Wi-Pest：一种基于CSI的储粮害虫检测方法

doi:10.11959/j.issn.2096-3750.2020.00186

物联网学报 ›› 2020, Vol. 4 ›› Issue (4): 51-61.doi: 10.11959/j.issn.2096-3750.2020.00186

Wi-Pest：一种基于CSI的储粮害虫检测方法

单少伟^1,²,杨卫东^1,²(),肖乐^1,²,王珂^1,²

¹ 河南工业大学信息科学与工程学院，河南郑州 450066
² 粮食信息处理与控制教育部重点实验室（河南工业大学），河南郑州 450066

修回日期:2020-03-03 出版日期:2020-12-30 发布日期:2020-12-14
作者简介:单少伟（1992- ），男，河南郑州人，河南工业大学硕士生，主要研究方向为无线网络、物联网等|杨卫东（1977- ），男，河南郑州人，博士，河南工业大学教授，主要研究方向为无线网络安全、隐私保护、车载自组织网络、物联网、车联网等|肖乐（1972- ），男，河南开封人，河南工业大学副教授，主要研究方向为人工智能、智能计算等|王珂（1980- ），男，河南郑州人，河南工业大学讲师，主要研究方向为大数据、物联网
基金资助:
国家重点研发计划(2017YFD0401001);国家自然科学基金资助项目(61741107);河南省省属高校基本科研业务费专项资金资助项目(2018RCJH12);河南工业大学科研平台开放课题(KFJJ-2016-202)

Wi-Pest:a method for detecting stored grain pests based on CSI

Shaowei SHAN^1,²,Weidong YANG^1,²(),Le XIAO^1,²,Ke WANG^1,²

¹ College of Information Science and Engineering,Henan University of Technology,Zhengzhou 450066,China
² Key Laboratory of Grain Information Processing and Control (Henan University of Technology),Ministry of Education,Zhengzhou 450066,China

Revised:2020-03-03 Online:2020-12-30 Published:2020-12-14
Supported by:
The National Key R＆D Program of China(2017YFD0401001);The National Natural Science Foundation of China(61741107);The Fundamental Research Funds for the Henan Provincial Colleges and Universities(2018RCJH12);The Open Fund for Henan University of Technology(KFJJ-2016-202)

摘要/Abstract

摘要：

在粮食储藏过程中，影响粮食安全的环境和生物因素，如粮食温度、环境湿度、水分、气体、霉变、害虫等，均会对粮食储藏安全构成威胁，其中害虫是威胁粮食储藏安全的一个重要因素。因此，需要研究一种快速且有效的检测方法，用于检测储粮害虫。现有的一些方法耗时、设备昂贵、具有潜在的健康危害并且检测效率较低，提出了一种基于信道状态信息（CSI,channel state information）振幅的非接触、快速、低成本的储粮害虫检测方法，即无线测害虫（Wi-Pest,wireless-pest）。通过使用CSI振幅数据验证储粮害虫检测的可行性，在此基础上，设计了Wi-Pest检测方法。首先对CSI振幅数据进行异常值检测、数据归一化和噪声消除预处理，然后通过主成分分析（PCA,principal component analysis）方法压缩数据并提取主特征成分，最后采用随机森林（RF,random forest）分类方法检测储粮害虫。实验结果表明，所提方法在视距（LOS,line of sight）场景下，能够检测粮堆活体害虫密度的异常情况，检测精度平均可以达到97%。

关键词: CSI, 储粮害虫检测, 振幅, 随机森林分类

Abstract:

The environmental and biological factors that affect the food security during the food storage,such as the food temperature,environment humidity,moisture,gas,mildew,pests and others pose a threat to the food storage security,among which the pest is an important factor threatening food storage security.Therefore,a fast and effective detection method is needed to detect stored grain pests.Some of the existing methods are time consuming,using expensive equipment,potentially harmful to health and inefficient.A non-contact,fast and low-cost detection method for stored grain pests based on the amplitude of the channel state information (CSI) was proposed,namely,wireless-pest (Wi-Pest).The feasibility of the pest detection in the stored grain was verified by using CSI amplitude data.On this basis,a Wi-Pest detection method was designed.Firstly,the amplitude data of CSI was preprocessed by outliers removal,data normalization and noise elimination.Then the principal component analysis (PCA) was used to compress the data and extract the main feature components.Finally,random forest (RF) classification method was used to detect stored grain pests.Experiments show that the abnormal density of live pests in grain heaps can be detected under the line of sight (LOS) scenario,and the detection accuracy of the proposed method can reach 97% on average.

