In order to solve the poor generalization ability of the back-propagation(BP)neural network in the model updating hybrid test,a novel method called the AdaBoost regression tree algorithm is introduced into the model u...In order to solve the poor generalization ability of the back-propagation(BP)neural network in the model updating hybrid test,a novel method called the AdaBoost regression tree algorithm is introduced into the model updating procedure in hybrid tests.During the learning phase,the regression tree is selected as a weak regression model to be trained,and then multiple trained weak regression models are integrated into a strong regression model.Finally,the training results are generated through voting by all the selected regression models.A 2-DOF nonlinear structure was numerically simulated by utilizing the online AdaBoost regression tree algorithm and the BP neural network algorithm as a contrast.The results show that the prediction accuracy of the online AdaBoost regression algorithm is 48.3%higher than that of the BP neural network algorithm,which verifies that the online AdaBoost regression tree algorithm has better generalization ability compared to the BP neural network algorithm.Furthermore,it can effectively eliminate the influence of weight initialization and improve the prediction accuracy of the restoring force in hybrid tests.展开更多
Density function M06 method has been used to optimize the geometries of camptothecin-cytosine at 6-3 I＋G＊ basis. Finally, thirteen stabilized complexes have been obtained. Theories of atoms in molecules （AIM） and ...Density function M06 method has been used to optimize the geometries of camptothecin-cytosine at 6-3 I＋G＊ basis. Finally, thirteen stabilized complexes have been obtained. Theories of atoms in molecules （AIM） and natural bond orbital （NBO） have been utilized to investigate the hydrogen bonds involved in all the complexes. The interaction energies of all the complexes are corrected by basis set superposition error （BSSE）. By the analysis of complexes interaction energy, charge density, second- order interaction energies E（2）; it is indicated that the complex 6 is the most stable structure.展开更多
基金The National Natural Science Foundation of China(No.51708110)。
文摘In order to solve the poor generalization ability of the back-propagation(BP)neural network in the model updating hybrid test,a novel method called the AdaBoost regression tree algorithm is introduced into the model updating procedure in hybrid tests.During the learning phase,the regression tree is selected as a weak regression model to be trained,and then multiple trained weak regression models are integrated into a strong regression model.Finally,the training results are generated through voting by all the selected regression models.A 2-DOF nonlinear structure was numerically simulated by utilizing the online AdaBoost regression tree algorithm and the BP neural network algorithm as a contrast.The results show that the prediction accuracy of the online AdaBoost regression algorithm is 48.3%higher than that of the BP neural network algorithm,which verifies that the online AdaBoost regression tree algorithm has better generalization ability compared to the BP neural network algorithm.Furthermore,it can effectively eliminate the influence of weight initialization and improve the prediction accuracy of the restoring force in hybrid tests.
基金Funded by the Health Department Science Foundation of Sichuan(Grant No. 2011-236)
文摘Density function M06 method has been used to optimize the geometries of camptothecin-cytosine at 6-3 I＋G＊ basis. Finally, thirteen stabilized complexes have been obtained. Theories of atoms in molecules （AIM） and natural bond orbital （NBO） have been utilized to investigate the hydrogen bonds involved in all the complexes. The interaction energies of all the complexes are corrected by basis set superposition error （BSSE）. By the analysis of complexes interaction energy, charge density, second- order interaction energies E（2）; it is indicated that the complex 6 is the most stable structure.
