Hierarchical MADM with fuzzy integral for evaluating enterprise intranet web sites

In the real world, most criteria have inter-dependent or interactive characteristics so they cannot be evaluated by conventional additive measures. Thus, to approximate the human subjective evaluation process, it would be more suitable to apply a fuzzy integral model, in which it is not necessary to assume additivity and independence. This research proposes an effective algorithm to determine the k-value using the input data of fuzzy densities and the fuzzy integral based on k-fuzzy measure to determine the overall evaluation. This research also gives an example of evaluating enterprise intranet web sites with illustrations of the hierarchical structure of k-fuzzy measure for a Choquet integral model. The results show that the fuzzy integral is more suitable than a traditional multicriteria evaluation method for human subjective evaluation, or when criteria are not mutually independent. 2004 Elsevier Inc. All rights reserved. 0020-0255/$ see front matter 2004 Elsevier Inc. All rights reserved. doi:10.1016/j.ins.2004.07.001 * Corresponding author. E-mail address: [email protected] (G.-H. Tzeng). 410 G.-H. Tzeng et al. / Information Sciences 169 (2005) 409–426