TY - GEN

T1 - Hybridisation of Artificial Bee Colony Algorithm on Four Classes of Real-valued Optimisation Functions

AU - Sharma, Mudita

AU - Kazakov, Dimitar Lubomirov

PY - 2017/7/15

Y1 - 2017/7/15

N2 - Hybridisation of algorithms in evolutionary computation (EC) has been used by researchers to overcome drawbacks of populationbased algorithms. The introduced algorithm called mutated Artifi-cial Bee Colony algorithm, is a novel variant of standard Artificial Bee Colony algorithm (ABC) which successfully moves out of local optima. First, new parameters are found and tuned in ABC algorithm. Second, the mutation operator is employed which is responsible for bringing diversity into solution. Third, to avoid tuning 'limit' parameter and prevent abandoning good solutions, it is replaced by average fitness comparison of worst employed bee. Thus, proposed algorithm gives the global solution thus improving the exploration capability of ABC. The proposed algorithm is tested on four classes of problems. The results are compared with six other population-based algorithms, namely Genetic Algorithm (GA), Particle Swarm Optimsation (PSO), Difierential Evolution (DE), standard Artificial Bee Colony algorithm (ABC) and its two variants-quick Artificial Bee Colony algorithm (qABC) and adaptive Artificial Bee Colony algorithm (aABC). Overall results show that mutated ABC is at par with aABC and better than above-mentioned algorithms. The novel algorithm is best suited to 3 of the 4 classes of functions under consideration. Functions belonging to UN class have shown near optimal solution.

AB - Hybridisation of algorithms in evolutionary computation (EC) has been used by researchers to overcome drawbacks of populationbased algorithms. The introduced algorithm called mutated Artifi-cial Bee Colony algorithm, is a novel variant of standard Artificial Bee Colony algorithm (ABC) which successfully moves out of local optima. First, new parameters are found and tuned in ABC algorithm. Second, the mutation operator is employed which is responsible for bringing diversity into solution. Third, to avoid tuning 'limit' parameter and prevent abandoning good solutions, it is replaced by average fitness comparison of worst employed bee. Thus, proposed algorithm gives the global solution thus improving the exploration capability of ABC. The proposed algorithm is tested on four classes of problems. The results are compared with six other population-based algorithms, namely Genetic Algorithm (GA), Particle Swarm Optimsation (PSO), Difierential Evolution (DE), standard Artificial Bee Colony algorithm (ABC) and its two variants-quick Artificial Bee Colony algorithm (qABC) and adaptive Artificial Bee Colony algorithm (aABC). Overall results show that mutated ABC is at par with aABC and better than above-mentioned algorithms. The novel algorithm is best suited to 3 of the 4 classes of functions under consideration. Functions belonging to UN class have shown near optimal solution.

KW - Artificial Bee Colony algorithm

KW - Mutation

KW - Numerical Optimisation

KW - Swarm Intelligence

UR - http://www.scopus.com/inward/record.url?scp=85026867395&partnerID=8YFLogxK

U2 - 10.1145/3067695.3082498

DO - 10.1145/3067695.3082498

M3 - Conference contribution

T3 - GECCO 2017 - Proceedings of the Genetic and Evolutionary Computation Conference Companion

SP - 1439

EP - 1442

BT - GECCO 2017 - Proceedings of the Genetic and Evolutionary Computation Conference Companion

ER -