基于SVM核机器学习的三文鱼新鲜度检测系统
|
摘要
为了实现对不同冷藏温度下三文鱼新鲜度的检测与识别,设计了一种用于三文鱼气味指纹采集与新鲜度辨识的电子鼻系统。电子鼻系统由密闭检测气室、半导体气体传感器阵列、数据采集模块、模式识别模块和显示界面等组成。电子鼻模式识别方法采用核机器学习方法,以支持向量机(SVM)作为学习机。采集0、4、6℃温度下冷藏三文鱼样本的气味数据,对不同核函数及参数的核机器学习模型进行训练与测试,最终确定了适于此电子鼻系统识别三文鱼新鲜度的最佳核机器学习模型:核函数选用多项式核函数,核参数q取3,γ取15,c取0。此模型对不同温度冷藏三文鱼样本的冷藏时间具有一定的辨识能力,对于测试集,0℃允许偏差1 d预测正确率为92. 86%,4℃无偏差预测正确率为88. 89%、允许偏差1 d预测正确率100%,6℃无偏差预测正确率为75. 00%、允许偏差1 d预测正确率100%。将辨识结果与主成分分析结果(PCA)进行对比,此模型具有明显的优势。
In order to detect the odor of salmon refrigerated at different refrigerating temperatures and identify its freshness more accurately,an electronic nose based on kernel-based machine learning model was designed. It consisted of five parts,which were the detection air chamber,the array of six gas sensors,the data acquisition module,the pattern recognition module and the display interface. Kernelbased machine learning model was selected as the pattern recognition method of the electronic nose,and support vector machine( SVM) was selected as the learning machine of kernel-based machine learning model. The odor fingerprint data of salmon samples respectively refrigerated at 0℃,4℃ and 6℃ was collected to train and test the kernel-based machine learning models with different kernel functions and kernel parameters. Finally,a kernel-based machine learning model that had the best salmon freshness identification effect was determined. And it was determined that the polynomial function was taken in the kernel function,and the kernel parameters of q,γ and c were taken as 3,15 and 0,respectively.Analysis of identification result of test set salmon samples was conducted,which showed that no days deviation correct rate was 57. 14% and allowable deviation of 1 day correct rate was 92. 86% at 0℃,no days deviation correct rate was 88. 89% and allowable deviation of 1 day correct rate was 100% at 4℃,no days deviation correct rate was 75. 00% and allowable deviation of 1 day correct rate was 100% at 6℃. It proved that the model had certain ability to identify the freshness of salmons refrigerated at different temperatures. Compared with the result of principal component analysis( PCA),the kernelbased machine learning model had a better ability.
In order to detect the odor of salmon refrigerated at different refrigerating temperatures and identify its freshness more accurately,an electronic nose based on kernel-based machine learning model was designed. It consisted of five parts,which were the detection air chamber,the array of six gas sensors,the data acquisition module,the pattern recognition module and the display interface. Kernelbased machine learning model was selected as the pattern recognition method of the electronic nose,and support vector machine( SVM) was selected as the learning machine of kernel-based machine learning model. The odor fingerprint data of salmon samples respectively refrigerated at 0℃,4℃ and 6℃ was collected to train and test the kernel-based machine learning models with different kernel functions and kernel parameters. Finally,a kernel-based machine learning model that had the best salmon freshness identification effect was determined. And it was determined that the polynomial function was taken in the kernel function,and the kernel parameters of q,γ and c were taken as 3,15 and 0,respectively.Analysis of identification result of test set salmon samples was conducted,which showed that no days deviation correct rate was 57. 14% and allowable deviation of 1 day correct rate was 92. 86% at 0℃,no days deviation correct rate was 88. 89% and allowable deviation of 1 day correct rate was 100% at 4℃,no days deviation correct rate was 75. 00% and allowable deviation of 1 day correct rate was 100% at 6℃. It proved that the model had certain ability to identify the freshness of salmons refrigerated at different temperatures. Compared with the result of principal component analysis( PCA),the kernelbased machine learning model had a better ability.
引文
[1]励建荣.海水鱼类腐败机制及其保鲜技术研究进展[J].中国食品学报,2018,18(5):1-12.LI Jianrong.Research progress on spoilage mechanism and preservation technology of marine fish[J].Journal of Chinese Institute of Food Science and Technology,2018,18(5):1-12.(in Chinese)
[2]KIM H W,HONG Y J,JO J I,et al.Raw ready-to-eat seafood safety:microbiological quality of the various seafood species available in fishery,hyper and online markets[J].Letters in Applied Microbiology,2017,64(1):27-34.
