摘要
空间分类是空间数据挖掘的重要分支,寻找高效的空间分类算法是空间分类研究的重要方向.在空间对象的邻接图及朴素贝叶斯分类法的基础上提出一个新的空间分类算法,该算法对空间对象进行分类时,既考虑了待分类对象的属性对分类的影响,又考虑了其空间邻接对象对它分类的影响.该算法的计算复杂度不高,分类的正确性好.
Spatial classification is one main case of spatial data mining.Finding effective spatial classification algorithm is an important problem of spatial classification.It is presented a new spatial classification algorithm based on neighbor graph and nave Bayesian classifier.The algorithm takes the attributes of classifying object and its neighbor objects into account when classifying spatial objects.The algorithm have low computing cost and high classifying accuracy.
出处
《云南大学学报（自然科学版）》
CAS
CSCD
2004年第4期297-300,共4页
Journal of Yunnan University(Natural Sciences Edition)
基金
云南省自然科学基金资助项目(2002F0013M).
