遗传算法的粗糙集理论在文本降维上的应用  

Genetic algorithm of rough set theory in text dimension reduction applications

作　　者：赵东红[1,2] 王来生[2] 张峰[1] 

机构地区：[1]北京科技大学数理学院应用数学系,北京100083 [2]中国农业大学理学院数学系,北京100085

出　　处：《计算机工程与应用》2012年第36期125-128,共4页Computer Engineering and Applications

基　　金：国家自然科学基金(No.10771213)

摘　　要：遗传算法作为一种有效的全局并行优化搜索工具,早被众多应用领域所接受。根据问题提出了相应的适应度函数,针对遗传算法和粗糙集理论两种方法各自的特点,将两种算法适当结合。还把结合后的方法和单一的粗糙集算法在文本分类效果上进行了对比。实验结果表明将遗传算法和粗糙集理论相结合的优化方法来应用到特征提取中,比单一的粗糙集算法,具有更好的降维效果,使得降维后的特征词更有利于文本数据的分类,大大优化了文本分类的效果。Genetic algorithms as an effective search tool for optimizing the overall parallel, its many applications have been accepted early. This paper makes some improvements on the foundations of former genetic algorithms which are connected with related concepts and knowledge of rough set, puts forward new adapting degree function, and focuses on genetic algorithms and rough set algorithms on feature extraction and text classification. At the same time, it compares combined algorithms with single rough set algorithms. The experiment results indicate that com- bined use of genetic algorithms and the rough set in feature extraction, makes drop-dimensional characteristics of the words more conducive for the classification of text data, greatly optimizes the text classification results.

关 键 词：混合遗传算法 特征降维 文本分类 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]