Distributed Deep Fusion Predictor for a Multi-Sensor System Based on Causality Entropy

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.

Recursive least squares estimation methods for a class of nonlinear systems based on non‐uniform sampling

“…Compared with the AM‐RLS algorithm, the AM‐HLS algorithm has higher computational efficiency. The proposed methods in this article can be extended to study the parameter identification problems of other nonlinear systems with colored noises 90‐98 and can be applied to other fields 99‐104 such as signal analysis and engineering application systems 105‐111 . In the future work, the further investigation includes the parameter estimation methods of the scalar or multivariable nonlinear systems and the convergence analysis of the proposed algorithms.…”

Decomposition‐based over‐parameterization forgetting factor stochastic gradient algorithm for Hammerstein‐Wiener nonlinear systems with non‐uniform sampling

“…In the future work, the further investigation includes the parameter estimation methods of other linear and nonlinear systems with colored noises [61][62][63][64] and bilinear systems [65][66][67][68] and so on. The methods proposed in the article can be applied to other literatures [69][70][71][72][73][74] such as paper-making systems, information processing, transportation communication systems [75][76][77][78][79][80] and so on.…”

Real-Time In-Vehicle Air Quality Monitoring System Using Machine Learning Prediction Algorithm

“…With respect to prediction systems, artificial intelligence algorithms are widely used in smart city applications for classification prediction and regression prediction such as human activity classification [ 26 , 27 ], transportation [ 28 ], and air quality prediction [ 29 , 30 , 31 , 32 ]. In [ 33 ] the authors applied the ML algorithms to predict the air quality by using the data from 750 observations with 0.95 accuracy and their prediction was successful.…”