Information Technology Reference
In-Depth Information
According to the simulation results, HBA provides a good solving efficiency and is
a ponderable challenge target. Although HBA displayed a good solving efficiency, the
quality of global optimal solution in GBA is outstandingly meliorated than it is in
HBA. And the iteration limitation is only set to 1000 in these three kinds of dimen-
sion for GBA. Therefore, GBA not only represents a better quality of global optimal
solution but also requires a less iteration. In addition, the quality of global optimal
solution in HBA is steadier than it is in BA because the statistics including Max. , Min.
and Std. are smaller. This smaller statistics benefits to enhance the reliability for
quality of the global optimal solution. As a whole, in [6], the simulation results show
that BA is better than GA and PSO. And in [10], the HBA improves the solving effi-
ciency of BA. Then, an innovative guidable bat algorithm is proposed in this study.
This proposed algorithm is a perfect swarm-based evolutionary computation and bet-
ter than the above algorithms by the demonstration of simulation results.
5
Conclusions
In this study, GBA based on Doppler Effect is proposed to improve the solving efficien-
cy of BA. The bats in GBA have the ability of guidance by frequency shift based on
Doppler Effect toward the correct direction in guidable search. Moreover, both refined
search and divers search are employed to reinforce the ability of local search and global
search. The bats are able to discover the eligible position to upgrade the position of the
current best bat in a short time. Therefore, the bats are able to rapidly and precisely to
discover the global optimal solution to augment the solving efficiency of the proposed
GBA. GBA is a perfect evolutionary computation and better than the other algorithms
such as GA, PSO, BA and HBA by the demonstration of simulation results. Hence, the
features of context-awareness and collective-effect in EC 2.0 benefit the performance
efficiency of the global optimal solution. In addition, the cooperation, competition and
conflict are not only to balance the operation but also to speed up the advancement in
organization. Additionally, how to adjust the individual behavior with cooperation, com-
petition and conflict to maintain the population advancement will be valuable and diffi-
cult topic for the technology of ECs in future.
Acknowledgement. The authors would like to express their sincere thanks to Minis-
try of Science and Technology, Taiwan (ROC), for financial support under the grants
NSC 102-2218-E-151 -005 and MOST 103-2221-E-151 -041 -.
References
1. Mukhopadhyay, A., Maulik, U., Bandyopadhyay, S., Coello Coello, C.A.: A Survey of
Multiobjective Evolutionary Algorithms for Data Mining: Part I. IEEE Transactions on
Evolutionary Computation 18(1), 4-19 (2014)
2. Mukhopadhyay, A., Maulik, U., Bandyopadhyay, S., Coello Coello, C.A.: A Survey of
Multiobjective Evolutionary Algorithms for Data Mining: Part II. IEEE Transactions on
Evolutionary Computation 18(1), 20-35 (2014)
Search WWH ::




Custom Search