Based on the factor of self-adaptive weight sum and self-adaptive penalty function, a self-adaptive genetic algorithm is proposed and applied to solve multi-objective reactive power optimization. 引入了自适应权重和因子及自适应罚函数的概念,提出了一种自适应遗传算法,将其应用于多目标无功优化问题的求解中。
The weight function models for penalty factor are generated according to the energy distribution characteristic of DCT coefficients and the human visual system models, and then these models are applied into the learning process of weighted SVM. 根据变换域系数的能量分布特征和人类视觉系统模型对惩罚因子建立加权函数模型,并将该模型应用到加权支持向量回归训练中。
It utilizes the prior variance - mean relationship to construct the weight matrix and the two - dimensional ( 2D ) spatial information as the penalty or regularization operator. 该方法可利用均值-方差间关系等先验知识来构造加权矩阵,并利用二维局部空间信息来构造惩罚项或正则算子。