quotation:		[Copy]
		[Copy]

This Paper:Browse 2456 Download 48
物联网终端自动识别方法
沈艳,席兵,张治中
0 Fontlarge +\|Default\|Small
(1.重庆邮电大学通信与信息工程学院，重庆 400065;2.南京信息工程大学电子与信息工程学院，南京210044)

摘要:

针对物联网终端设备类型复杂、数量繁多，传统的识别方法难以对终端进行精准识别的问题，提出了一种新的终端自动识别方法。该方法利用ZMap工具在网络中进行扫描，对扫描出的主机发送“get”请求以获取终端的登录页面，并根据超文本标记语言源代码、超文本传输协议中响应头字段和导航栏信息构建终端特征数据库，并利用长短期记忆(Long ShortTerm Memory,LSTM)算法生成三级分类器，实现对终端进行类型、品牌及版本的自动识别。实验结果表明，该方法在F1score上表现出优异的结果，最高可达98.4〖WT《Times New Roman》〗%〖WTBZ〗，对于具体品牌“TPLink”交换机识别的准确率最高为99〖WT《Times New Roman》〗%〖WTBZ〗，召回率最高为98.7〖WT《Times New Roman》〗%〖WTBZ〗。由此可见，该方法具有精准识别终端属性的优点。

关键词: 物联网终端自动识别 LSTM算法三级分类

DOI：

基金项目:国家重点研发计划（2018YFB2100200）

Automatic identification method for Internet of Things terminal

SHEN Yan,XI Bing,ZHANG Zhizhong

(1.School of Communication and Information Engineering,Chongqing University of Posts and Telecommunications,Chongqing 400065;2.School of Electronics and Information Engineering,Nanjing University of Information Technology,Nanjing 210044,China)

Abstract:

For the problem that the types of Internet of Things(IoT) terminals are complex and numerous,and the traditional methods are difficult to accurately identify the terminal,a new automatic terminal identification method is proposed.This method uses the ZMap tool to scan the network and sends a “get” request to the scanned host to obtain the login page of the terminal.Based on the source code of Hyper Text Markup Language(HTML) and the response header fields and navigation bar information in Hyper Text Transfer Protocol(HTTP),an IoT terminal feature database is established.In the meantime,the long shortterm memory(LSTM) algorithm is used to generate a threelevel classifier to realize automatic identification of the terminal type,brand and version.The experimental results illustrate that this method has excellent results on F1score,with a value of up to 98.4〖WT《Times New Roman》〗%〖WTBZ〗.The recognition accuracy rate of the specific brand “TPLink” switch is up to 99〖WT《Times New Roman》〗%〖WTBZ〗,and the recall rate is up to 98.7〖WT《Times New Roman》〗%〖WTBZ〗.It can be seen that this method has the advantage of accurately identifying terminal attributes.

Key words: Internet of Things(IoT) terminal automatic identification LSTM algorithm three level classification