Shulou(Shulou.com)06/01 Report--

This article mainly introduces the structure of BP neural network in big data, which has certain reference value. Interested friends can refer to it. I hope you will gain a lot after reading this article. Let's take you to know it.

BP neural network structure

The neural network aims to imitate the animal's nervous system and use neurons as connection nodes. The neural network itself consists of three layers: input layer, hidden layer and output layer, each of which has its own special function. The input layer carries on the input and processing of factors. Because in the actual situation, all the input data is not linear, some time is still multi-dimensional, let the data through the hidden layer training, make the data visualization, in order to achieve the data needed, is the core of the neural network is after the hidden layer training, the data basically meets its own requirements, then it is necessary to output the data, the three levels do not affect each other The state of the neurons in each layer can only affect the state of the neurons in the next layer, and its structure is shown in the following figure:

The neural network prediction process established in this paper is as follows:

An example of neural network prediction

Based on the 54-year data of Huashan Meteorological Station in the middle reaches of the Yellow River Basin from 1957 to 2010, this paper takes the data from 1957 to 2000 as the forecast data, the data from 2001 to 2010 as the reference data, and uses the data of the first 44 years to predict the data of the next ten years. and compared with the actual data of the next decade to determine the prediction accuracy. Through the previous analysis, we can get that the set factors of the selected input variables are water vapor pressure, wind speed, air temperature and relative humidity. Precipitation is taken as the prediction variable, and the water vapor pressure, wind speed, air temperature and relative humidity are substituted into the Matlab program as input variables for prediction. The prediction results are as follows.

Through the calculation of water vapor pressure, wind speed, air temperature and relative humidity as input variables to predict precipitation is more accurate, through the calculation of the correlation coefficient in the prediction reached 72.16%, the prediction accuracy is still very high, the error rate is also small; but the prediction accuracy still needs to be improved. According to the analysis, on the one hand, in the prediction of precipitation, the prediction factors are not the more the better, but the factors which are closely related to the prediction variables should be found. only by using the factors which are highly related to the prediction variables as input variables can we obtain accurate prediction results in the prediction algorithm and get the desired results. On the other hand, in the selection of prediction algorithm, neural network prediction algorithm is not only convenient and accurate, but because there are many types of neural network prediction algorithm, we should choose the appropriate prediction algorithm according to the actual needs. Thank you for reading this article carefully. I hope the article "what is the structure of BP neural network in big data" shared by the editor will be helpful to you. At the same time, I also hope that you will support us and pay attention to the industry information channel. More related knowledge is waiting for you to learn!

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.