Research On Improved Bacterial Foraging Optimization Algorithm And Its Applications

The Bacterial Foraging Optimization algorithm(BFO)is a natureinspired optimization algorithm based on the foraging behavior of Escherichia coli.Due to its simplicity and effectiveness,BFO has been applied widely in many engineering and scientific fields.However,BFO suffers from multiple drawbacks,including slow convergence speed,inability to jump out of local optima and fixed step length.In order to overcome the weakness of the original BFO,in this paper,two improved BFO algorithms are proposed,and apply the proposed improved BFO algorithms to practical problems such as engineering optimization problems,disease diagnosis,and financial risk prediction.The main contributions of this paper are as follows:1?In order to achieve a more suitable balance between the exploitation and exploration capabilities of the original BFO in the process of BFO algorithm optimization,this paper introduces chaotic operations to propose an improved BFO,which is called Chaotic BFO.Specifically,a chaotic initialization strategy is incorporated into BFO for bacterial population initialization to achieve acceleration throughout early steps of the proposed algorithm.Then,a chaotic local search with a “shrinking” strategy is introduced into the chemotaxis step to escape from local optimum.The performance of Chaotic BFO was validated on 23 numerical well-known benchmark functions by comparing with 10 other competitive metaheuristic algorithms.Moreover,it was applied to two real-world benchmarks problems from IEEE CEC2011,as well as two classical engineering design problems.The experimental results demonstrate that Chaotic BFO is superior to its counterparts in both convergence speed and solution quality in most of the cases.The Chaotic BFO algorithm proposed in this paper is of great significance for promoting the research,improvement and application of the BFO algorithm.2?In addition,in order to change the fixed step size of the original BFO,increase the diversity of the population,avoid falling into the local optimum,which is conducive to the global search,so as to improve the convergence speed and accuracy of the algorithm.In this paper,an enhanced BFO called CCGBFO with adaptive step size adjustment,Gaussian mutation and local adaptive search strategy guided by the current optimal solution is also proposed.First,a step size adaptive adjustment operation is used to produce adaptive chemotaxis step length.Then,by combining the optimal position in the current bacteria with the Gaussian mutation operation to make full use of the information of the optimal position.Finally,a local adaptive search strategy guided by the current optimal solution is introduced into the chemotaxis step to ensure that the algorithm can explore a large search space in the early stage.The performance of CCGBFO was evaluated on a comprehensive set of numerical benchmark functions including IEEE CEC2014 and CEC2017 problems.In addition,CCGBFO was also used to tune the key parameters of kernel extreme learning machine for dealing with the real-world problems of disease classification and financial risk prediction.The experimental results show that the proposed CCGBFO significantly outperforms the original BFO in terms of both convergence speed and solution accuracy.