article · 1997

To Normalize the Relationship between the Certainty Factor Model and Probability Theory

Xudong Luo, Chengqi Zhang, Yuhui Qiu

Cited by 0Abstract and details only

Abstract

In this paper, we prove that the EMYCIN formula for the sequential propagation can be derived strictly from the definition of the certainty factor according to probability theory. Some researchers think that this combination formula is inconsistent with the definition of certainty factor in the sense of probability theory. This was not correct. Moreover, under the condition that there exists no need for prior probabilities to be supplied with values, we reformulate the parallel propagation from the definition of the certainty factor according to probability theory. Therefore, the paper normalizes the relationship between the definition of the certainty factor and combination formulae for sequential and parallel propagations. In conclusion, this paper demonstrated that the certainty factor model can be built on the foundation of probability theory. Keywords: Uncertainty, Expert System, Prior Probability, Extension Conditional Probability, Certainty Factor, Ternary Rule Strength. 1 Int...

Cite this paper

APA 7

Luo, X., Zhang, C., & Qiu, Y. (1997). To Normalize the Relationship between the Certainty Factor Model and Probability Theory.

MLA 9

Luo, Xudong, et al. “To Normalize the Relationship between the Certainty Factor Model and Probability Theory.” 1997.

Chicago

Luo, Xudong, Chengqi Zhang, and Yuhui Qiu. 1997. “To Normalize the Relationship between the Certainty Factor Model and Probability Theory.”

Harvard

Luo, X., Zhang, C. and Qiu, Y. (1997) ‘To Normalize the Relationship between the Certainty Factor Model and Probability Theory’.

BibTeX

@article{luo1997normalize,
  title = {{To Normalize the Relationship between the Certainty Factor Model and Probability Theory}},
  author = {Luo, Xudong and Zhang, Chengqi and Qiu, Yuhui},
  year = {1997}
}

Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.