Novel support vector regression for structural system identification

2011 International Conference on Management and Service Science

2011

Using both qualitative and quantitative analysis, a set of relatively integrated evaluation indexes was developed to analyze the urban planning process in Guanzhong urban agglomeration. Key impact factors of coordinated development obtained from literature analysis were used as input, and the degree of coordinated development during 1988~2008 calculated by principal component analysis and the coordinated development model were used as output. On this basis, a support vector machine model was built to predict the trends of coordinated development. The method was compared with artificial neural network, decision tree, logistic regression and naive Bayesian classifier regarding urban ecosystem coordinated development prediction for Guanzhong urban agglomeration. It is found that the method has the best accuracy rate, hit rate, covering rate and lift coefficient, and provides an effective measurement for urban ecosystem coordinated development prediction.

Section: Methodsmentioning

confidence: 99%

Simulation of Coordinated Development of an Urban Ecosystem: A Case Study in Guanzhong Urban Agglomeration

2011 International Conference on Management and Service Science

2011

“…Here, W can not be expressed by explicit expression, the solution of function approximation would be directly made in Hilbert space, so avoid calculating the nonlinear mapping qJ( x) [15] III. EMPIRICAL STUDY…”

Section: Methodsmentioning

confidence: 99%

Coordinated development degree of county socio-economic system prediction based on support vector machine: Taking twenty-six Chinese counties as the example

2010 International Conference on Educational and Information Technology

2010

Coordinated development degree of county socio economic system analysis and prediction play an important role in urban agglomeration coordinated development and improve benefit of regional coordinated development in China.According to the county socio-economic system data which is large scale and imbalance, this paper presented a support vector machine model to predict coordinated development degree of county socio-economic system. The method was compared with artificial neural network, decision tree, logistic regression and naive Bayesian classifier regarding coordinated development degree of county socio-economic system prediction for Guanzhong urban agglomeration. It is found that the method has the best accuracy rate, hit rate, covering rate and lift coefficient, and provides an effective measurement for coordinated development degree of county socio-economic system classification and prediction.

Section: Methodsmentioning

confidence: 99%

City Innovative Capability Prediction Based on Support Vector Machine: Taking Thirteen Chinese Cities as the Example

2010 International Conference on Management and Service Science

2010

City innovative capability analysis and prediction play an important role in regional innovation systems development and improve benefit of innovative capability for country. According to the city innovative capability data which is large scale and imbalance, this paper presented a support vector machine model to predict city innovative capability. The method was compared with artificial neural network, decision tree, logistic regression and naive Bayesian classifier regarding city innovative capability prediction for thirteen Chinese cities. It is found that the method has the best accuracy rate, hit rate, covering rate and lift coefficient, and provides an effective measurement for city innovative capability classification and prediction. Keywords-city innovative capability; support vector machine; regional innovation systems; prediction I.978-1-4244-5326-9/10/$26.00 ©2010 IEEE