基于Wi-Fi的烟雾实时检测方法

doi:10.11959/j.issn.1000-0801.2019150

电信科学 ›› 2019, Vol. 35 ›› Issue (6): 70-77.doi: 10.11959/j.issn.1000-0801.2019150

基于Wi-Fi的烟雾实时检测方法

吴哲夫¹,唐万利¹,陈骋²,方路平¹()

¹ 浙江工业大学信息学院，浙江杭州 310023
² 华信咨询设计研究院有限公司，浙江杭州 310052

修回日期:2019-05-20 出版日期:2019-06-20 发布日期:2019-06-20
作者简介:曹奇英（1960- ），男，博士，东华大学计算机科学与技术学院教授、博士生导师，主要研究方向为普适计算、智能信息处理。|唐万利（1995- ），女，浙江工业大学信息学院硕士生，主要研究方向为无线网络烟雾检测技术。|陈骋（1991- ），男，华信咨询设计研究院有限公司通信工程师，主要研究方向为无线传输网络研究和规划设计。|方路平（1968- ），男，浙江工业大学信息学院教授、硕士生导师，CCF会员，主要研究方向为计算机网络、深度学习等。
基金资助:
浙江省自然科学基金资助项目(LY18F010025);浙江省自然科学基金资助项目(LY14F050004);浙江省自然科学基金资助项目(LY13F010011)

Real-time detection method of smoke based on Wi-Fi

WU Zhefu¹,TANG Wanli¹,CHEN Cheng²,FANG Luping¹()

¹ College of Information Engineering,Zhejiang University of Technology,Hangzhou 310023,China
² China Comservice Huaxin Consulting Co.,Ltd.,Hangzhou 310052,China

Revised:2019-05-20 Online:2019-06-20 Published:2019-06-20
Supported by:
The Natural Science Foundation of Zhejiang Provincial of China(LY18F010025);The Natural Science Foundation of Zhejiang Provincial of China(LY14F050004);The Natural Science Foundation of Zhejiang Provincial of China(LY13F010011)

摘要/Abstract

摘要：

与火灾相关的烟雾实时检测方法是保障公共安全的重要手段之一。针对现有火灾传感器系统的高成本和视频探测的拍摄盲区等问题，提出了一种基于 Wi-Fi 网络信道状态信息的火灾烟雾检测方法。该方法无需专用的火灾烟雾监测设备，通过研究火灾烟雾对无线传输信号的影响，提取信道状态信息中的烟雾特征参数并应用机器学习进行分类，从而实现环境火灾实时监测的目的。实验结果表明，基于 Wi-Fi 信道状态信息的环境烟雾检测准确率可达98.06%。

关键词: 无线信道, 信道状态信息, 烟雾检测, 机器学习

Abstract:

Fire-related smoke real-time detection method is one of the important means to ensure public safety.A fire smoke detection method based on channel state information of Wi-Fi network was proposed to avoid the high cost of existing fire sensor system or the blind spot of video detection.The method need not require a dedicated fire smoke monitoring device.By studying the influence of fire smoke on wireless transmission signals,the smoke characteristic parameters in the channel state information were extracted and classified by machine learning,thereby realizing the real-time monitoring of environmental fire.The experimental results show that the accuracy of environmental smoke detection based on Wi-Fi channel status information can reach 98.06%.

Key words: wireless channel, channel state information, smoke detection, machine learning

中图分类号:

TN929

吴哲夫,唐万利,陈骋,方路平. 基于Wi-Fi的烟雾实时检测方法[J]. 电信科学, 2019, 35(6): 70-77.

WU Zhefu,TANG Wanli,CHEN Cheng,FANG Luping. Real-time detection method of smoke based on Wi-Fi[J]. Telecommunications Science, 2019, 35(6): 70-77.

