基于茎干含水率的紫薇病虫害等级早期诊断方法
|
摘要
为了对植物病虫害进行早期预警,提出一种基于茎干含水率的植物病虫害等级早期诊断方法。以紫薇为研究对象,监测复苏萌芽期内不同健康等级紫薇的茎干含水率;然后,分别通过关键参数和主成分分析对茎干含水率进行特征提取;最后,结合有监督和无监督学习模型实现对紫薇病虫害等级的早期诊断。基于方差分析,紫薇健康等级对日最小含水率、日最大含水率、日平均含水率、日极差含水率4个关键参数的影响均为极显著。基于主成分分析,茎干含水率时间序列前4个主成分的累计贡献率达到99. 7%。在有监督模型中,以主成分特征为输入的BP模型的性能最优,平均识别率达到98%;在无监督模型中,以主成分特征为输入的K均值模型最优,平均识别率达到92%。因此,茎干含水率可以作为诊断植物病虫害等级的早期指标,主成分特征优于关键参数特征,有监督模型优于无监督模型。
A new method was proposed for early diagnosis of disease and pest level based on stem water content,which provided early warning for diseases and pests. Lagerstroemia indica seedlings with different health levels were monitored for acquiring stem water content. Then the features of stem water content were respectively extracted by two methods,including key parameter and principle component analysis. Ultimately,some supervised and unsupervised models were established for early diagnosis of disease and pest level on Lagerstroemia indica. Judging from variance analysis,the effects of health level on four key parameters(daily minimum,maximum,average and range of stem water contents) were all in very significant difference. Judging from principle component analysis,the cumulative contribution rate of the first four principal components of stem water content reached 99. 7%. Among supervised models,BP model with input of PCA features performed the best and its average recognition reached 98%. Among unsupervised models,K-means model with input of PCA features performed the best and its average recognition rate reached 92%. Hence,stem water content can be chosen as a reliable index for early diagnosis of plant disease and pest level. The PCA features were superior to the key parameter features.The performance of supervised models was better than that of unsupervised models.
A new method was proposed for early diagnosis of disease and pest level based on stem water content,which provided early warning for diseases and pests. Lagerstroemia indica seedlings with different health levels were monitored for acquiring stem water content. Then the features of stem water content were respectively extracted by two methods,including key parameter and principle component analysis. Ultimately,some supervised and unsupervised models were established for early diagnosis of disease and pest level on Lagerstroemia indica. Judging from variance analysis,the effects of health level on four key parameters(daily minimum,maximum,average and range of stem water contents) were all in very significant difference. Judging from principle component analysis,the cumulative contribution rate of the first four principal components of stem water content reached 99. 7%. Among supervised models,BP model with input of PCA features performed the best and its average recognition reached 98%. Among unsupervised models,K-means model with input of PCA features performed the best and its average recognition rate reached 92%. Hence,stem water content can be chosen as a reliable index for early diagnosis of plant disease and pest level. The PCA features were superior to the key parameter features.The performance of supervised models was better than that of unsupervised models.
引文
1 CUBERO S,LEE W S,ALEIXOS N,et al.Automated systems based on machine vision for inspecting citrus fruits from the field to postharvest-a review[J].Food and Bioprocess Technology,2016,9(10):1623-1639.
2 SANKARAN S,MISHRA A,EHSANI R,et al.A review of advanced techniques for detecting plant diseases[J].Computers and Electronics in Agriculture,2010,72(1):1-13.
3 MARTINELLI F,SCALENGHE R,DAVINO S,et al.Advanced methods of plant disease detection:a review[J].Agronomy for Sustainable Development,2015,35(1):1-25.
4 BOISSARD P,MARTIN V,MOISAN S.A cognitive vision approach to early pest detection in greenhouse crops[J].Computers and Electronics in Agriculture,2008,62(2):81-93.
5 PYDIPATI R,BURKS T F,LEE W S.Statistical and neural network classifiers for citrus disease detection using machine vision[J].Transactions of the ASAE,2005,48(5):2007-2014.
