基于电学特征的苹果水心病无损检测
|
摘要
为了探寻快速而准确的苹果水心病无损检测新方法,该文以‘秦冠’水心病疑似病果和好果作为试材,逐果采集11个电学指标在100 Hz~3.98 MHz间13个频率点的特征值,然后切开并统计真实发病情况。利用主成分分析结合不同分类模型进行好果与病果判别分析,结果选取方差累积贡献率大于90%的主成分15个,Fisher判别、多层感知器人工神经网络(multi-layer perceptron,MLP)对好果和病果的判断正确率均随着主成分数的增加而增大,并分别在主成分数量达到前13、10时趋于稳定水平93.3%、95.4%。径向基人工神经网络(radical basis function,RBF)结合15个主成分判别的正确率75.1%。水心病引起介电损耗系数D、复阻抗相角deg、串联等效电容Cs和并联等效电容Cp及相对介电常数(ε')、损耗因子(ε")共6个参数在低频区(100~10 000 Hz)的观测值高于好果,是电学法能够对水心病果和好果进行‘识别’的原因。同时发现,利用低频率下(100~25 100 Hz)损耗因子(ε")值结合MLP或RBF人工神经网络模型对水心病果和好果识别正确率均能达到100%,是一种简便而高效的苹果水心病无损检测方法,可为今后进一步研发苹果果实水心病在线无损检测仪器提供理论与技术依据。
In order to find more cost-saving and efficient technology for non-destructive detection of watercore apple, recognizing the disease by following electric feature changes of the fruit was tested in this study. With the suspected watercore fruit and sound fruit of Malus pumila cv. Qinguan as material, we collected 143 feature data of 11 electric parameters at 13 frequency points from 100 Hz to 3.98 MHz fruit by fruit. Then each fruit was crosscut to tell and record whether watercore occurred in it. All the features data were analyzed by 3 steps. The first 2 steps were to screen differential features between sound and watercore apple, and then determine principal components(PCs) whose cumulative variance contribution rate reached over 90%. In the third step, different classification models were used to discriminate the sound and watercore fruit in combination with PCs obtained. The results showed that the incidence of watercore caused the increase in feature values of dielectric loss coefficient, complex impedance angle, series equivalent capacitance, parallel capacitance, relative dielectric constant, and loss factor at low frequency region(100-10000 Hz), a total of 36 differential feature values. These findings supported theoretically the possibility to discriminate sound and watercore apple based on differences in their electric features. Using principal component analysis, 15 and 7 PCs were extracted for original group of 143 features, and the group of 36 differential features, respectively. Accuracy rates of Fisher discrimination and multilayer perceptron(MLP) artificial neural network for the groups of 143 features and 36 differential features all elevated with the increase of PCs number, and reached a stable high level when PC number reached 13 and 10, respectively. Accuracy rates of Fisher discrimination and MLP for the group of 143 features using the former 13 PCs reached 93.8% and 95.4%, while for the group of 36 features using its former 7 PCs reached 91.7% and 93.8%, respectively. It indicated that the discrimination ability between sound and watercore apples was ascribed to mainly the 36 differential electric features. Discrimination by radial basis function(RBF) modeled by using 15 PCs reached an accuracy rate of 75.1% for the group of 143 features. Quality profiles of 2 kinds of apples differed in density, firmness, and soluble solids, which presented significantly higher level in watercore fruit(P<0.05), but titrate acids content was significantly lower. Physio-chemical characteristics changes resulted in the alternation of electric feature of watercore fruit and showed multiple-to-multiple correlation of cause-effect. Values of loss factor at low frequencies(100-25100 Hz) combined with MLP or RBF classifier all achieved accuracy rates of 100% on the recognization of either watercore or sound apple, which can be selected as the simple and effective method for apple watercore detection. The result can provide theoretical and technical support for the development of on-line equipment which can non-destructively detect the disease of apple watercore in the future.
