期刊文献+

预测Al_2O_3粒子衰减特性的LSSVM方法

Prediction for Extinction Property of Al_2O_3 Particle by LSSVM Method
下载PDF
导出
摘要 应用最小二乘支持向量机建立了Al2O3粒子衰减特性预测模型,引入微粒群算法解决了模型多参数优化问题,结合辐射传输数值求解方法获得了吸收散射性介质的红外辐射特性。比较结果表明,该方法具有较好的预测能力,在保证模拟结果精度的同时提高了运算速度。 A prediction model for extinction property of Al2O3 particle was established by using least square support vector machine. Particle swarm optimization method was applied to optimize the multi-parameters. Combined with the numerical method for radiative heat transfer, the infrared properties of emitting and scattering medium were obtained. The result shows that the method is capable to predict the extinction property accurately meanwhile the operation rate has great enhancement.
出处 《科学技术与工程》 2009年第18期5531-5533,共3页 Science Technology and Engineering
基金 国家自然科学基金(NO.50806017)资助
关键词 粒子辐射特性 最小二乘支持向量机 微粒群算法 particle radiative property least square support vector machine Particle swarm optimization
  • 相关文献

参考文献5

  • 1Suykens J A K. Vandewalle J. Least squares support vector machine classifiers. Neural Processing Letter, 1999 ;9:293--300.
  • 2Mohamed/S/S, Salama M M A, Kamel M, et al. Region of interest based prostate tissue characterization using least square support vector machine LS-SVM. Lecture Notes in Computer Science, 2004 ; 3212 : 51--58.
  • 3Van G T , Suykens J A K. Baestaens D E , et al. Financial time series prediction using least squares support vector machines within the evidence framework. IEEE Transactions on Neural Networks, 2001, 12(4) : 809--821.
  • 4Viaene S , Baesens B , Van G T, et al. Knowledge discovery in a direct marketing ease using least squares support vector machines. International Journal of Intelligent Systems, 2001;16(9) : 1023--1036.
  • 5Kennedy J , Eberhart R C. Particle swarm optimization. Proc IEEE International Conference on Neural Networks, Perth, Australia, 1995 : 1942--1948.

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部