6 EBRAHIMI M A,KHOSHTAGHAZA M H,MINAEI S,et al.Vision-based pest detection based on SVM classification method[J].Computers and Electronics in Agriculture,2017,137:52-58.
7 MOHANTY S P,HUGHES D P,SALATHM.Using deep learning for image-based plant disease detection[J].Frontiers in Plant Science,2016,7:1419.
8游崇娟,王建美,田呈明.植物病害检测领域的电生理学研究进展[J].西北林学院学报,2010,25(1):118-122,153.YOU Chongjuan,WANG Jianmei,TIAN Chengming.Research progress of electrophysiology in plant disease detection[J].Journal of Northwest Forestry University,2010,25(1):118-122,153.(in Chinese)
9 MOSHOU D,BRAVO C,OBERTI R,et al.Plant disease detection based on data fusion of hyper-spectral and multi-spectral fluorescence imaging using Kohonen maps[J].Real-Time Imaging,2005,11(2):75-83.
10 ELLIS M A,FERREE D C,SPRING D E.Photosynthesis,transpiration,and carbohydrate content of apple leaves infected by Podosphaera leucotricha[J].Phytopathology,1981,71(4):392-395.
11 MOALEMIYAN M,VIKRAM A,KUSHALAPPA A C,et al.Volatile metabolite profiling to detect and discriminate stem-end rot and anthracnose diseases of mango fruits[J].Plant Pathology,2006,55(6):792-802.
12 MINSAVAGE G V,THOMPSON C M,HOPKINS D L,et al.Development of a polymerase chain reaction protocol for detection of Xylella fastidiosa in plant tissue[J].Phytopathology,1994,84(5):456-461.
13 SAPONARI M,MANJUNATH K,YOKOMI R K.Quantitative detection of citrus tristeza virus in citrus and aphids by real-time reverse transcription-PCR(Taq Man)[J].Journal of Virological Methods,2008,147(1):43-53.
14 GUTIRREZ-AGUIRRE I,MEHLE N,DELI'C D,et al.Real-time quantitative PCR based sensitive detection and genotype discrimination of Pepino mosaic virus[J].Journal of Virological Methods,2009,162(1-2):46-55.
15 SELMAN I W.Virus infection and water loss in tomato foliage[J].Journal of Pomology and Horticultural Science,1945,21(1):146-154.
16 SPOTTS R A,FERREE D C.Photosynthesis,transpiration and water potential of apple leaves infected by Venturia inaequalis[J].Phytopathology,1979,69:717-719.(下转第页)
17 CLOVER G R G,JAGGARD K W,SMITH H G,et al.The use of radiation interception and transpiration to predict the yield of healthy,droughted and virus-infected sugar beet[J].The Journal of Agricultural Science,2001,136(2):169-178.
18 ZHOU H,SUN Y,TYREE M T,et al.An improved sensor for precision detection of in situ stem water content using a frequency domain fringing capacitor[J].New Phytologist,2015,206(1):471-481.
19周海洋,孙宇瑞,SCHULZE L P,等.基于内边缘场电容效应的树干/枝水分传感器研究[J/OL].农业机械学报,2016,47(1):317-323.http:∥www.j-csam.org/jcsam/ch/reader/view_abstract.aspx?file_no=20160143&flag=1.DOI:10.6041/j.issn.1000-1298.2016.01.043.ZHOU Haiyang,SUN Yurui,SCHULZE L P,et al.Inner fringing-filed capacitance sensor for measurement of stem water content[J/OL].Transactions of the Chinese Society for Agricultural Machinery,2016,47(1):317-323.(in Chinese)
20赵燕东,高超,张新,等.基于驻波率原理的植物茎体水分无损检测方法研究[J/OL].农业机械学报,2016,47(1):310-316.http:∥www.j-csam.org/jcsam/ch/reader/view_abstract.aspx?file_no=20160142&flag=1.DOI:10.6041/j.issn.1000-1298.2016.01.042.ZHAO Yandong,GAO Chao,ZHANG Xin,et al.Non-destructive measurement of plant stem water content based on standing wave ratio[J/OL].Transactions of the Chinese Society for Agricultural Machinery,2016,47(1):310-316.(in Chinese)
21严太淑.紫薇虫害紫薇绒蚧形态特征及防治对策探讨[J].农业灾害研究,2017,7(3):44-45.YAN Taishu.Discussion on morphological features and countermeasures of Eriococcus lagerostroemiae Kuwana on Lagerstroemia indica[J].Journal of Agricultural Catastrophology,2017,7(3):44-45.(in Chinese)
22 SOPHIAN A,TIAN G Y,TAYLOR D,et al.A feature extraction technique based on principal component analysis for pulsed eddy current NDT[J].NDT&E International,2003,36(1):37-41.