图/表 12

图1

图2

图3

表1

图4

图5

图6

图7

图8

图9

图10

表2

参考文献 15

[1]	袁飞阁 . 基于烟雾浓度的火灾视频检测方法[D]. 武汉:华中科技大学, 2013.
	YUAN F G . Smoke detection method based on smoke density with video[D]. Wuhan:Huazhong University of Science and Technology, 2017.
[2]	相徐斌 . 基于视频的烟雾检测算法研究[D]. 杭州:浙江大学, 2017.
	XIANG X B . The research of smoke detection algorithm on video[D]. Hangzhou:Zhejiang University, 2017.
[3]	程文彬, 杜磊, 刘依依 . 无线多传感器数据融合的家庭火灾检测系统设计[J]. 电信科学, 2017,33(9): 174-181.
	CHENG W B , DU L , LIU Y Y . Design of home fire detection system based on wireless multi-sensor data fusion[J]. Telecommunications Science, 2017,33(9): 174-181.
[4]	KAABI R , FRIZZI S , BOUCHOUICHA M ,et al. Video smoke detection review:state of the art of smoke detection in visible and IR range[C]// International Conference on Smart,Monitored and Controlled Cities,Feb 17-19,2017,Kerkennah Islands,Tunisia. Piscataway:IEEE Press, 2017: 81-86.
[5]	BORGES P V , IZQUIERDO E . A probabilistic approach for vision-based fire detection in videos[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2010,20(5): 721-731.
[6]	FOGGIA P , SAGGESE A , VENTO M ,et al. Real-time fire detection for video-surveillance applications using a combination of experts based on color,shape,and motion[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2015,25(9): 1545-1556.
[7]	WANG Y , WU K , NI L M ,et al. WiFall:device-free fall detection by wireless networks[J]. IEEE Transactions on Mobile Computing, 2017,16(2): 581-594.
[8]	WANG H , ZHANG D , WANG Y ,et al. RT-fall:a real-time and contactless fall detection system with commodity Wi-Fi devices[J]. IEEE Transactions on Mobile Computing, 2017,16(2): 511-526.
[9]	ALI K , LIU A X , WANG W ,et al. Recognizing keystrokes using Wi-Fi devices[J]. IEEE Journal on Selected Areas in Communications, 2017,35(5): 1175-1190.
[10]	WANG X , YANG C , MAO S ,et al. Phasebeat:exploiting CSI phase data for vital sign monitoring with commodity Wi-Fidevices[C]// The 37th IEEE International Conference on Distributed Computing Systems,June 5-8,2017,Atlanta,GA,USA. Piscataway:IEEE Press, 2017: 1230-1239.
[11]	LEE S , PARK Y D , SUH Y ,et al. Design and implementation of monitoring system for breathing and heart rate pattern using Wi-Fi signals[C]// 15th IEEE Annual Consumer Communications ＆ Networking Conference,Jan 12-15,2018,Sfax,Tunisia. Piscataway:IEEE Press, 2018: 1-7.
[12]	WU K , XIAO J , YI Y ,et al. CSI-based indoor localization[J]. IEEE Transactions on Parallel and Distributed Systems, 2013,24(7): 1300-1309.
[13]	孙君, 谢利娟, 许晖 ,等. 15 GHz 频段下会议室内信道大尺度衰落特性测量与分析[J]. 电信科学, 2016,32(2): 13-19.
	SUN J , XIE L J , XU H ,et al. Measurement and analysis on channel large scale fading characteristics of conference room at 15 GHz[J]. Telecommunications Science, 2016,32(2): 13-19.
[14]	韩玲, 张永明, 方俊 ,等. 室内火灾烟雾对微波衰减的影响研究[J]. 火灾科学, 2016,25(1): 47-52.
	HAN L , ZHANG Y M , FANG J ,et al. Effect of indoor fire smokes on microwave attenuation[J]. Fire Safety Science, 2016,25(1): 47-52.
[15]	HALPERIN D , HU W J , SHETH A ,et al. Tool release:gathering 802.11n traces with channel state information[J]. ACM SIGCOMM Computer Communication Review, 2011,41(1):53.

场景名称	面积	天线间距
视距环境1	2 m× 2 m	1.8 m
视距环境2	6 m× 6 m	0.5～3.5 m
视距环境3	8 m× 8 m	3m
非视距环境1	5 m× 2 m	1m
非视距环境2	8 m× 2 m	6m

分类器	KNN	NB	SVM	BP
分类精度	83.1%	84.46%	89.43%	93.51%
时间/s	0.29	0.20	1.5	72.40

基于Wi-Fi的烟雾实时检测方法

Real-time detection method of smoke based on Wi-Fi

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 12

参考文献 15

相关文章 15

Metrics

推荐阅读 0

[1]	郭泽华, 朱昊文, 徐同文. 面向分布式机器学习的网络模态创新[J]. 电信科学, 2023, 39(6): 44-51.
[2]	沈静洁, 李光球, 罗延翠, 刘会芝. 过时CSI下全双工中继辅助D2D网络的物理层安全[J]. 电信科学, 2023, 39(3): 89-99.
[3]	刘雅琼, 吕哲, 赵亚飞, 寿国础. AI技术在卫星通信/互联网领域的应用综述[J]. 电信科学, 2023, 39(2): 10-24.
[4]	章坚武, 安彦军, 邓黄燕. DNS攻击检测与安全防护研究综述[J]. 电信科学, 2022, 38(9): 1-17.
[5]	黄秋萍, 刘晓峰, 高秋彬, 刘正宣, 金立强, 孙韶辉. 基于人工智能的大规模天线信道状态信息反馈研究[J]. 电信科学, 2022, 38(3): 74-83.
[6]	李艳丽, 林志, 王子宁, 许拔, 程铭, 欧阳键. 基于无人机中继的星地认知网络波束成形算法[J]. 电信科学, 2021, 37(8): 27-37.
[7]	周志超, 冯毅, 夏小涵, 冯瑜瑶, 蔡超, 邱佳慧, 杨立辉, 乌云霄. 基于移动蜂窝网的机器学习室外指纹定位方案[J]. 电信科学, 2021, 37(8): 85-95.
[8]	卢艳萍, 刘留, 付丽琴, 邱佳慧, 刘凯. 大规模MIMO信道测量与建模综述[J]. 电信科学, 2021, 37(4): 14-27.
[9]	李想,李原,张子飞,杨哲. 基于密度聚类的网络性能故障大数据分析方法[J]. 电信科学, 2020, 36(9): 51-58.
[10]	肖子玉. 面向2030的未来网络关键技术综述——Beyond 5G[J]. 电信科学, 2020, 36(9): 114-121.
[11]	邱亚星,王希栋,边森,岳磊. 基于聚类分析和深度学习的多频多模网络负载均衡优化[J]. 电信科学, 2020, 36(7): 156-162.
[12]	欧阳晔,杨爱东,孟凡语. 一种博弈论辅助的机器学习算法检测用户流失行为[J]. 电信科学, 2020, 36(6): 79-89.
[13]	林锋,徐柳婧,陈晓华,戚伟强,陈可,朱添田. 一种基于多视角特征融合的Webshell检测方法[J]. 电信科学, 2020, 36(6): 125-132.
[14]	盛剑涛,陈茂飞,刘东鑫,汪来富,史国水,金华敏. 基于组合分类器的恶意域名检测技术[J]. 电信科学, 2020, 36(5): 47-55.
[15]	庞涛,丘海华,潘碧莹. 手机终端人工智能关键技术研究[J]. 电信科学, 2020, 36(5): 145-151.