Abstract Nondominated Neighbor Immune Algorithm (NNIA) is a Representative algorithm for multi-objective problems (MOPs). However, for some test problems, the diversity or convergence of NNIA cannot always keep very well. In order to avoid this phenomenon as well as not to increase the number of function evaluations as far as possible, a modified Invasive Weed Optimization (IWO) operator is introduced into NNIA and we proposed an improved NNIA for MOPs, denoted as NNIAIWO. There are three modifications for basic IWO. Firstly, each parent weed generates two weeds called associated parent weeds which do not join in the evaluation but produce new seeds; Secondly, these new seeds generated by the associated parent weeds distribute obey Cauchy distribution near them; Thirdly an oscillator factor is adopted in the calculation of the standard deviation during the iteration process. Fifteen benchmark problems are used to validate the performance of the proposed algorithm. Experimental results shows that NNIAIWO can obtain improved performance on some test problems, meanwhile the numbers of function evaluation do not increase. And for five complex unconstrained MOPs, namely UF, NNIAIWO also presents a better performance than NNIA.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Improved Artificial Weed Colonization Based Multi-objective Optimization Algorithm


    Contributors:
    Liu, Ruochen (author) / Wang, Ruinan (author) / He, Manman (author) / Wang, Xiao (author)


    Publication date :

    2017-01-01


    Size :

    10 pages





    Type of media :

    Article/Chapter (Book)


    Type of material :

    Electronic Resource


    Language :

    English