In order to find more cost-saving and efficient technology for non-destructive detection of watercore apple, recognizing the disease by following electric feature changes of the fruit was tested in this study. With the suspected watercore fruit and sound fruit of Malus pumila cv. Qinguan as material, we collected 143 feature data of 11 electric parameters at 13 frequency points from 100 Hz to 3.98 MHz fruit by fruit. Then each fruit was crosscut to tell and record whether watercore occurred in it. All the features data were analyzed by 3 steps. The first 2 steps were to screen differential features between sound and watercore apple, and then determine principal components(PCs) whose cumulative variance contribution rate reached over 90%. In the third step, different classification models were used to discriminate the sound and watercore fruit in combination with PCs obtained. The results showed that the incidence of watercore caused the increase in feature values of dielectric loss coefficient, complex impedance angle, series equivalent capacitance, parallel capacitance, relative dielectric constant, and loss factor at low frequency region(100-10000 Hz), a total of 36 differential feature values. These findings supported theoretically the possibility to discriminate sound and watercore apple based on differences in their electric features. Using principal component analysis, 15 and 7 PCs were extracted for original group of 143 features, and the group of 36 differential features, respectively. Accuracy rates of Fisher discrimination and multilayer perceptron(MLP) artificial neural network for the groups of 143 features and 36 differential features all elevated with the increase of PCs number, and reached a stable high level when PC number reached 13 and 10, respectively. Accuracy rates of Fisher discrimination and MLP for the group of 143 features using the former 13 PCs reached 93.8% and 95.4%, while for the group of 36 features using its former 7 PCs reached 91.7% and 93.8%, respectively. It indicated that the discrimination ability between sound and watercore apples was ascribed to mainly the 36 differential electric features. Discrimination by radial basis function(RBF) modeled by using 15 PCs reached an accuracy rate of 75.1% for the group of 143 features. Quality profiles of 2 kinds of apples differed in density, firmness, and soluble solids, which presented significantly higher level in watercore fruit(P<0.05), but titrate acids content was significantly lower. Physio-chemical characteristics changes resulted in the alternation of electric feature of watercore fruit and showed multiple-to-multiple correlation of cause-effect. Values of loss factor at low frequencies(100-25100 Hz) combined with MLP or RBF classifier all achieved accuracy rates of 100% on the recognization of either watercore or sound apple, which can be selected as the simple and effective method for apple watercore detection. The result can provide theoretical and technical support for the development of on-line equipment which can non-destructively detect the disease of apple watercore in the future.
引文
[1]刘小勇,张辉元,董铁.苹果水心病无损检测与防治研究进展[J].果树学报,2008,25(5):721-726.
[2]王列珍,郭保才,张红梅.苹果水心病的成因及预防[J].科学种养,2016,(10):30-30.
[3]王金友.苹果病虫害防治[M].北京:金盾出版社,1992:90-91.
[4]Baranowski P,Lipecki J,Mazurek W.Detection of watercore in‘Gloster’apples using thermography[J].Postharvest Biology&Technology,2008,47(3):358-366.
[5]Dai T,Cai C,Ma H.Apple watercore region detection using color pixel classification[J].Icic Express Letters,2015,9(4):1213-1219.
[6]Sun D W.Hyperspectral Imaging for Food Quality Analysis and Control[M].Amsterdam:Elsevier,2010:471-477.
[7]韩东海,刘新鑫,赵丽丽.苹果水心病的光学无损检测[J].农业机械学报,2004,35(5):143-146.Han Donghai,Liu Xinxin,Zhao Lili,et al.Research of nondestructive detection of apple watercore by optical means[J].Transactions of the Chinese Society for Agricultural Machinery,2004,35(5):143-146.(in Chinese with English abstract)
[8]刘新鑫,韩东海,涂润林.苹果水心病在贮藏期变化的无损检测[J].农业工程学报,2004,20(1):211-214.Liu Xinxin,Han Donghai,Tu Runlin,et al.Non-destructive detecting watercore apple during storage[J].Transactions of the Chinese Society of Agricultural Engineering(Transactions of the CSAE),2004,20(1):211-214.(in Chinese with English abstract)
[9]田秀丽,付广伟.基于近红外便携式苹果水心病自动无损检测仪的研制[J].计算机与信息技术,2005(8):5-7.
