Multi-source Heterogeneous Data Fusion Model Based on FC-SAE

Abstract

Multi-source heterogeneous data has different degrees of data correlation or data conflict. How to fuse this data and fully mine its inherent meanings to obtain more accurate decision information is a problem that needs to be solved urgently. This paper proposes a multi-source heterogeneous data fusion model based on fully connected layers and sparse autoencoders (short for FC-SAE) to solve the above problem. This model can effectively improve the time series forecasting performance compared with the traditional time series forecasting model. The MAE value is reduced by 4.4% and the RMSE value is reduced by 3.7%. In terms of fusion strategy, the method that uses the sparse autoencoder as the fusion strategy reduces the MAE value by 1.7% and the RMSE value by 2.3% compared with the method that uses the fully connected layer as the fusion strategy.