average height, leaf area, projected leaf area, and mass volume of the transplant population obtained from the image analysis system. Outputs of the ANN model were average height, number of unfolded leaves, leaf area, and fresh and dry masses of the transplant population, which give a more accurate assessment of the transplant growth status than that obtained from the image analysis system. The number of nodes in the hidden layer of the ANN model was determined through trial and error. The growth variables thus obtained from the ANN model using a sweetpotato (Ipomoea batatas (L.) Lam.) transplant population were more accurate than those obtained from a regression model. The image analysis system, after being improved by using the ANN model, successfully identified the transplant growth status with a high degree of accuracy.

To address the problems of 5G network planning and optimization, a 5G user time delay prediction model based on the BiLSTM neural network optimized by APSO-SD is proposed. First, a channel generative model based on the ray-tracing model and the statistical channel model is constructed to obtain a large amount of time delay data, and a 5G user ray data feature model based on three-dimensional stereo mapping is proposed for input feature extraction. Then, an adaptive particle swarm optimization algorithm based on a search perturbation mechanism and differential enhancement strategy (APSO-SD) is proposed for the parameters’ optimization of BiLSTM neural networks. Finally, the APSO-SD-BiLSTM model is proposed to predict the time delay of 5G users. The experimental results show that the APSO-SD has a better convergence performance and optimization performance in benchmark function optimization compared with the other PSO algorithms, and the APSO-SD-BiLSTM model has better user time delay prediction accuracy in different scenarios.