【SVM分类】基于哈里斯鹰算法优化支持向量机SVM实现分类附matlab的代码
1 简介
提出一种基于哈里斯鹰优化算法(HHO)和支持向量机(SVM)的股价预测方法.针对SVM预测模型参数难以确定的问题,采用HHO算法对SVM中惩罚因子及核函数参数进行优化,构建HHOSVM股价预测模型。
支持向量机是利用已知数据类别的样本为训练样本，寻找同类数据的空间聚集特征，从而对测试样本进行分类验证，通过验证可将分类错误的数据进行更正。本文以体检数据为数据背景，首先通过利用因子分析将高维数据进行降维，由此将所有指标整合成几个综合性指标；为降低指标之间的衡量标准所引起的误差，本文利用 MATLAB软件将数据进行归一化处理，结合聚类分析将数据分类；最后本文利用最小二乘支持向量机分类算法进行分类验证，从而计算出数据分类的准确率，并验证了数据分类的准确性和合理性。
2 部分代码
function [sFeat,Sf,Nf,curve] = jBHHO(feat,label,N,max_Iter,HO)beta = 1.5;ub = 1;lb = 0;fun = @jFitnessFunction;dim = size(feat,2);X = zeros(N,dim);for i = 1:Nfor d = 1:dimif rand() > 0.5= 1;endendendfitR = inf;fit = zeros(1,N);Y = zeros(1,dim);Z = zeros(1,dim);curve = inf;t = 1;start-------------------------------------------------while t <= max_Iterfor i = 1:N= fun(feat,label,X(i,:),HO);if fit(i) < fitRfitR = fit(i);Xrb = X(i,:);endendX_mu = mean(X,1);for i = 1:NE0 = -1 + 2 * rand();E = 2 * E0 * (1 - (t / max_Iter));if abs(E) >= 1q = rand();if q >= 0.5k = randi([1,N]);r1 = rand();r2 = rand();for d = 1:dimXn = X(k,d) - r1 * abs(X(k,d) - 2 * r2 * X(i,d));S = 1 / (1 + exp(-Xn));if rand() < S= 1;else= 0;endendelseif q < 0.5r3 = rand();r4 = rand();for d = 1:dimXn = (Xrb(d) - X_mu(d)) - r3 * (lb + r4 * (ub - lb));S = 1 / (1 + exp(-Xn));if rand() < S= 1;else= 0;endendendelseif abs(E) < 1J = 2 * (1 - rand());r = rand();if r >= 0.5 && abs(E) >= 0.5for d = 1:dimDX = Xrb(d) - X(i,d);Xn = DX - E * abs(J * Xrb(d) - X(i,d));S = 1 / (1 + exp(-Xn));if rand() < S= 1;else= 0;endendelseif r >= 0.5 && abs(E) < 0.5for d = 1:dimDX = Xrb(d) - X(i,d);Xn = Xrb(d) - E * abs(DX);S = 1 / (1 + exp(-Xn));if rand() < S= 1;else= 0;endendelseif r < 0.5 && abs(E) >= 0.5LF = jLevyDistribution(beta,dim);for d = 1:dimYn = Xrb(d) - E * abs(J * Xrb(d) - X(i,d));S = 1 / (1 + exp(-Yn));if rand() < S= 1;else= 0;endZn = Y(d) + rand() * LF(d);S = 1 / (1 + exp(-Zn));if rand() < S= 1;else= 0;endendfitY = fun(feat,label,Y,HO);fitZ = fun(feat,label,Z,HO);if fitY <= fit(i)= fitY;:) = Y;endif fitZ <= fit(i)= fitZ;:) = Z;endelseif r < 0.5 && abs(E) < 0.5LF = jLevyDistribution(beta,dim);for d = 1:dimYn = Xrb(d) - E * abs(J * Xrb(d) - X_mu(d));S = 1 / (1 + exp(-Yn));if rand() < S= 1;else= 0;endZn = Y(d) + rand() * LF(d);S = 1 / (1 + exp(-Zn));if rand() < S= 1;else= 0;endendfitY = fun(feat,label,Y,HO);fitZ = fun(feat,label,Z,HO);if fitY <= fit(i)= fitY;:) = Y;endif fitZ <= fit(i)= fitZ;:) = Z;endendendend= fitR;%d Best (BHHO)= %f',t,curve(t))t = t + 1;endPos = 1:dim;Sf = Pos(Xrb == 1);Nf = length(Sf);sFeat = feat(:,Sf);endfunction LF = jLevyDistribution(beta,dim)nume = gamma(1 + beta) * sin(pi * beta / 2);deno = gamma((1 + beta) / 2) * beta * 2 ^ ((beta - 1) / 2);sigma = (nume / deno) ^ (1 / beta);u = randn(1,dim) * sigma;v = randn(1,dim);step = u ./ abs(v) .^ (1 / beta);LF = 0.01 * step;end
3 仿真结果
4 参考文献
[1]董婷. 支持向量机分类算法在MATLAB环境下的实现[J]. 榆林学院学报, 2008, 18(4):3.