[10]王思玲,蔡骋,马惠玲.基于高光谱成像的苹果水心病无损检测[J].北方园艺,2015(8):124-130.Wang Siling,Cai Cheng,Ma Huiling,et al.Nondestructive detection of apple watercore based on hyperspectral imaging[J].Northern Horticulture,2015,(8):124-130.(in Chinese with English abstract)
[11]孔繁荣,郭文川.发育后期苹果的介电特性与理化特性的关系[J].食品科学,2016,37(9):13-17.Kong Fanrong,Guo Wenchuan.Relationship between dielectric properties and physicochemical properties of apples during late developmental period[J].Food Science,2016,37(9):13-17.(in Chinese with English abstract)
[12]李芳,蔡骋,马惠玲.基于生物阻抗特性分析的苹果霉心病无损检测[J].食品科学,2013,34(18):197-202.Li Fang,Cai Cheng,Ma Huiling.Nondestructive detection of apple mouldy core based on bioimpedance properties[J].Food Science,2013,34(18):197-202.(in Chinese with English abstract)
[13]马海军,宋长冰,张继澍.电激信号频率对红点病苹果采后电学特性影响[J].农业机械学报,2009,40(10):97-101.Ma Haijun,Song Changbing,Zhang Jishu,et al.Influence of frequency of electric excitation signal on dielectric property of Fuji apples with Red-dot disease[J].Transactions of the Chinese Society for Agricultural Machinery,2009,40(10):97-101.(in Chinese with English abstract)
[14]朱新华,郭文川,郭康权.电激信号对果品电参数的影响[J].西北农林科技大学学报自然科学版,2004,32(11):125-128.Zhu Xinhua,Guo Wenchuan,Guo Kangquan.The effect of electrical excitation signal on the electrical parameters of fruit[J].Journal of Northwest A&F university(Natural Science Edition),2004,32(11):125-128.(in Chinese with English abstract)
[15]中国农业科学院蔬菜花卉研究所.GB/T 12293-90水果、蔬菜制品可滴定酸度的测定[S].北京:国家技术监督局,1989.
[16]Roweis S.EM algorithms for PCA and SPCA[J].Advances in Neural Information Processing Systems,1998,(10):626-632.
[17]蔡骋,李晓龙,马惠玲.基于生物阻抗特性的苹果新鲜度无损测定[J].农业机械学报,2013,44(2):147-152.Cai Cheng,Li Xiaolong,Ma Huiling,et al.Non-destructive detection of freshness grade for apple fruit based on bio-impedance properties[J].Transactions of the Chinese Society for Agricultural Machinery,2013a,44(2).(in Chinese with English abstract)
[18]郭文川,郭康权,朱新华.介电特性在蕃茄和苹果品种识别中的应用[J].农业机械学报,2006,37(8):130-132.Guo Wenchuan,Guo Kangquan,Zhu Xinhua.Application of dielectric properties in identifying species of tomatoes and apples[J].Transactions of the Chinese Society for Agricultural Machinery,2006,37(8):130-132.(in Chinese with English abstract)
[19]Harker F R,Elgar H J,Watkins C B.Physical and mechanical changes in strawberry fruit after high carbon dioxide treatments[J].Postharvest Biology&Technology,2000,19(2):139-146.
