Application of  CPSO-LSSVM model based on wavelet transform and Kalman filter to the subsiding analysis of structure

Hong Gao; Hongyan Wen; Ruibo Fang; Guangyu Nie; Zhi Yang

doi:10.1117/12.2206113

9 December 2015 Application of CPSO-LSSVM model based on wavelet transform and Kalman filter to the subsiding analysis of structure

Hong Gao, Hongyan Wen, Ruibo Fang, Guangyu Nie, Zhi Yang

Author Affiliations +

Proceedings Volume 9808, International Conference on Intelligent Earth Observing and Applications 2015; 980830 (2015) https://doi.org/10.1117/12.2206113
Event: International Conference on Intelligent Earth Observing and Applications, 2015, Guilin, China

Abstract

In the analysis on building deformation, when the deformation is unconscious, the significant effect random noise contributes, in addition that the prediction model of neural network has slow convergence. A new CPSO-LSSVM forecasting model is established, based on the combination of wavelet analysis and Kalman filter. The forecasting model resolves the noise problem and with a high accuracy by improving the PSO algorithm. The results show that it has a higher accuracy than the BP network and the LSSVM.

Citation Download Citation

Hong Gao, Hongyan Wen, Ruibo Fang, Guangyu Nie, and Zhi Yang "Application of CPSO-LSSVM model based on wavelet transform and Kalman filter to the subsiding analysis of structure", Proc. SPIE 9808, International Conference on Intelligent Earth Observing and Applications 2015, 980830 (9 December 2015); https://doi.org/10.1117/12.2206113

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available