基于稀疏自编码器和SVM的垃圾短信过滤  

Spam messages filtering based on sparse auto-encoder and SVM

作　　者：王贵新 彭娟 郑孝宗 张小川[2] 

机构地区：[1]重庆工程学院,重庆400056 [2]重庆理工大学,重庆402260

出　　处：《现代电子技术》2016年第17期145-148,共4页Modern Electronics Technique

基　　金：国家自然科学基金项目(60443004):人工生命动觉智能行为选择图式理论研究;校内科研基金资助项目(2014xcxtd05;2014xzky05)

摘　　要：在垃圾短信过滤系统中,传统方法的短信息特征很难准确地考虑到词语的贡献。提出了一种新的特征词查找和特征构造方法,较好地反映了词语之间的关系和在短信中的贡献度。通过联合采用稀疏自编码器和支撑矢量机(SVM)进行学习和分类仿真实验,结果表明过滤效果比目前报道的类似分类器效果有显著的提升和改进。In the spam messages filtering system,the traditional methods are difficult to consider the words contribution for short message feature correctly,so a new feature words search and feature construction method is proposed,which can reflect the relationship among the words and contribution in short messages. The simulation experiments of learning and classification were performed in combination with the sparse auto-encoder and support vector machine（SVM）. The results show that,in comparison with the reported similar classifiers,the filtering effect of the proposed method is promoted and improved significantly.

关 键 词：支撑矢量机 稀疏自编码器 短信 特征提取 

分 类 号：TN911-34[电子电信—通信与信息系统] TP391[电子电信—信息与通信工程]