The traditional Dead Reckoning algorithm predicts the future motion state based on a determined polynomial predictor,and the forecasting performance would vary with different types of motion *** paper proposes an enha...
详细信息
The traditional Dead Reckoning algorithm predicts the future motion state based on a determined polynomial predictor,and the forecasting performance would vary with different types of motion *** paper proposes an enhanced dead reckoning algorithm based on hybrid extrapolation models,which can be used to reduce the communication in a distributed interactive *** proposed algorithm perform extrapolation using a number of candidate *** idea is based on the assumption that a complex trajectory can be decomposed into several simple *** experimental evaluations show that the enhanced Dead Reckoning algorithm provides better performance in correction data reduction and accurate estimation.
In view of the low efficiency in the measurement of multi-source information synergy structure for the smart city and other problems,a kind of computer aided measurement of smart city multi-source information synergy ...
详细信息
In view of the low efficiency in the measurement of multi-source information synergy structure for the smart city and other problems,a kind of computer aided measurement of smart city multi-source information synergy structure(hereinafter referred to as CAMMISS for short) that is dependent on the adaptive artificial immune network algorithm(hereinafter referred to as AAINA for short) is put ***,the number of the input and output nodes in the multi-source information synergy structure(hereinafter referred to as MSISS for short) is determined in accordance with the number of the situation input index and the value of the output *** connection weight value and the threshold value of each layer are randomly initialized,and the floating number encoding method is used to encode the weight value and the threshold value into the adaptive artificial immune network *** experimental results show that compared with the methods of the MSISS and the genetic algorithm for the optimization of the multi-source information,the method put forward in this paper has relatively fast convergence speed and relatively high prediction accuracy.
To improve the performance of copper-matte Peirce-Smith Converting(PSC), the influence of local process data to e-support vector regression(SVR)model for converting process is studied. This paper proposes an Error Cor...
详细信息
To improve the performance of copper-matte Peirce-Smith Converting(PSC), the influence of local process data to e-support vector regression(SVR)model for converting process is studied. This paper proposes an Error Correction method for e-Support Vector Regression(ECVR), in which the influence of local support vector to prediction results is considered. Two ECVR models for slag weight and blowing time of S1 period(that is, the first slag producing period of PSC) are developed by the real production data. Simulation results show that ECVR model can significantly improve prediction accuracy and generalization of the converting decision variable in S1 period.
Aiming at the problems of low prediction accuracy and weak generalization ability of current reliability prediction models,this paper proposes a hybrid multi-layer heterogeneous particle swarm optimization algorithm(H...
详细信息
Aiming at the problems of low prediction accuracy and weak generalization ability of current reliability prediction models,this paper proposes a hybrid multi-layer heterogeneous particle swarm optimization algorithm(HMHPSO)that can simultaneously optimize the structure and parameters of the GRU neural *** first introduced a multi-layer heteromass particle swarm optimization(MHPSO)algorithm,which sets the population topology as a hierarchical structure and introduces the concept of attractors,so as to improve the update formula of particle speed,and enhance the information interaction ability between particles,increase the diversity of the groups,thereby improving the optimization ability of the *** the HMHPSO used the quantum particle swarm optimization(QPSO)algorithm to determine the structure of the GRU,that is,the number of hidden *** results show that the algorithm can generate GRU neural networks with high generalization performance and low architecture complexity,and has better prediction accuracy in software reliability prediction.
暂无评论