Distributed Deep Fusion Predictor for a Multi-Sensor System Based on Causality Entropy |
| |
Authors: | Xue-Bo Jin Xing-Hong Yu Ting-Li Su Dan-Ni Yang Yu-Ting Bai Jian-Lei Kong Li Wang |
| |
Institution: | 1.Artificial Intelligence College, Beijing Technology and Business University, Beijing 10048, China; (X.-H.Y.); (Y.-T.B.); (J.-L.K.);2.China Light Industry Key Laboratory of Industrial Internet and Big Data Beijing Technology and Business University, Beijing 10048, China;3.Electrical and Information Engineering College, Tianjin University, Tianjin 300072, China; |
| |
Abstract: | Trend prediction based on sensor data in a multi-sensor system is an important topic. As the number of sensors increases, we can measure and store more and more data. However, the increase in data has not effectively improved prediction performance. This paper focuses on this problem and presents a distributed predictor that can overcome unrelated data and sensor noise: First, we define the causality entropy to calculate the measurement’s causality. Then, the series causality coefficient (SCC) is proposed to select the high causal measurement as the input data. To overcome the traditional deep learning network’s over-fitting to the sensor noise, the Bayesian method is used to obtain the weight distribution characteristics of the sub-predictor network. A multi-layer perceptron (MLP) is constructed as the fusion layer to fuse the results from different sub-predictors. The experiments were implemented to verify the effectiveness of the proposed method by meteorological data from Beijing. The results show that the proposed predictor can effectively model the multi-sensor system’s big measurement data to improve prediction performance. |
| |
Keywords: | series causality analysis Bayesian LSTM multi-sensor system meteorological data big measurement data deep fusion predictor |
|
|