基于二次特征的模糊分类算法在普适计算上下文变化感知中的研究

Further feature based fuzzy classification for context change awareness in pervasive computing

为了简化普适计算环境原始特征的复杂度,方便该环境下的知识推理,采用核典型相关分析方法进行原始特征的二次提取,得到简约而重要的二次特征。在此二次特征的基础上施以模糊K近邻法计算待测模式相对于各类中心的隶属度,并按最大隶属度原则确定该模式所属上下文场景类。本算法致力于在不显著损失分类准确度的情况下尽可能地降低分类复杂度,从而解决普适计算环境中上下文变化感知的问题。

In order to simplify the complexity of the original features,this paper used firstly KCCA to extract compendious and important further features from the original features.Then used fuzzy KNN to calculate the membership degree of the unknown pattern to the center of every context class.Finally,adopted the maximum membership degree principle to determine the class of the unknown pattern.Devoted this algorithm to decrease the classification complexity as much as possible under the condition of not clearly degrading the classification accuracy.Thus could solve effectively the problem of context change awareness in pervasive computing.