利用微粒群算法（pso）优化支持向量机（SVM）的参数-c,-g-Using pso optimized support vector machine parameters-c,-g

：针对发酵过程中生物参数难以实时在线测量的问题，建立了用于生物参数状态预估的 支持向量机软测量模型。考虑到该支持向量回归(SVR)模型的复杂性和冷化特征取决于其三 个参数 ，c， 能否取到最优值，采用粒子群优化(PSO)算法实现对参数 ，c， 的同时寻优。在 此基础上，以饲料用 ．甘露聚糖酶为对象，建立了基于PSO—SVR的发酵过程产物浓度状态预估 模型。发酵罐控制结果表明：该模型具有很好的学习精度和泛化能力，可实现对 ．甘露聚糖酶 产物浓度的实时在线预估。-In

Feature selection methods for machine learning algorithms such as SVR, including one filter-based method (CFS) and two wrapper-based methods (GA and PSO). The gridsearch is for the grid search for the optimal hyperparemeters of SVR. The SVM_CV is for

以优化SVR算法的参数c和g为例，对DE（差分进化）算法MATLAB源码进行了详细中文注解。(Differential Evolution algorithm (DE) is a heuristic random search algorithm based on group differences. This algorithm is proposed by R.S and k.p. rice for solving Chebyshev polynomials. DE algorithm is

基于粒子群优化的向量回归预测分析 matlab代码(Support vector regression code with pso)