Key words: CSI, stored grain pest detection, amplitude, random forest classification

中图分类号:

TN92

单少伟,杨卫东,肖乐,王珂. Wi-Pest：一种基于CSI的储粮害虫检测方法[J]. 物联网学报, 2020, 4(4): 51-61.

Shaowei SHAN,Weidong YANG,Le XIAO,Ke WANG. Wi-Pest:a method for detecting stored grain pests based on CSI[J]. Chinese Journal on Internet of Things, 2020, 4(4): 51-61.

图/表 13

图1

图2

图3

图4

表1

表2

图5

图6

图7

图8

图9

表3

图10

参考文献 35

[1]	Food and Agriculture Organization of United Nations. Save food:global initiative on food loss and waste reduction[EB/OL]. .
[2]	PARFITT J , BARTHEL M , MACNAUGHTON S . Food waste within food supply chains:quantification and potential for change to 2050[J]. Philosophical Transactions of the Royal Society B:Biological Sciences, 2010,365(1554): 3065-3081.
[3]	VASISHT D , KAPETANOVIC Z , WON J ,et al. FarmBeats:an IoT platform for data-driven agriculture[C]// The 14th USENIX Symposium on Networked Systems Design and Implementation. 2017: 515-529.
[4]	JAYAS D S . Storing grains for food security and sustainability[J]. Agricultural Research, 2012,1(1): 21-24.
[5]	ASRAR M , ASHRAF N , HUSSAIN S M ,et al. Toxicity and repellence of plant oils against Tribolium castaneum (Herbst),Rhyzopertha dominica (F.) and Trogoderma granarium (E.)[J]. Pakistan Entomologist, 2016,38(1): 55-63.
[6]	张红涛, 胡玉霞, 邱道尹 . 储粮害虫检测现状[J]. 河南农业科学, 2006(3): 66-68.
	ZHANG H T , HU Y X , QIU D Y . Current situation of stored grain pest detection[J]. Journal of Henan Agricultural, 2006(3): 66-68.
[7]	杨自力, 蒋天科, 李伟 ,等. 探管诱集与取样筛检两种方法检测储粮害虫数量比较[J]. 粮食储藏, 2007,36(3): 16-19.
	YANG Z L , JIANG T K , LI W ,et al. Comparison of probe-tube traps and sampling inspection to detect stored grain pests[J]. Grain Storage, 2007,36(3): 16-19.
[8]	秦昕, 郭敏 . 2 种储粮害虫活动声信号的检测及其功率谱分析[J]. 华中农业大学学报, 2012,31(5): 656-660.
	QIN X , GUO M . Detection of activity sound from two species stored grain insects and analysis of its power spectrum[J]. Journal of Huazhong Agricultural University, 2012,31(5): 656-660.
[9]	LIU T , CHEN W , WU W ,et al. Detection of aphids in wheat fields using a computer vision technique[J]. Biosystems Engineering, 2016,141: 82-93.
[10]	赵彬宇, 周慧玲, 李江涛 ,等. 储粮害虫智能图鉴及图像识别 App软件设计[J]. 粮食储藏, 2019,48(3): 42-46.
	ZHAO B Y , ZHOU H L , LI J T ,et al. Mobile App design for stored grain insect illustration guide and image recognition[J]. Grain Storage, 2019,48(3): 42-46.
[11]	ELIZABETH B M , DOWELL F E , BAKER J E ,et al. Detecting single wheat kernels containing live or dead insects using near infrared reflectance spectroscopy[C]// American Society of Agricultural and Biological Engineers Annual Meeting. 2002.
[12]	邵小龙, 徐水红, 徐文 . 基于软X射线与低场核磁检测小麦隐蔽性害虫玉米象[J]. 中国粮油学报, 2019,34(7): 101-106.
	SHAO X L , XU S H , XU W . Detection of wheat hidden pest Sitophilus zeamais based on soft X-ray and low field nuclear magnetic resonance[J]. Journal of the Chinese Cereals and Oils Association, 2019,34(7): 101-106.
[13]	MANKIN R W . Microwave radar detection of stored-product insects[J]. Journal of Economic Entomology, 2004,97(3): 1168-1173.
[14]	PEARSON T C , BRABEC D L . Automated detection of hidden internal insect infestations in wheat kernels using electrical conductance[C]// American Society of Agricultural and Biological Engineers Annual Meeting. 2002.
[15]	XIAO J , WU K , YI Y ,et al. FIFS:fine-grained indoor fingerprinting system[C]// International Conference on Computer Communication Networks. IEEE, 2012: 1-7.
