The application of BP neural net real-time data forecasting model used in home environment

With the help of powerful function mapping capability of BP neural network, this paper presents a BP neural net real-time data forecasting model which is suitable for the home environment by using the correlation between the indoor temperature, outdoor humidity and indoor humidity. The model is based on the size of the correlation coefficient to identify the weights of relative factors. The functional relationship of the indoor temperature, outdoor humidity and indoor humidity can be mapped more accurately. Then the trends of indoor humidity could be predicted accurately. By comparing the unimproved BP neural network algorithm, it is proved that the model has high prediction accuracy. The improved BP neural net real-time data forecasting model is applied to indoor PM2.5 value prediction. This model can be applied to home environments in real-time data forecasting.