Improved wavelet neural network based on change rate to predict satellite clock bias
Xu Wang, Hongzhou Chai, Chang Wang, Guorui Xiao, Yang Chong, Xiaoguo Guan
Abstract
To develop a high-accuracy method for predicting SCB based on the analysis of the shortcomings of the wavelet neural network (WNN) model, an improved WNN model to predict SCB is proposed herein. The activation function of the WNN is constructed by combining the advantages of Shannon and Gauss ‘window’ functions to improve the WNN. Finally, the improved WNN model is used to predict SCB. The results show that the proposed model has the highest prediction accuracy, stability, and robustness. Moreover, it effectively predicts long-time SCB data. Therefore, the proposed model can predict SCB with high accuracy.
Topics & Concepts
Robustness (evolution)Computer scienceArtificial neural networkWaveletWavelet transformStability (learning theory)Data miningAlgorithmArtificial intelligenceMachine learningChemistryGeneBiochemistryInertial Sensor and NavigationRegional Economic and Spatial AnalysisWater Quality Monitoring and Analysis