基于属性加权k最近邻算法的降雨预测  

Method for precipitation forecast based on improved k-nearest neighbor algorithm

作　　者：周芸 杜景林[1] 陶晔 ZHOU Yun;DU Jing-lin;TAO Ye(School of Electronic and Information Engineering,Nanjing University of Information Science and Technology,Nanjing 210044,China)

机构地区：[1]南京信息工程大学电子与信息工程学院,江苏南京210044

出　　处：《计算机工程与设计》2020年第6期1605-1609,共5页Computer Engineering and Design

基　　金：国家自然科学基金项目(41575155);2018年江苏省研究生实践创新计划基金项目(1344051901038)。

摘　　要：针对传统k最近邻算法处理多维数据分类时,没有考虑不同属性对分类结果的影响程度存在相异性这一问题,提出一种基于属性重要度的k最近邻算法。将大气压强、风向、风速、气温和相对湿度作为样本属性,将降水量作为类,利用属性空间上同类数据分布的内聚性和异类数据的耦合性确定样本属性的权重,通过属性加权欧氏距离进行近邻搜索,实现最优分类。实验结果表明,该降水模型在性能指标上表现更优,提高了预报结果的准确率、TS评分和正样本概括率,降低了降水预测的标准误差与漏报率。To address the problem that k-nearest neighbor algorithm ignores the influence of different attributes on the classification results when dealing with multi-dimensional data classification,a k-nearest neighbor algorithm based on attribute significance was proposed to improve the classification performance of classifiers.Using pressure,wind direction,wind speed,temperature and relative humidity as the feature of the sample and the observed precipitation data as the class,a weight was set to each attri-bute according to the cohesion and heterogeneity of data distribution of same category.The neighborhood search was implemented using weighted Euclidean distance to achieve optimal classification.The results show that the proposed precipitation model performs better.The accuracy,TS score and positive sample summary rate of forecast result are increased,and the standard error and false negative rate of precipitation prediction are reduced.

关 键 词：数据挖掘 K最近邻算法 属性重要度 气象要素 降雨预测 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]