23 SAEYS Y,INZA I,LARRAAGA P.A review of feature selection techniques in bioinformatics[J].Bioinformatics,2007,23(19):2507-2517.
24 BALLABIO D.A MATLAB toolbox for principal component analysis and unsupervised exploration of data structure[J].Chemometrics and Intelligent Laboratory Systems,2015,149(12):1-9.
25 ABDI H,WILLIAMS L J.Principal component analysis[J].Wiley Interdisciplinary Reviews:Computational Statistics,2010,2(4):433-459.
26 BRO R,SMILDE A K.Principal component analysis[J].Analytical Methods,2014,6(9):2812-2831.
27 MATHUR A,FOODY G M.Multiclass and binary SVM classification:implications for training and classification users[J].IEEEGeoscience and Remote Sensing Letters,2008,5(2):241-245.
2 SANKARAN S,MISHRA A,EHSANI R,et al.A review of advanced techniques for detecting plant diseases[J].Computers and Electronics in Agriculture,2010,72(1):1-13.
3 MARTINELLI F,SCALENGHE R,DAVINO S,et al.Advanced methods of plant disease detection:a review[J].Agronomy for Sustainable Development,2015,35(1):1-25.
4 BOISSARD P,MARTIN V,MOISAN S.A cognitive vision approach to early pest detection in greenhouse crops[J].Computers and Electronics in Agriculture,2008,62(2):81-93.
5 PYDIPATI R,BURKS T F,LEE W S.Statistical and neural network classifiers for citrus disease detection using machine vision[J].Transactions of the ASAE,2005,48(5):2007-2014.
6 EBRAHIMI M A,KHOSHTAGHAZA M H,MINAEI S,et al.Vision-based pest detection based on SVM classification method[J].Computers and Electronics in Agriculture,2017,137:52-58.
7 MOHANTY S P,HUGHES D P,SALATHM.Using deep learning for image-based plant disease detection[J].Frontiers in Plant Science,2016,7:1419.
8游崇娟,王建美,田呈明.植物病害检测领域的电生理学研究进展[J].西北林学院学报,2010,25(1):118-122,153.YOU Chongjuan,WANG Jianmei,TIAN Chengming.Research progress of electrophysiology in plant disease detection[J].Journal of Northwest Forestry University,2010,25(1):118-122,153.(in Chinese)
9 MOSHOU D,BRAVO C,OBERTI R,et al.Plant disease detection based on data fusion of hyper-spectral and multi-spectral fluorescence imaging using Kohonen maps[J].Real-Time Imaging,2005,11(2):75-83.
10 ELLIS M A,FERREE D C,SPRING D E.Photosynthesis,transpiration,and carbohydrate content of apple leaves infected by Podosphaera leucotricha[J].Phytopathology,1981,71(4):392-395.
11 MOALEMIYAN M,VIKRAM A,KUSHALAPPA A C,et al.Volatile metabolite profiling to detect and discriminate stem-end rot and anthracnose diseases of mango fruits[J].Plant Pathology,2006,55(6):792-802.
12 MINSAVAGE G V,THOMPSON C M,HOPKINS D L,et al.Development of a polymerase chain reaction protocol for detection of Xylella fastidiosa in plant tissue[J].Phytopathology,1994,84(5):456-461.
