基于WiFi接收信号强度监测的设备类型识别机制  

Identification Mechanism of Device Type Based on Wi-Fi Signal Strength Monitoring

作　　者：姜明星 王玺[2] 郭忠文[2] 王进新 JIANG Ming-Xing;WANG Xi;GUO Zhong-Wen;WANG Jin-Xin(Teaching Center of Fundamental Courses, Ocean University of China, Qingdao 266100, China;College of Information Science and Engineering, Ocean University of China, Qingdao 266100, China)

机构地区：[1]中国海洋大学基础教学中心,山东青岛266100 [2]中国海洋大学信息科学与工程学院,山东青岛266100

出　　处：《中国海洋大学学报（自然科学版）》2020年第10期134-139,共6页Periodical of Ocean University of China

基　　金：国家自然科学基金项目(61379127)资助。

摘　　要：当今WiFi技术迅速发展,WiFi设备的种类和数量随之急剧增长,但WiFi设备识别这方面的研究并不多,仅有的一些研究也过多的依靠beacon节点主动搜集无线信号的方式开展。本文基于非侵入式监测搜集的WiFi信号数据,提出了一种WiFi设备类型的识别机制。通过监测WiFi通信过程中的技术参数,如接收信号强度(Received Signal Strength,RSS)、MAC地址(Media Access Control Address)、通信时间戳等,我们分析提取各类WiFi设备的特征,构建特征向量,然后运用机器学习中相对成熟的分类算法实现对常见无线设备如手机、笔记本电脑和无线路由器的分类。实验结果表明,本文提出的设备类型识别机制使用不同分类算法进行层次化分类后,均可达到较好的效果。With the development of wireless communication technologies,Wi-Fi devices are becoming widely popular and grow rapidly in the amount andvariety and as long as the Wi-Fi functionality of such device is switched on,signals containing lots of information can be monitored.The network traffic problem due to numerousWi-Fi devices has been increasinglystudied by researchers.However tracking network traffic must be built on prioracquaintance of device type.At present,there are not so many studies on recognition of Wi-Fi devices and they all rely on beacon nodes to actively collect wireless signals.In this paper,based on non-invasive collecting of Wi-Fi signal data,a method for classifying Wi-Fi enabled devices is proposed.By constantly monitoring some key parameters in Wi-Fi communication,such as RSS(Received Signal Strength),MAC address,timestamp,etc.we collect a lot of long-term data and divide them in units of 24 hours a day.According to the behavioral patterns of such devices’carriers,we extract different types of devices’features,and represent each device with a feature vector.Then different classifier algorithms are adopted to categorize these common Wi-Fi enabled devices,including smartphones,laptops and wireless routers.According to result of the experiment,the type recognition mechanism proposed in this paper achieves better performance,applying todifferent classification algorithms for hierarchical classification.

关 键 词：WiFi监测 接收信号强度 机器学习 层次化分类 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]