Share Email Print
cover

Proceedings Paper • new

Index-weight integration optimized by expert reliability
Author(s): Faming L.; Gang M.; Di W.; Chaoshuai H.; Longtao W.
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

For the simplicity and utility, the traditional analytic hierarchy process (AHP) has been widely applied for multi-criteria decision-making. However, its index weight as well as the evaluation conclusion are still affected by the expert subjectivity. To solve this problem, our paper introduces the probability statistics theory to quantify the judgment qualities from different evaluation experts, and transforms the quantified qualities into expert reliabilities, and then optimizes the index-weight integration with the transformed expert reliabilities. Specifically, our method integrates the index weights with following steps. Firstly, using the traditional AHP, it calculates the evaluation values for all index weights according to each expert judgments respectively. Secondly, employing the probability statistics theory, it quantifies the judgment qualities from all experts. The quantified qualities are then transformed into expert reliabilities and expert weights. The transform rule is as followings: the larger reliability to those experts whose judgments have high quality, while smaller reliability to those experts whose judgments have low quality. Lastly, our method replaces the equal expert weight in the traditional AHP with the reliability-based expert weights. As a result, the expert subjectivity is decreased in the index-weight integration, and the evaluation conclusion becomes more creditable. The creditability is verified by experiments.

Paper Details

Date Published: 12 March 2019
PDF: 7 pages
Proc. SPIE 11023, Fifth Symposium on Novel Optoelectronic Detection Technology and Application, 110234Y (12 March 2019); doi: 10.1117/12.2520399
Show Author Affiliations
Faming L., Research Institute for Chemical Defense (China)
Gang M., Research Institute for Chemical Defense (China)
Di W., Research Institute for Chemical Defense (China)
Chaoshuai H., Research Institute for Chemical Defense (China)
Longtao W., Research Institute for Chemical Defense (China)


Published in SPIE Proceedings Vol. 11023:
Fifth Symposium on Novel Optoelectronic Detection Technology and Application
Qifeng Yu; Wei Huang; You He, Editor(s)

© SPIE. Terms of Use
Back to Top