Earticle

초록

영어

Because of the nonlinear characteristics of the BTP in sintering process, the BTP forecasting is difficult to realize. The LS-SVM was employed in this study for forecasting. However, Because SVM is using the two programming support vector, computing and solving two quadratic programming will involve matrix of order m, when the M number is large storage and computing the matrix will consume a large amount of computer memory and calculation time. The traditional training methods based on searching technique are not effective and fast. Therefore, bacterial foraging optimization (BFO) was adopted to optimize the LS-SVM. BFO is a novel and powerful global search technique, It is found that Bacteria Foraging Algorithm (BFO) is capable of improving the speed of convergence as well as the precision in the desired result. Simulation results clearly illustrate that the proposed approach is very efficient and could easily be extended for other global optimization problems. It can conclude that BFO is effective and rapid for the cluster analysis problem.

목차

Abstract
 1. Introduction
 2. Sintering Process and the Analysis of BTP
  2.1 . The Analysis of BTP
 3. The Bacteria Foraging Optimization Algorithm
 4. Prediction Model based on Bayesian Framework and LS-SVM
  4.1 LS-SVM Algorithm
 5. BFO Optimize SVM Parameters
  5.1 Prediction Step BFO-SVM Prediction Steps are as Follows:
  5.2 Experiments and Discussions
 6. Conclusion
 References

키워드

저자

• SONG Qiang [ Mechanical engineering department of Anyang institute of technology ]
• GUO Xiao-bo [ School of computer and Information Engineering of Anyang institute of technology ]
• LI hua [ The Transport Department of Anyang iron and Steel Group Company ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Hybrid Information Technology

• 간기

  격월간

• pISSN

  1738-9968

• 수록기간

  2008~2016

• 십진분류

  KDC 505 DDC 605