Research on network-aware data fusion algorithm based on fuzzy time series

The traditional adaptive weighted fusion algorithm ignores the spatial correlation between the network sensing data and has high fusion bias, significantly reducing network data transmission quality. The network perception data fusion algorithm based on fuzzy time series is proposed, and the network perception data prediction algorithm based on fuzzy time series is used. The network data value is calculated using first and two-order fuzzy relations during the training stage, and the trend value of the network data is obtained. The trend value in the prediction stage dynamically obtains the network sense. Based on the relationship, the fuzzy relation of knowledge data is used to predict the network perception data for the next time series. The network sensing data fusion algorithm based on the confidence matrix is used to fuse the data by predicting the spatial correlation between the data and filtering the noise of the abnormal data to the fusion results. The proposed algorithm’s high fusion accuracy and improved quality of network data transmission are demonstrated by experimental results.