This work was supported in part by the Situation analysis and demonstration application of saffron cultivation and soil nutrients based on big data mining technology 201900014, Provincial Project in Data Fusion Analysis and Intelligent Regulation of Saffron Growth Environment Monitoring LGN19C130002 ABSTRACT Ensemble deep learning can combine strengths of neural network and ensemble learning and gradually becomes a new emerging research direction. However, the existing methods either lack theoretical support or demand large integrated models. To solve these problems, in this paper, Ensembles of Gradient Boosting Recurrent Neural Network (EGB-RNN) is proposed, which combines the gradient boosting ensemble framework with three types of recurrent neural network models, namely Minimal Gated Unit (MGU), Gated Recurrent Unit (GRU) and Long Short-Term Memory (LSTM). RNN model is used as base learner to integrate an ensemble learner, through the way of gradient boosting. Meanwhile, for ensuring the ensemble model fit data better, Step Iteration Algorithm is designed to find an appropriate learning rate before models being integrated. Contrast trials are carried out on four time series data sets. Experimental results demonstrate that with the number of integration increasing, the performance of three types of EGB-RNN models tend to converge and the best EGB-RNN model and the best degree of ensemble vary with data sets. It is also shown in statistical results that the designed EGB-RNN models perform better than six baselines.

This paper is concerned with the distributed fusion estimation problem of range-only target tracking system with unknown but bounded noises, where the linear and nonlinear motion models are both considered. Particularly, a kind of nonlinear transformation is used to convert the nonlinear distance measurement model into a linear one, which eliminates the corresponding linearization errors in the design of estimation error system. In spite of the transformed measurement noise becomes more complicated, while it is still bounded. Moreover, for the nonlinear target motion model, the state linearization error caused by the Taylor expansion is modeled by the state dependent matrix with uncertainty bounded matrix. In this case, based on the bounded recursive optimization algorithm, two kinds of convex optimization problems are established to determine the gains of the local/fusion estimators, and the stability of the designed estimators also can be guaranteed. Finally, two different range-only target tracking systems are presented to show the effectiveness and advantages of the proposed methods.

In this paper, a new type of modified Smith predictor based on the H 2 and predictive PI control strategy is proposed. The modified Smith predictor not only has H 2 robust performance but also has a similar predictive PI control structure. By introducing a time delay term, the modified Smith predictor controller overcomes the shortcoming that the conventional control algorithm can only use the low-order approximation of time delay term to design the control algorithm. The modified Smith predictor controller’s output is related to the current system error and related to the output in a period before the controller. Simultaneously, the modified Smith predictor controller is applied to conventional process systems based on dynamic optimization estimation in the case study to show absolute superiority over the nonpredictive control method (such as the classical PID control method).