[16]	WANG X Y , GAO L J , MAO S W ,et al. CSI-based fingerprinting for indoor localization:a deep learning approach[J]. IEEE Transactions on Vehicular Technology, 2017,66(1): 763-776.
[17]	WANG X Y , GAO L J , MAO S W . CSI phase fingerprinting for indoor localization with a deep learning approach[J]. IEEE Internet of Things Journal, 2016,3(6): 1113-1123.
[18]	WANG X Y , GAO L J , MAO S W . BiLoc:Bi-modal deep learning for indoor localization with commodity 5 GHz Wi-Fi[J]. IEEE Access, 2017,5: 4209-4220.
[19]	WANG X Y , WANG X Y , MAO S W . CiFi:Deep convolutional neural networks for indoor localization with 5 GHz Wi-Fi[C]// 2017 IEEE International Conference on Communications (ICC). IEEE, 2017: 1-6.
[20]	党小超, 司雄, 郝占军 ,等. 复杂室内环境下基于 CSI 的定位方法[J]. 物联网学报, 2018,2(4): 68-77.
	DANG X C , SI X , HAO Z J ,et al. Indoor localization method based on CSI in complex environment[J]. Chinese Journal on Internet of Things, 2018,2(4): 68-77.
[21]	WANG Y , LIU J , CHEN Y Y ,et al. E-eyes:Device-free location-oriented activity identification using fine-grained Wi-Fi signatures[C]// The 20th Annual International Conference on Mobile Computing and Networking. ACM, 2014: 617-628.
[22]	WANG G H , ZOU Y P , ZHOU Z M ,et al. We can hear you with Wi-Fi![J]. IEEE Transactions on Mobile Computing, 2016,15(11): 2907-2920.
[23]	WANG W , LIU A X , SHAHZAD M ,et al. Understanding and modeling of WiFi signal based human activity recognition[C]// The 21st Annual International Conference on Mobile Computing and Networking. 2015: 65-76.
[24]	WANG Y X , WU K S , NI L M . WiFall:device-free fall detection by wireless networks[J]. IEEE Transactions on Mobile Computing, 2017,16(2): 581-594.
[25]	WANG H , ZHANG D Q , WANG Y S ,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.
[26]	WANG X Y , YANG C , MAO S W . PhaseBeat:exploiting CSI phase data for vital sign monitoring with commodity Wi-Fi devices[C]// 2017 IEEE 37th International Conference on Distributed Computing Systems (ICDCS). IEEE, 2017: 1230-1239.
[27]	WANG X Y , YANG C , MAO S W . TensorBeat:tensor decomposition for monitoring multi-person breathing beats with commodity Wi-Fi[J]. ACM Transactions on Intelligent Systems and Technology, 2017,9(1): 1-27.
[28]	ZHONG S X , HUANG Y Z , RUBY R ,et al. Wi-fire:Device-free fire detection using Wi-Fi networks[C]// 2017 IEEE International Conference on Communications (ICC). IEEE, 2017: 1-6.
[29]	WU K S , . Wi-metal:Detecting metal by using wireless networks[C]// 2016 IEEE International Conference on Communications (ICC). IEEE, 2016: 1-6.
[30]	WANG Z , HAN J S , XI W ,et al. Efficient and secure key extraction using channel state information[J]. The Journal of Supercomputing, 2014,70(3): 1537-1554.
[31]	郭峰 . 浅谈无线通信系统中的传输技术[J]. 通讯世界, 2019,26(10): 91-92.
	GUO F . Talk about the transmission technology in wireless communication system[J]. Telecom World, 2019,26(10): 91-92.
[32]	GONG M X , HART B , MAO S W . Advanced wireless LAN technologies[J]. GetMobile:Mobile Computing and Communications, 2015,18(4): 48-52.
[33]	WANG X Y , MAO S W , GONG M X . A survey of LTE Wi-Fi coexistence in unlicensed bands[J]. GetMobile:Mobile Computing and Communications, 2017,20(3): 17-23.
[34]	王奕森, 夏树涛 . 集成学习之RF算法综述[J]. 信息通信技术, 2018,12(1): 49-55.
	WANG Y S , XIA S T . A survey of random forests algorithms[J]. Information and Communications Technologies, 2018,12(1): 49-55.
[35]	SUYKENS J , LUKAS L , VAN P ,et al. Least squares support vector machine classifiers:a large scale algorithm[J]. Neural Processing Letters, 1999,9(3): 293-300.

