Along with the development and progress of science and technology,people often encounter the most optimal solution in our research,practice and daily life.Exploring an effective and simple method to solve optimization problems has become one of some research directions.In recent years,many scholars will be shuffled frog leaping algorithm is applied to optimization in various fields,and get some research results.The shuffled frog leaping algorithm is an intelligent bionic algorithm from the frog group foraging activity generated by nature,this algorithm has a variable factor small,this algorithm has many advantages such as variable factors,easy to understand,parallel search,and so on,it has become one of the hot spots in optimization problem solving.However,the algorithm also has its disadvantages: dependence on initial values and the slow speed of convergence.In this paper,we first analyze some scholars about the algorithm results and theory,on the basis of this,aiming at the disadvantage,the shuffled frog leaping algorithm is improved through initialization,individual variation and the frog population grouping.The improved algorithm is applied to the traditional algorithm,which obviously improves the performance of the traditional algorithm;In addition,the improved algorithm is applied to the two-dimensional path planning,the experiment proved that the algorithm has a good path planning effect.The specific work of this paper is as follows:(1)In this paper,we first introduce the selected topic background,the significance of the research and related theories,analyzes the present situation of the research,aiming at the defects of shuffled frog leaping algorithm convergence speed and local search speed is slow,the shuffled frog leaping algorithm is improved through initialization,individual variation and the frog population grouping,after the simulation experiment in the standard function,it shows the superiority of the improved algorithm.(2)Traditional k-means algorithms rely too much on initial value setting,easy issues such as local optimization,the improved hybrid shuffled frog leaping algorithm is applied to the k-means algorithm,experimental results show that the combined algorithm effectively overcomes the kmeans algorithm in the presence of problem.(3)The improved shuffled frog leaping algorithm is applied to the traditional collaborative filtering algorithm.Firstly clustering and filling score matrix,again using the improved shuffled frog leaping algorithm to calculate the neighbor set,finally prediction score.By data experiments show that the improved recommendation algorithm has better.(4)In order to reflect the widespread application algorithm,the improved hybrid shuffled frog leaping algorithm for two-dimensional static path planning,the path planning problem is converted into the optimal solution of the problem,and then use the improved shuffled frog leaping algorithm for adapting to the minimum value of the function,get the optimal path,the experiments show,relative to other swarm intelligence algorithm of path planning,based on the improved shuffled frog leaping algorithm of path planning with better results. |