面向遥感影像分类的时延权重及群体分类PSO改进方法

粒子群优化是经典的优化算法，其适用于多种情况目标最优解的获取。本文引入时延权重系数及粒子群群体分类方法，提出了一种基础粒子群改进算法，并将该算法应用于遥感影像分类，取得了理想的数据处理结果。本文以复杂的数据模型对改进算法进行了分析，相对基础粒子群算法优势明显，可以在较少粒子群个数及迭代次数的情况下取得较高精度的目标解。改进算法大幅减少了计算的时间复杂度，能够有效降低遥感大数据处理的时间成本，在遥感领域具有较好的推广价值。

An Improved Approach to PSO through Time-delay Weight Factors and Group Classification for Remote Sensing Image Classification

Particle swarm optimization is a classical optimization algorithm, which is applicable to the acquisition of optimal solutions of objectives for a variety of situations. In this paper, a time-delay weight and particle swarm population classification method is used to improve the PSO algorithm. This method is used in remote sensing image classification and satisfactory data processing results have been achieved . The improved algorithm with a complex mathematical model has been analyzed. It has obvious advantages over the basic PSO algorithm and can achieve a higher accuracy target solution with a smaller number of particles and iterations. The improved algorithm significantly reduces the time complexity of computation and can effectively reduce the time cost of remote sensing big data processing, which is of good value for promotion in the field of remote sensing.