对比类型	小麦虫口密度/(头·kg^-1)	实验内容
无虫与大量活虫	0与40	向装满小麦的塑料瓶子放入约140头玉米象活体害虫，并将其埋入实验有机玻璃盒子，然后把未放入害虫的塑料瓶子埋入实验有机玻璃盒子，分别收集CSI数据
无虫与大量死虫	0与40	向装满小麦的塑料瓶子放入约140头玉米象死虫，并将其埋入实验有机玻璃盒子，然后把未放入害虫的塑料瓶子埋入实验有机玻璃盒子，分别收集CSI数据

对比类型	小麦虫口密度/(头·kg^-1)	实验内容
无虫粮与基本无虫粮	0与4	实验用有机玻璃盒子可以盛放约3.5 kg小麦，按照0、4头/kg、20头/kg、40头/kg配置小麦
无虫粮与一般虫粮无虫粮与严重虫粮	0与200与40	样本，共配置了0、14头/盒、70头/盒、140头/盒共计4种不同虫口密度比例的小麦样本，然后分别收集这4种小麦样本LOS场景下的CSI数据

不同虫粮对比	SVM分类精度	RF分类精度
无虫粮与基本无虫粮	96.7%	98.2%
无虫粮与一般虫粮	97.2%	98.5%
无虫粮与严重虫粮	96.8%	98.9%

Wi-Pest：一种基于CSI的储粮害虫检测方法

Wi-Pest:a method for detecting stored grain pests based on CSI

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 13

参考文献 35

相关文章 4

Metrics

推荐阅读 0

[1]	曾钰婷, 毕宿志, 郑莉莉, 林晓辉, 王晖. 基于CSI小样本学习的场景鲁棒性跌倒检测系统[J]. 物联网学报, 2023, 7(2): 118-132.
[2]	马柱华, 罗丽平. 非理想顺序干扰消除和信道状态信息下SWIPT-NOMA-CR网络中断性能[J]. 物联网学报, 2023, 7(1): 129-139.
[3]	陈慕涵,郭佳佳,李潇,金石. 基于深度学习的大规模MIMO信道状态信息反馈[J]. 物联网学报, 2020, 4(1): 33-44.
[4]	廖勇,姚海梅,花远肖. 一种基于深度学习的物联网信道状态信息获取算法[J]. 物联网学报, 2019, 3(1): 8-13.