深度置信网络在垃圾邮件过滤中的应用  

Application of deep belief nets in spam filtering

作　　者：孙劲光[1] 蒋金叶[2] 孟祥福[1] 李秀娟[2] 

机构地区：[1]辽宁工程技术大学电子与信息工程学院,辽宁葫芦岛125105 [2]辽宁工程技术大学研究生学院,辽宁葫芦岛125105

出　　处：《计算机应用》2014年第4期1122-1125,共4页journal of Computer Applications

基　　金：国家青年科学基金资助项目(61003162);国家科技支撑计划项目(2013bah12f01)

摘　　要：针对深层神经网络初始化方法不明确、泛化能力差而导致解决垃圾邮件过滤时效果较差的问题,提出了基于深度置信网络的分类方法。深度置信网络通过逐层无监督的方法来预训练网络,实现了网络的初始化。在LingSpam,SpamAssassin和Enron1三个广泛使用的数据集上,通过与目前最好的垃圾邮件过滤方法支持向量机(SVM)在分类性能上进行比较,实验结果表明深度置信网络的垃圾邮件过滤方法是有效的,获得了较高的准确率和召回率。Concerning the problem that how to initialize the weights of deep neural networks,which resulted in poor solutions with low generalization for spam filtering,a classification method of Deep Belief Net （DBN） was proposed based on the fact that the existing spam classifications are shallow learning methods.The DBN was pre-trained with the greedy layerwise unsupervised algorithm,which achieved the initialization of the network.The experiments were conducted on three datesets named LinsSpam,SpamAssassin and Enronl.It is shown that compared with Support Vector Machines （SVM） which is the state-of-the-art method for spam filtering in terms of classification performance,the spam filtering using DBN is feasible,and can get better accuracy and recall.

关 键 词：垃圾邮件 深度置信网络 分类 受限玻尔兹曼机 支持向量机 

分 类 号：TP393.098[自动化与计算机技术—计算机应用技术]