13 SAPONARI M,MANJUNATH K,YOKOMI R K.Quantitative detection of citrus tristeza virus in citrus and aphids by real-time reverse transcription-PCR(Taq Man)[J].Journal of Virological Methods,2008,147(1):43-53.
14 GUTIRREZ-AGUIRRE I,MEHLE N,DELI'C D,et al.Real-time quantitative PCR based sensitive detection and genotype discrimination of Pepino mosaic virus[J].Journal of Virological Methods,2009,162(1-2):46-55.
15 SELMAN I W.Virus infection and water loss in tomato foliage[J].Journal of Pomology and Horticultural Science,1945,21(1):146-154.
16 SPOTTS R A,FERREE D C.Photosynthesis,transpiration and water potential of apple leaves infected by Venturia inaequalis[J].Phytopathology,1979,69:717-719.(下转第页)
17 CLOVER G R G,JAGGARD K W,SMITH H G,et al.The use of radiation interception and transpiration to predict the yield of healthy,droughted and virus-infected sugar beet[J].The Journal of Agricultural Science,2001,136(2):169-178.
18 ZHOU H,SUN Y,TYREE M T,et al.An improved sensor for precision detection of in situ stem water content using a frequency domain fringing capacitor[J].New Phytologist,2015,206(1):471-481.
19周海洋,孙宇瑞,SCHULZE L P,等.基于内边缘场电容效应的树干/枝水分传感器研究[J/OL].农业机械学报,2016,47(1):317-323.http:∥www.j-csam.org/jcsam/ch/reader/view_abstract.aspx?file_no=20160143&flag=1.DOI:10.6041/j.issn.1000-1298.2016.01.043.ZHOU Haiyang,SUN Yurui,SCHULZE L P,et al.Inner fringing-filed capacitance sensor for measurement of stem water content[J/OL].Transactions of the Chinese Society for Agricultural Machinery,2016,47(1):317-323.(in Chinese)
20赵燕东,高超,张新,等.基于驻波率原理的植物茎体水分无损检测方法研究[J/OL].农业机械学报,2016,47(1):310-316.http:∥www.j-csam.org/jcsam/ch/reader/view_abstract.aspx?file_no=20160142&flag=1.DOI:10.6041/j.issn.1000-1298.2016.01.042.ZHAO Yandong,GAO Chao,ZHANG Xin,et al.Non-destructive measurement of plant stem water content based on standing wave ratio[J/OL].Transactions of the Chinese Society for Agricultural Machinery,2016,47(1):310-316.(in Chinese)
21严太淑.紫薇虫害紫薇绒蚧形态特征及防治对策探讨[J].农业灾害研究,2017,7(3):44-45.YAN Taishu.Discussion on morphological features and countermeasures of Eriococcus lagerostroemiae Kuwana on Lagerstroemia indica[J].Journal of Agricultural Catastrophology,2017,7(3):44-45.(in Chinese)
22 SOPHIAN A,TIAN G Y,TAYLOR D,et al.A feature extraction technique based on principal component analysis for pulsed eddy current NDT[J].NDT&E International,2003,36(1):37-41.
23 SAEYS Y,INZA I,LARRAAGA P.A review of feature selection techniques in bioinformatics[J].Bioinformatics,2007,23(19):2507-2517.
24 BALLABIO D.A MATLAB toolbox for principal component analysis and unsupervised exploration of data structure[J].Chemometrics and Intelligent Laboratory Systems,2015,149(12):1-9.
25 ABDI H,WILLIAMS L J.Principal component analysis[J].Wiley Interdisciplinary Reviews:Computational Statistics,2010,2(4):433-459.
26 BRO R,SMILDE A K.Principal component analysis[J].Analytical Methods,2014,6(9):2812-2831.
27 MATHUR A,FOODY G M.Multiclass and binary SVM classification:implications for training and classification users[J].IEEEGeoscience and Remote Sensing Letters,2008,5(2):241-245.