[20]郭文川,朱新华,郭康权.采后苹果电特性与生理特性的关系及其应用[J].农业工程学报,2005,21(7):136-139.Guo Wenchuan,Zhu Xinhua,Guo Kangquan.Relationship between electrical properties and physiological properties of postharvest apples and its application[J].Transactions of the Chinese Society of Agricultural Engineering(Transactions of the CSAE),2005,21(7):136-139.(in Chinese with English abstract)
[21]刘亚平,刘兴华,李红波.葡萄冷藏中电学参数与质地特性变化规律[J].农业工程学报,2011,27(10):343-348.Liu Yaping,Liu Xinghua,Li Hongbo.Law of dielectric parameters and texture properties for grape during cold storage[J].Transactions of the Chinese Society of Agricultural Engineering(Transactions of the CSAE),2011,27(10):343-348.(in Chinese with English abstract)
[22]王仁才,熊兴耀,谭兴和.美味猕猴桃果实采后硬度与细胞壁超微结构变化[J].湖南农业大学学报(自然科学版),2000,26(6):457-460.Wang Rencai,Xiong Xingyao,Tan Xinghe,et al.Changes of fruit and ultrastructure of cell wall in Actinidia deliciosa lines during postharvest ripening[J].Journal of Hunan Agricultural University(Natural Sciences),2000,26(6):457-460.(in Chinese with English abstract)
[23]王瑞庆,张继澍,马书尚.基于电学参数的货架期红巴梨无损检测[J].农业工程学报,2009,25(4):243-247.Wang Ruiqing,Zhang Jishu,Ma Shushang.Nondestructive determination of the quality of Red Bartlett pear during shelf life by electrical characteristics[J].Transactions of the Chinese Society of Agricultural Engineering(Transactions of the CSAE),2009,25(4):243-247.(in Chinese with English abstract)
[24]唐玉荣,张宏,曹昕昕.库尔勒香梨果实品质的电学特性研究[J].河南农业科学,2017,46(3):148-151.Tang Yurong,Zhang Hong,Cao Xinxin,et al.Study on electric properties of Korla Pear Quality[J].Journal of Henan Agricultural Sciences,2017,46(3):148-151.(in Chinese with English abstract)
[25]安慧珍,马惠玲,任小林.苹果果实贮藏期间电学参数与品质指标的关系[J].食品科学,2013,34(2):298-302.An Huizhen,Ma Huiling,Ren Xiaolin.Relationship between electrical parameters and quality indexes of apple fruits during storage[J].Food Science,2013,34(2):298-302.(in Chinese with English abstract)
[26]李琳,罗安伟,苏苗.CPPU处理和失重对猕猴桃品质和电学特性的影响[J/OL].食品科学,2017-09-27,1-9.http://kns.cnki.net/kcms/detail/11.2206.TS.20170927.606.196.html.Li Lin,Luo Anwei,Su Miao,et al.Effects of CPPUtreatment and weight loss on the quality and electrical properties of kiwifruit[J/OL].Food Science,2017-09-27,1-9.http://kns.cnki.net/kcms/detail/11.2206.TS.20170927.1606.196.html.(in Chinese with English abstract)
[27]蔡骋,李永超,马惠玲.基于介电特征选择的苹果内部品质无损分级[J].农业工程学报,2013,29(21):279-287.Cai Cheng,Li Yongchao,Ma Huiling,et al.Nondestructive classification of internal quality of apple based on dielectric feature selection[J].Transactions of the Chinese Society of Agricultural Engineering(Transactions of the CSAE),2013b,29(21):279-287.(in Chinese with English abstract)
[28]兰海鹏,唐玉荣,刘文亮.成熟期基库尔勒香梨电学特性研究[J].农机化研究,2014,36(7):178-181.Lan Haipeng,Tang Yurong,Liu Wenliang,et al.Study on the Korla Pear electrophysiological properties during Maturation Process[J].Journal of Agricultural Mechanization Research,2014,(7):178-181.(in Chinese with English abstract)
[29]Williamson P P.Mathematical statistics with applications[J].Journal of the American Statistical Association,2006,48(473):384-385.
[30]Singh S.Artificial neural network[J].Science Mosaic,2016,1522(1):65-65.
[2]王列珍,郭保才,张红梅.苹果水心病的成因及预防[J].科学种养,2016,(10):30-30.
[3]王金友.苹果病虫害防治[M].北京:金盾出版社,1992:90-91.
[4]Baranowski P,Lipecki J,Mazurek W.Detection of watercore in‘Gloster’apples using thermography[J].Postharvest Biology&Technology,2008,47(3):358-366.
[5]Dai T,Cai C,Ma H.Apple watercore region detection using color pixel classification[J].Icic Express Letters,2015,9(4):1213-1219.
[6]Sun D W.Hyperspectral Imaging for Food Quality Analysis and Control[M].Amsterdam:Elsevier,2010:471-477.
