基于双隐层极限学习机的模糊XML文档分类

发布时间：2019-07-13 21:00

【摘要】：随着大数据时代的到来,对异构和分布式的模糊XML数据管理显得越来越重要。在模糊XML数据的管理中,模糊XML文档的分类是关键问题。针对模糊XML文档的分类,提出采用双隐层极限学习机模型来实现模糊XML文档自动分类。这个模型可以分为两个部分:第一层采用极限学习机提取模糊XML文档的相应特征,第二层利用核极限学习机根据这些特征进行最终的模糊XML文档分类。通过实验验证了所提方法的性能优势。首先对主要的调节参数包括隐藏层节点的数目L,常量C和核参数γ进行了研究,接下来的对比实验说明提出的基于双隐层ELM(Extreme Learning Machine)的方法相较于传统单隐层ELM以及SVM(Support Vector Machine)方法,分类精度得到较大提高,训练时间进一步缩减。
[Abstract]:With the advent of big data era, heterogeneous and distributed fuzzy XML data management is becoming more and more important. In the management of fuzzy XML data, the classification of fuzzy XML documents is the key problem. Aiming at the classification of fuzzy XML documents, a double hidden layer limit learning machine model is proposed to realize the automatic classification of fuzzy XML documents. The model can be divided into two parts: the first layer uses limit learning machine to extract the corresponding features of fuzzy XML documents, and the second layer uses kernel limit learning machine to classify fuzzy XML documents according to these features. The performance advantages of the proposed method are verified by experiments. Firstly, the main adjustment parameters, including the number of hidden layer nodes L, constant C and kernel parameter 纬, are studied. Then, the comparative experiments show that compared with the traditional single hidden layer ELM and SVM (Support Vector Machine) methods, the proposed method based on double hidden layer ELM has a great improvement in classification accuracy and further reduces the training time.
【作者单位】：东北大学计算机科学与工程学院;渤海大学信息科学与技术学院;
【基金】：国家自然科学基金(No.61370075,No.61073139,No.61202260) 教育部新世纪优秀人才支持计划项目(No.NCET-05-0288)
【分类号】：TP391.1;TP18

【相似文献】