计算机与数字工程2018，Vol.46Issue(1)：35-38,148,5.DOI:10.3969/j.issn.1672-9722.2018.01.009
一种基于k-近邻算法的最优解算法
An Optimal Solution Algorithm Based on k-nearest Neighbour Algorithm
朱俚治1
作者信息
- 1. 南京航空航天大学信息中心 南京 210016
- 折叠
摘要
Abstract
k-nearest neighbor algorithm,simulated annealing algorithm and particle swarm optimization(pso)algorithm are classified and the solving algorithm,the three algorithms are different and each algorithm has its own characteristics. Instance using the k-nearest neighbor algorithm,using the Euclidean distance formula to calculate the distance between the instance to find the op?timal solution,finally realizes the classification of the instance. In this paper,based on the characteristics of the k-nearest neighbor algorithm and the included Angle cosine similarity algorithm is put forward in the k-nearest neighbor classification algorithm in the application and calculation,so as to achieve the instance classification to find the optimal solution. The similarity algorithm in the search for a more optimal solution for application,and the included Angle cosine algorithm as the solution of the evaluation criterion which is the innovation of this article.关键词
相似性/聚类/k-近邻算法/粒子群/夹角余弦Key words
similarity/clustering/k-nearest neighbour algorithm/particle swarm/included Angle cosine分类
信息技术与安全科学引用本文复制引用
朱俚治..一种基于k-近邻算法的最优解算法[J].计算机与数字工程,2018,46(1):35-38,148,5.
