Y. Jin, T. Okabe & B. Sendhoff, Adapting weighted aggregation for multi-objective evolution strategies, First International Conference on Evolutionary Multi-criterion Optimization, Lecture Notes in Computer Science, Springer, Zurich, pp. 96-110 (2001).  Home/Search   Document Details and Download   Summary   Related Articles   Check

....such as in aerodynamic design optimization problems [5] In Section two, we will briefly review some of the expectation based approaches to searching for robust optimal solutions. The multiobjective optimization algorithm used in this paper, the dynamic weighted aggregation method proposed in [6, 7], is described in Section 4. Simulation results on two test problems are presented in Section 5 to demonstrate the e#ectiveness of the proposed method. A summary of the method and a brief discussion of future work conclude the paper, where a simple example of detecting multiple optima using the ....

....# i is mutated as in equation (19) and # , # # are constants as follows: # = 2 # n ; # # = # 2n (20) 4.2 Dynamic Weighted Aggregation The classical approach to multiobjective optimization using weighted aggregation of objectives has often been criticized. However, it has been shown [6, 7] through a number of test functions as well as several real world applications that the shortcomings of the weighted aggregation method can be addressed by changing the weights dynamically during optimization using evolutionary algorithms. Two methods for changing the weights have been proposed. ....

[Article contains additional citation context not shown here]

Y. Jin, T. Okabe, and B. Sendho#. Adapting weighted aggregation for multiobjective evolution strategies. In First International Conference on Evolutionary Multi-Criterion Optimization, pages 96--110, Zurich, March 2001. Springer.

....importantly, the paper suggests two methods for estimating the robustness measure using the information in the current population solely. Thus, no additional evaluations of the fitness function are necessary. To achieve the trade o# solutions, the evolutionary dynamic weighted method suggested in [13, 14] will be employed. The remainder of the paper is organized as follows. Section 2 introduces a measure for robustness of optimal solutions. Two methods for estimating the robustness measure using individuals in the current population are suggested. The robustness measure is then applied in ....

....# i is mutated as in equation (20) and # , # # are constants as follows: # = 2 # n ; # # = # 2n (21) 3.2 Dynamic Weighted Aggregation The classical approach to multiobjective optimization using weighted aggregation of objectives has often been criticized. However, it has been shown [13, 14] through a number of test functions as well as several real world applications that the shortcomings of the weighted aggregation method can be addressed by changing the weights dynamically during optimization using evolutionary algorithms. Two methods for changing the weights have been proposed. ....

[Article contains additional citation context not shown here]

Y. Jin, T. Okabe, and B. Sendho#. Adapting weighted aggregation for multiobjective evolution strategies. In Proceedings of First International Conference on Evolutionary Multi-Criterion Optimization, Leture Notes in Computer Science, pages 96--110, Zurich, March 2001. Springer.

.... Carl Legien Strasse 30, 63073 Oftenbach M, Germany tatsuya.okabe, yaochu.jin, bernhard.sendhoff de.hrdeu.com Abstract In evolutionary multi objective optimisation (EMOO) using dynamic weighted aggregation (DWA) very interesting dynamic be haviours of the individuals have been ob served [7] [8] In this paper, the dynamics of the individuals on fitness space (FS) during multi objective optimisation (MOO) using evolution strategies (ES) is studied by in vestigating the mapping of a normal distribu tion in the parameter space (PS) onto the FS. It is found that the movement of ....

....of evolutionary algorithms, see e.g. 10] Thus, we are confident that the general approach presented in this paper is not restricted to evolution strategies. The work in this paper is partly motivated by the behaviours observed in MOO using the dynamically weighted aggregation (DWA) algorithm [7, 8]. The basic idea is to combine the optimisation objectives with different weights, which are changed dynamically during optimisation so that a set of Pareto optimal solutions instead of one single solution will be obtained. It has been shown that the method is not only effective for problems with ....

[Article contains additional citation context not shown here]

Y. Jin, T. Okabe, and B. Sendhoff. Adapting Weighted Aggregation for Multiobjective Evolution Strategies. In Lecture Notes in Computer Science 1993.

....Sendho Future Technology Research Honda R D Europe (D) GmbH 63073 O enbach Main, Germany Email: fyaochu.jin, markus.olhofer, bernhard.sendho g hre ftr.f.rd.honda.co. jp Abstract Evolutionary Dynamic Weighted Aggregation (EDWA) has shown to be both e ective and computationally ecient [1] for multiobjective optimization (MOO) Besides, it was also found empirically and surprisingly that EDWA was able to deal with multiobjective optimization problems with a concave Pareto front, which has proved to be beyond the capability of the Conventional Weighted Aggregation (CWA) ....

....more than one Pareto solution. Phenotypic tness sharing is used to keep the diversity of the weight combinations and mating restrictions are required so that the algorithm can work properly. An ecient and e ective method called evolutionary dynamic weighted aggregation (EDWA) was proposed in [1]. The original idea in EDWA was straightforward, i.e. if the weights for the di erent objectives are changing during optimization, the optimizer will go through all points on the Pareto front. If the found non dominated solutions are archived, the whole Pareto front can be achieved. This has been ....

[Article contains additional citation context not shown here]

Y. Jin, T. Okabe, and B. Sendho. Adapting weighted aggregation for multi-objective evolution strategies. In K. Deb, L. Thiele, and E. Zitzler, editors, First International Conference on Evolutionary Multi-criterion Optimization, Lecture Notes in Computer Science, pages 96-110, Zurich, Switzerland, 2001. Springer.

No context found.

Y. Jin, T. Okabe & B. Sendhoff, Adapting weighted aggregation for multi-objective evolution strategies, First International Conference on Evolutionary Multi-criterion Optimization, Lecture Notes in Computer Science, Springer, Zurich, pp. 96-110 (2001).

No context found.

Y. Jin, T. Okabe, and B. Sendhoff, "Adapting Weighted Aggregation for Multiobjective Evolution Strategies," in First International Conference on Evolutionary Multi-Criterion Optimization, E. Zitzler, K. Deb, L. Thiele, C. A. Coello Coello, and D. Corne, Eds. Springer-Verlag. Lecture Notes in Computer Science No. 1993.

No context found.

Y. Jin, T. Okabe, and B. Sendho#. Adapting weighted aggregation for multiobjective evolution strategies. In L. Thiele K. Deb and E. Zitzler, editors, Proceedings of First International Conference on Evolutionary Multi-Criterion Optimization, pages 96--110. Springer, 2001.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC