基于WiFi信号的入侵检测机理及实验研究
|
摘要
室内安全关乎人们的生命财产安全,通过室内入侵检测可以达到预警、避免损失的目的。与常见的入侵检测方法不同,利用了无线通信信号WiFi的信道状态信息(Channel Status Information,CSI)与人体行为的关联,可以达到入侵检测的目的。研究了信道冲击响应与信道频率响应及CSI的关系,并利用CSI数据集EHUCOUNT和机器学习方法仿真验证了CSI与人行为的关联,结果表明6种典型场景下SVM (Support Vector Machine)入侵检测准确率为93. 35%～99. 23%; CNN (Convolutional Neural Network)入侵检测准确率为89. 17%～99. 14%。通过研制的专用谱传感节点采集WiFi信号进行实际场景测试,证明入侵检测准确率为98%,这表明基于WiFi信号的入侵检测具有应用价值。
Indoor safety concerns the safety of people ′ s life and property. Through indoor intrusion detection, it is possible to achieve early warning and avoid loss. Different from the common intrusion detection methods, the CSI( Channel status information) of the wireless communication signal WiFi is used to correlate with human behavior, which can achieve intrusion detection. The rela-tionship between channel impulse response, channel frequency response and CSI is studied. The association between CSI and human behavior is verified using CSI dataset EHUCOUNT and machine learning method. The results show that the accuracy of intrusion detection based on SVM( Support Vector Machine) and CNN( Convolutional Neural Network) in six typical scenarios is 93. 35 % ～99. 23 % and 89. 17 % ～ 99. 14 %, respectively. Actual tests are carried out through collecting the WiFi signal using self-made spec-trum sensor nodes. Experiment results show that intrusion detection accuracy is about 98 %, which indicates that the intrusion detec-tion based on WiFi signal is applicable to real scenario.
Indoor safety concerns the safety of people ′ s life and property. Through indoor intrusion detection, it is possible to achieve early warning and avoid loss. Different from the common intrusion detection methods, the CSI( Channel status information) of the wireless communication signal WiFi is used to correlate with human behavior, which can achieve intrusion detection. The rela-tionship between channel impulse response, channel frequency response and CSI is studied. The association between CSI and human behavior is verified using CSI dataset EHUCOUNT and machine learning method. The results show that the accuracy of intrusion detection based on SVM( Support Vector Machine) and CNN( Convolutional Neural Network) in six typical scenarios is 93. 35 % ～99. 23 % and 89. 17 % ～ 99. 14 %, respectively. Actual tests are carried out through collecting the WiFi signal using self-made spec-trum sensor nodes. Experiment results show that intrusion detection accuracy is about 98 %, which indicates that the intrusion detec-tion based on WiFi signal is applicable to real scenario.
引文
[1]段玮倩,胡岸勇,苗俊刚.射频与微波技术在安防领域的应用[J].电子技术应用,2017,43(7):4-7,15.
[2]蔡彬彬,包亚萍,陶卉,等.基于ZigBee协议的红外入侵检测系统的设计[J].电子技术应用,2007,33(11):97-99,103.
[3]GHOSH A,CHAKRABORTY D,PRASAD D,et al.Can we recognize multiple human group activities using ultrasonic sensors[C].2018 10th International Conference on Communication Systems&Networks(COMSNETS),Bengaluru,2018:557-560.
[4]王俊,郑彤,雷鹏,等.深度学习在雷达中的研究综述[J].雷达学报,2018,7(4):395-411.
[5]黄凯奇,陈晓棠,康运锋,等.智能视频监控技术综述[J].计算机学报,2015,20(6):1093-1118.
[6]鲁勇,吕绍和,王晓东,等.基于WiFi信号的人体行为感知技术研究综述[J/OL].计算机学报,2018,41(27):1-22.[2018-11-06].http://kns.cnki.net/kcms/detail/11.1826.TP.20180303.1407.018.html.
[7]庞娜.基于WiFi的非入侵式异常用户活动检测[J].信息安全研究,2018,4(8):711-714.
[8]周启臻,邢建春,杨启亮.基于信道状态信息相位差的人员入侵检测方法[J].传感技术学报,2018(1):103-109.
[9]DOMENICO S D,SANCTIS M D,CIANCA E,et al.WiFibased through-the-wall presence detection of stationary and moving humans analyzing the doppler spectrum[J].IEEEAerospace and Electronic Systems Magazine,2018,33(5-6):14-19.
[10]Wang Jie,Zhao Yunong,Fan Xinxin,et al.Device-free identification using intrinsic CSI features[J].IEEE Transactions on Vehicular Technology,2018,PP(99):1.
[11]MOORE R,HOWARD R,KUKSA P,et al.A geometric approach to device-free motion localization using signal strength[OL].(2010-xx-xx)[2018-11-06].https://doi.org/doi:10.7282/T3PC35T2.
[12]SOBRON I,SER J D,EIZMENDI I,et al.Device-free people counting in IoT environments:new insights,results and open challenges[J].IEEE Internet of Things Journal,2018,PP(99):1.
[13]HAN C,TAN Q,SUN L,et al.CSI frequency domain fingerprint-based passive indoor human detection[J].Information,2018,9(4):95.
[14]DOMENICO S D,PECORARO G,CIANCA E,et al.Trained-once device-free crowd counting and occupancy estimation using WiFi:a Doppler spectrum based approach[C].2016 IEEE 12th International Conference on Wireless and Mobile Computing,Networking and Communications(WiMob).IEEE,2016:1-8.
[15]苑霸,姚萍,郑天垚.基于权重归一化奇异值分解的辐射源信号识别研究[J/OL].雷达学报,2018,7:1-10[2018-11-06].http://radars.ie.ac.cn/fileup/HTML/R18053.htm.
[16]周明快,黄巍,陈滨,等.基于无线信道状态相位信息优化的定位算法[J].传感技术学报,2018,31(6):957-962.
[17]张松龙,谢林柏.基于全部卷积特征融合的显著性检测[J].激光与光电子学进展,2018,55(10):232-238.
[2]蔡彬彬,包亚萍,陶卉,等.基于ZigBee协议的红外入侵检测系统的设计[J].电子技术应用,2007,33(11):97-99,103.
[3]GHOSH A,CHAKRABORTY D,PRASAD D,et al.Can we recognize multiple human group activities using ultrasonic sensors[C].2018 10th International Conference on Communication Systems&Networks(COMSNETS),Bengaluru,2018:557-560.
[4]王俊,郑彤,雷鹏,等.深度学习在雷达中的研究综述[J].雷达学报,2018,7(4):395-411.
[5]黄凯奇,陈晓棠,康运锋,等.智能视频监控技术综述[J].计算机学报,2015,20(6):1093-1118.
[6]鲁勇,吕绍和,王晓东,等.基于WiFi信号的人体行为感知技术研究综述[J/OL].计算机学报,2018,41(27):1-22.[2018-11-06].http://kns.cnki.net/kcms/detail/11.1826.TP.20180303.1407.018.html.
[7]庞娜.基于WiFi的非入侵式异常用户活动检测[J].信息安全研究,2018,4(8):711-714.
[8]周启臻,邢建春,杨启亮.基于信道状态信息相位差的人员入侵检测方法[J].传感技术学报,2018(1):103-109.
[9]DOMENICO S D,SANCTIS M D,CIANCA E,et al.WiFibased through-the-wall presence detection of stationary and moving humans analyzing the doppler spectrum[J].IEEEAerospace and Electronic Systems Magazine,2018,33(5-6):14-19.
[10]Wang Jie,Zhao Yunong,Fan Xinxin,et al.Device-free identification using intrinsic CSI features[J].IEEE Transactions on Vehicular Technology,2018,PP(99):1.
[11]MOORE R,HOWARD R,KUKSA P,et al.A geometric approach to device-free motion localization using signal strength[OL].(2010-xx-xx)[2018-11-06].https://doi.org/doi:10.7282/T3PC35T2.
[12]SOBRON I,SER J D,EIZMENDI I,et al.Device-free people counting in IoT environments:new insights,results and open challenges[J].IEEE Internet of Things Journal,2018,PP(99):1.
[13]HAN C,TAN Q,SUN L,et al.CSI frequency domain fingerprint-based passive indoor human detection[J].Information,2018,9(4):95.
[14]DOMENICO S D,PECORARO G,CIANCA E,et al.Trained-once device-free crowd counting and occupancy estimation using WiFi:a Doppler spectrum based approach[C].2016 IEEE 12th International Conference on Wireless and Mobile Computing,Networking and Communications(WiMob).IEEE,2016:1-8.
[15]苑霸,姚萍,郑天垚.基于权重归一化奇异值分解的辐射源信号识别研究[J/OL].雷达学报,2018,7:1-10[2018-11-06].http://radars.ie.ac.cn/fileup/HTML/R18053.htm.
[16]周明快,黄巍,陈滨,等.基于无线信道状态相位信息优化的定位算法[J].传感技术学报,2018,31(6):957-962.
[17]张松龙,谢林柏.基于全部卷积特征融合的显著性检测[J].激光与光电子学进展,2018,55(10):232-238.