1 简介近年来已有越来越多的建模方法被相关学者提出用来解决分类识别、风险预测、效能评估等问题这些建模方法包括时间序列分析、灰色理论、神经网络等。但是时间序列分析方法复杂且预测精度较低灰色理论需要规律性的数据神经网络方法易出现过拟合以及易陷入局部极值等问题。支持向量机Support Vector MachineSVM是一种基于结构风险最小化且有着强大的泛化能力的建模方法。它可以很好地解决小样本、非线性以及陷入局部极值等问题。然而SVM的学习能力和泛化能力取决于合适的参数选择这些参数直接影响了模型的性能。因此近年来越来越多的参数优化方法被应用于 SVM的参数选择问题比如网格搜索法、粒子群算法、蝙蝠算法等然而网格搜索法运算量大搜索效率低粒子群算法和蝙蝠算法在参数寻优过程中会出现收敛速度慢、易陷入局部极值的问题。花朵授粉算法Flower Pollinate AlgorithmFPA 是由英国学者 Xin- She Yang 受开花植物授粉过程的启发于 2012 年提出的一种新型元启发式群智能算法该算法简单易实现且有着新颖的寻优结构可以很好地实现全局搜索与局部搜索之间的平衡具有较大的研究潜力目前已被成功应用于图形着色、特征选择、电力系统优化等问题。本文提出的 FPA—SVM模型仿真结果表明该模型预测精度较高。2 部分代码clc clear all close all n30; % Population size, typically 10 to 25 p0.8; % probabibility switch % Iteration parameters N_iter3000; % Total number of iterations fitnessMSE ones(1,N_iter); % % Dimension of the search variables Example 1 d2; Lb -1*ones(1,d); Ub 1*ones(1,d); % % Dimension of the search variables Example 2 % d3; % Lb [-2 -1 -1]; % Ub [2 1 1]; % % % Dimension of the search variables Example 3 % d3; % Lb [-1 -1 -1]; % Ub [1 1 1]; % % % % % Dimension of the search variables Example 4 % d9; % Lb -1.5*ones(1,d); % Ub 1.5*ones(1,d); % Initialize the population/solutions for i1:n, Sol(i,:)Lb(Ub-Lb).*rand(1,d); % To simulate the filters use fitnessX() functions in the next line Fitness(i)fitness(Sol(i,:)); end % Find the current best [fmin,I]min(Fitness); bestSol(I,:); SSol; % Start the iterations -- Flower Algorithm for t1:N_iter, % Loop over all bats/solutions for i1:n, % Pollens are carried by insects and thus can move in % large scale, large distance. % This L should replace by Levy flights % Formula: x_i^{t1}x_i^t L (x_i^t-gbest) if randp, %% Lrand; LLevy(d); dSL.*(Sol(i,:)-best); S(i,:)Sol(i,:)dS; % Check if the simple limits/bounds are OK S(i,:)simplebounds(S(i,:),Lb,Ub); % If not, then local pollenation of neighbor flowers else epsilonrand; % Find random flowers in the neighbourhood JKrandperm(n); % As they are random, the first two entries also random % If the flower are the same or similar species, then % they can be pollenated, otherwise, no action. % Formula: x_i^{t1}epsilon*(x_j^t-x_k^t) S(i,:)S(i,:)epsilon*(Sol(JK(1),:)-Sol(JK(2),:)); % Check if the simple limits/bounds are OK S(i,:)simplebounds(S(i,:),Lb,Ub); end % Evaluate new solutions % To simulate the filters use fitnessX() functions in the next % line Fnewfitness(S(i,:)); % If fitness improves (better solutions found), update then if (FnewFitness(i)), Sol(i,:)S(i,:); Fitness(i)Fnew; end % Update the current global best if Fnewfmin, bestS(i,:) ; fminFnew ; end end % Display results every 100 iterations if round(t/100)t/100, best fmin end fitnessMSE(t) fmin; end %figure, plot(1:N_iter,fitnessMSE); % Output/display disp([Total number of evaluations: ,num2str(N_iter*n)]); disp([Best solution,num2str(best), fmin,num2str(fmin)]); figure(1) plot( fitnessMSE) xlabel(Iteration); ylabel(Best score obtained so far);3 仿真结果4 参考文献[1]王玉鑫, 李东生, 高杨. (2018). 基于改进型花朵授粉算法的svm参数优化. 火力与指挥控制, 43(10), 6.部分理论引用网络文献若有侵权联系博主删除。
)
