Affiliation:
1. ISTANBUL TECHNICAL UNIVERSITY, FACULTY OF COMPUTER AND INFORMATICS ENGINEERING, DEPARTMENT OF COMPUTER ENGINEERING
2. FATIH SULTAN MEHMET VAKIF UNIVERSITY, FACULTY OF ENGINEERING
Abstract
We propose a Mamdani-Type Fuzzy Inference based posterior decision-making approach to multi-objective diet optimization problem. We optimize the multi-objective diet problem with evolutionary algorithms that result in tens/hundreds of non-dominated solutions which is too large to pick one of them by the decision-maker. Even though all the solutions are optimized for all the objectives simultaneously, not all objective functions may be equally important to a user and, also their importance may change for that user over time. Our main goal is to develop an applicable method for representing and incorporating a decision maker's (DM) instant preferences for objectives into decision-making stage. The FIS based decision making can guide users to decide on the most suitable menus. User's instant preferences for each objective form rule sets. Using Mamdani type FIS in the post-decision process of the multi-objective diet problem is a novel contribution. A desirability measure is calculated by using rule sets and membership functions considering the objective values, and based on the desirability measure the most preferred menu(s) are provided to the user. Our method can direct the DM to the region of interest in the search space of the multi-objective diet problem. Thus, the daily menu suggestions become more applicable, practical, and desirable for the users.
Publisher
European Journal of Science and Technology
Subject
General Earth and Planetary Sciences,General Environmental Science
Reference14 articles.
1. Zadeh, L.A. (1965). Fuzzy sets, Information and control, 8(3), 338–353.
2. Deb, K. (2001). Multi-objective optimization using evolutionary algorithms, volume 16, John Wiley & Sons.
3. Deb, K. and Jain, H. (2014). An evolutionary many-objective optimization algorithm using reference-point-based nondominated sorting approach, part I: Solving problems with box constraints., IEEE Trans. Evolutionary Computation, 18(4), 577–601.
4. Purshouse, R.C. and Fleming, P.J. (2007). On the evolutionary optimization of many conflicting objectives, IEEE Transactions on Evolutionary Computation, 11(6), 770–784.
5. Miettinen, K. (2012). Nonlinear multiobjective optimization, volume 12, Springer Science & Business Media.