[7]韩东海,刘新鑫,赵丽丽.苹果水心病的光学无损检测[J].农业机械学报,2004,35(5):143-146.Han Donghai,Liu Xinxin,Zhao Lili,et al.Research of nondestructive detection of apple watercore by optical means[J].Transactions of the Chinese Society for Agricultural Machinery,2004,35(5):143-146.(in Chinese with English abstract)
[8]刘新鑫,韩东海,涂润林.苹果水心病在贮藏期变化的无损检测[J].农业工程学报,2004,20(1):211-214.Liu Xinxin,Han Donghai,Tu Runlin,et al.Non-destructive detecting watercore apple during storage[J].Transactions of the Chinese Society of Agricultural Engineering(Transactions of the CSAE),2004,20(1):211-214.(in Chinese with English abstract)
[9]田秀丽,付广伟.基于近红外便携式苹果水心病自动无损检测仪的研制[J].计算机与信息技术,2005(8):5-7.
[10]王思玲,蔡骋,马惠玲.基于高光谱成像的苹果水心病无损检测[J].北方园艺,2015(8):124-130.Wang Siling,Cai Cheng,Ma Huiling,et al.Nondestructive detection of apple watercore based on hyperspectral imaging[J].Northern Horticulture,2015,(8):124-130.(in Chinese with English abstract)
[11]孔繁荣,郭文川.发育后期苹果的介电特性与理化特性的关系[J].食品科学,2016,37(9):13-17.Kong Fanrong,Guo Wenchuan.Relationship between dielectric properties and physicochemical properties of apples during late developmental period[J].Food Science,2016,37(9):13-17.(in Chinese with English abstract)
[12]李芳,蔡骋,马惠玲.基于生物阻抗特性分析的苹果霉心病无损检测[J].食品科学,2013,34(18):197-202.Li Fang,Cai Cheng,Ma Huiling.Nondestructive detection of apple mouldy core based on bioimpedance properties[J].Food Science,2013,34(18):197-202.(in Chinese with English abstract)
[13]马海军,宋长冰,张继澍.电激信号频率对红点病苹果采后电学特性影响[J].农业机械学报,2009,40(10):97-101.Ma Haijun,Song Changbing,Zhang Jishu,et al.Influence of frequency of electric excitation signal on dielectric property of Fuji apples with Red-dot disease[J].Transactions of the Chinese Society for Agricultural Machinery,2009,40(10):97-101.(in Chinese with English abstract)
[14]朱新华,郭文川,郭康权.电激信号对果品电参数的影响[J].西北农林科技大学学报自然科学版,2004,32(11):125-128.Zhu Xinhua,Guo Wenchuan,Guo Kangquan.The effect of electrical excitation signal on the electrical parameters of fruit[J].Journal of Northwest A&F university(Natural Science Edition),2004,32(11):125-128.(in Chinese with English abstract)
[15]中国农业科学院蔬菜花卉研究所.GB/T 12293-90水果、蔬菜制品可滴定酸度的测定[S].北京:国家技术监督局,1989.
[16]Roweis S.EM algorithms for PCA and SPCA[J].Advances in Neural Information Processing Systems,1998,(10):626-632.
[17]蔡骋,李晓龙,马惠玲.基于生物阻抗特性的苹果新鲜度无损测定[J].农业机械学报,2013,44(2):147-152.Cai Cheng,Li Xiaolong,Ma Huiling,et al.Non-destructive detection of freshness grade for apple fruit based on bio-impedance properties[J].Transactions of the Chinese Society for Agricultural Machinery,2013a,44(2).(in Chinese with English abstract)
[18]郭文川,郭康权,朱新华.介电特性在蕃茄和苹果品种识别中的应用[J].农业机械学报,2006,37(8):130-132.Guo Wenchuan,Guo Kangquan,Zhu Xinhua.Application of dielectric properties in identifying species of tomatoes and apples[J].Transactions of the Chinese Society for Agricultural Machinery,2006,37(8):130-132.(in Chinese with English abstract)
[19]Harker F R,Elgar H J,Watkins C B.Physical and mechanical changes in strawberry fruit after high carbon dioxide treatments[J].Postharvest Biology&Technology,2000,19(2):139-146.
