中文

Journal of Applied Sciences ›› 2004, Vol. 22 ›› Issue (1): 55-59.

• Articles • Previous Articles     Next Articles

Support Vector Machine Technique Applied to Computerized Prediction of Intermediate Phases of Some Phase Diagrams of Molten Salt Systems

LIU Xu1, LU Wen-cong1, LIU Liang1, CHEN Nian-yi1, YE Chen-zhou2, YANG Jie2   

  1. 1. School of Science, Shanghai University, Shanghai 200436, China;
    2. Institute of Image Processing and Pattern Recognition, Jiaotong University, Shanghai 200030, China
  • Received:2002-10-23 Revised:2003-01-20 Online:2004-03-31 Published:2004-03-31

PDF

87

Cited

8

Abstract: The newly developed support vector machine technique is suitable for data processing based on a finite number of training samples, with a special technique to restrict overfitting. In the present case the support vector classification technique is used for the computerized prediction of the formation of intermediate compounds in some molten salt systems. The prediction of the intermediate compound formation of KNO3-KBr, KNO3-KI and Cs,Li,Er|Cl systems has been made and the results confirmed by experiments. Besides, the leaving-one method has been used to compare the rate of correctness of the prediction of the formation of the intermediate compounds in AX-BX, AX2-BX2 systems,with that of the formation of A3B2C19 and A2BCl5 type compounds in some rare earth-chloride containing systems by SVM, Fisher and KNN methods. The results indicate that the rate of correctness of prediction by SVM method is usually higher than the other two methods.

Key words: overfitting, prediction of intermediate phases of phase diagrams, support vector machine

CLC Number: