Weighted value assessment of linear fractional programming for possibilistic multi-objective problem. (2016)

• Record Type: Journal Article
• Authors: Arbaiy, Nureize; Lin, Pei-Chun
• Is Part Of: International journal of advanced intelligence paradigms. Volume 8:Number 1(2016)
• Page Start: 42
• Page End: 58
• Publication Date: 2016
• Subjects: weighting method -- fuzzy random regression -- FRR -- multi-objective decision making -- possibilistic programming -- weight assessment -- weighted value assessment -- linear fractional programming -- weight values -- mathematical modelling; Artificial intelligence -- Periodicals; Machine theory -- Periodicals; Fuzzy logic -- Periodicals; 006.305
• Languages: English
• ISSNs: 1755-0386

Abstract

Determining the weight values is crucial in developing problem's mathematical model. The value of the model's weight must be determined before the model is solved. Nevertheless, the developed mathematical model is troublesome when the weight values are not exactly known, as relevant data are sometimes not given or difficult to obtain or estimate. Since numerous researches focusing in finding the solution of the model, this paper focuses on determining the weight value and a weighting method specifically for linear fractional programming to solve possibilistic programming of the multi-objective decision-making problem. Fuzzy random regression approach is applied to estimate the multi-objective model's weight value. Meanwhile, the minimal and maximal values of the objective function are utilised in determination for objective function weight value. Since most of the weight values in the developed model discusses in this paper are estimated from real data, assessment to these weights value in the objective function is executed. The weight value assessment uses weight absolute percentage error of fuzzy demand (WAPE_FD). This analysis concludes that it is worthwhile to pursue proposed solution approach to the multi-objective evaluation scheme, which addresses some limitation to determine and assess the weight values within fuzzy circumstances.