[20]郭文川,朱新华,郭康权.采后苹果电特性与生理特性的关系及其应用[J].农业工程学报,2005,21(7):136-139.Guo Wenchuan,Zhu Xinhua,Guo Kangquan.Relationship between electrical properties and physiological properties of postharvest apples and its application[J].Transactions of the Chinese Society of Agricultural Engineering(Transactions of the CSAE),2005,21(7):136-139.(in Chinese with English abstract)
[21]刘亚平,刘兴华,李红波.葡萄冷藏中电学参数与质地特性变化规律[J].农业工程学报,2011,27(10):343-348.Liu Yaping,Liu Xinghua,Li Hongbo.Law of dielectric parameters and texture properties for grape during cold storage[J].Transactions of the Chinese Society of Agricultural Engineering(Transactions of the CSAE),2011,27(10):343-348.(in Chinese with English abstract)
[22]王仁才,熊兴耀,谭兴和.美味猕猴桃果实采后硬度与细胞壁超微结构变化[J].湖南农业大学学报(自然科学版),2000,26(6):457-460.Wang Rencai,Xiong Xingyao,Tan Xinghe,et al.Changes of fruit and ultrastructure of cell wall in Actinidia deliciosa lines during postharvest ripening[J].Journal of Hunan Agricultural University(Natural Sciences),2000,26(6):457-460.(in Chinese with English abstract)
[23]王瑞庆,张继澍,马书尚.基于电学参数的货架期红巴梨无损检测[J].农业工程学报,2009,25(4):243-247.Wang Ruiqing,Zhang Jishu,Ma Shushang.Nondestructive determination of the quality of Red Bartlett pear during shelf life by electrical characteristics[J].Transactions of the Chinese Society of Agricultural Engineering(Transactions of the CSAE),2009,25(4):243-247.(in Chinese with English abstract)
[24]唐玉荣,张宏,曹昕昕.库尔勒香梨果实品质的电学特性研究[J].河南农业科学,2017,46(3):148-151.Tang Yurong,Zhang Hong,Cao Xinxin,et al.Study on electric properties of Korla Pear Quality[J].Journal of Henan Agricultural Sciences,2017,46(3):148-151.(in Chinese with English abstract)
[25]安慧珍,马惠玲,任小林.苹果果实贮藏期间电学参数与品质指标的关系[J].食品科学,2013,34(2):298-302.An Huizhen,Ma Huiling,Ren Xiaolin.Relationship between electrical parameters and quality indexes of apple fruits during storage[J].Food Science,2013,34(2):298-302.(in Chinese with English abstract)
[26]李琳,罗安伟,苏苗.CPPU处理和失重对猕猴桃品质和电学特性的影响[J/OL].食品科学,2017-09-27,1-9.http://kns.cnki.net/kcms/detail/11.2206.TS.20170927.606.196.html.Li Lin,Luo Anwei,Su Miao,et al.Effects of CPPUtreatment and weight loss on the quality and electrical properties of kiwifruit[J/OL].Food Science,2017-09-27,1-9.http://kns.cnki.net/kcms/detail/11.2206.TS.20170927.1606.196.html.(in Chinese with English abstract)
[27]蔡骋,李永超,马惠玲.基于介电特征选择的苹果内部品质无损分级[J].农业工程学报,2013,29(21):279-287.Cai Cheng,Li Yongchao,Ma Huiling,et al.Nondestructive classification of internal quality of apple based on dielectric feature selection[J].Transactions of the Chinese Society of Agricultural Engineering(Transactions of the CSAE),2013b,29(21):279-287.(in Chinese with English abstract)
[28]兰海鹏,唐玉荣,刘文亮.成熟期基库尔勒香梨电学特性研究[J].农机化研究,2014,36(7):178-181.Lan Haipeng,Tang Yurong,Liu Wenliang,et al.Study on the Korla Pear electrophysiological properties during Maturation Process[J].Journal of Agricultural Mechanization Research,2014,(7):178-181.(in Chinese with English abstract)
[29]Williamson P P.Mathematical statistics with applications[J].Journal of the American Statistical Association,2006,48(473):384-385.
[30]Singh S.Artificial neural network[J].Science Mosaic,2016,1522(1):65-65.