[3]王一帆,宋晓燕,刘宝林.冷藏期间温度波动对三文鱼片品质的影响[J].食品与发酵科技,2016,52(1):24-27,32.WANG Yifan,SONG Xiaoyan,LIU Baolin.Effect of different temperature fluctuations on quality changes of salmon fillets during the cold storage[J].Food and Fermentation Technology,2016,52(1):24-27,32.(in Chinese)
[4]KAALE L D,EIKEVIK TM,RUSTAD T,et al.Changes in water holding capacity and drip loss of Atlantic salmon(Salmo salar)muscle during superchilled storage[J].LWT-Food Science and Technology,2014,55(2):528-535.
[5]江艳华,许东勤,姚琳,等.噬菌体复配抑菌剂对三文鱼中沙门氏菌的抑制与保鲜作用[J].农业工程学报,2018,34(16):287-293.JIANG Yanhua,XU Dongqin,YAO Lin,et al.Effects of combination of bacteriophage with other bacteriostatic agents on Salmonella control and freshness preservation of raw salmon[J].Transactions of the CSAE,2018,34(16):287-293.(in Chinese)
[6]李婷婷,丁婷,邹朝阳,等.顶空固相微萃取-气质联用技术结合电子鼻分析4℃冷藏过程中三文鱼片挥发性成分的变化[J].现代食品科技,2015,31(2):249-260.LI Tingting,DING Ting,ZOU Zhaoyang,et al.Analysis of changes in volatile components of salmon fillets during refrigerated storage by the HS-SPME-GC-MS technique combined with electronic nose[J].Modern Food Science&Technology,2015,31(2):249-260.(in Chinese)
[7]陈新伟,王俊,沈睿谦.基于GPRS的远程检测无线电子鼻系统[J/OL].农业机械学报,2015,46(4):238-245.CHEN Xinwei,WANG Jun,SHEN Ruiqian.Wireless electronic nose based on GPRS and its application on mangos[J/OL].Transactions of the Chinese Society for Agricultural Machinery,2015,46(4):238-245.http:∥www.j-csam.org/jcsam/ch/reader/view_abstract.aspx?flag=1&file_no=20150435&journal_id=jcsam.DOI:10.6041/j.issn.1000-1298.2015.04.035.(in Chinese)
[8]HONG E J,PARK S J,CHOI J Y,et al.Discrimination of palm olein oil and palm stearin oil mixtures using a mass spectrometry based electronic nose[J].Food Science&Biotechnology,2011,20(3):809-816.
[9]徐赛,陆华忠,周志艳,等.基于理化指标和电子鼻的果园荔枝成熟度识别方法[J/OL].农业机械学报,2015,46(12):226-232.XU Sai,LU Huazhong,ZHOU Zhiyan,et al.Identification of litchi's maturing stage in orchard based on physicochemical indexes and electronic nose[J/OL].Transactions of the Chinese Society for Agricultural Machinery,2015,46(12):226-232.http:∥www.j-csam.org/jcsam/ch/reader/view_abstract.aspx?flag=1&file_no=20151230&journal_id=jcsam DOI:10.6041/j.issn.1000-1298.2015.12.030.(in Chinese)
[10]HONG X,WANG J,HAI Z.Discrimination and prediction of multiple beef freshness indexes based on electronic nose[J].Sensors and Actuators:B Chemical,2012,161(1):381-389.
[11]傅润泽,沈建,王锡昌,等.基于神经网络及电子鼻的虾夷扇贝鲜活品质评价及传感器的筛选[J].农业工程学报,2016,32(6):268-275.FU Runze,SHEN Jian,WANG Xichang,et al.Quality evaluation of live Yesso scallop and sensor selection based on artificial neural network and electronic nose[J].Transactions of the CSAE,2016,32(6):268-275.(in Chinese)
[12]殷勇,薛俊莉,于慧春,等.基于KFDA的食醋电子鼻鉴别方法[J/OL].农业机械学报,2014,45(9):236-240.YIN Yong,XUE Junli,YU Huichun,et al.Identification method of electronic nose based on KFDA for different vinegar samples[J/OL].Transactions of the Chinese Society for Agricultural Machinery,2014,45(9):236-240.http:∥www.jcsam.org/jcsam/ch/reader/view_abstract.aspx?flag=1&file_no=20140938&journal_id=jcsam.DOI:10.6041/j.issn.1000-1298.2014.09.038.(in Chinese)
[13]SHAO Xiaolong,LI Hui,WANG Nan,et al.Comparison of different classification methods for analyzing electronic nose data to characterize sesame oils and blends[J].Sensors,2015,15(10):26726-26742.
[14]YAO Y,PAN S,FAN G,et al.Evaluation of volatile profile of Sichuan dongcai,a traditional salted vegetable,by SPME-GC-MSand E-nose[J].LWT-Food Science and Technology,2015,64(2):528-535.
[15]SHAO J D,RONG G,LEE J M.Learning a data-dependent kernel function for KPCA-based nonlinear process monitoring[J].Chemical Engineering Research and Design,2009,87(11):1471-1480.
[16]谭治英.核机器学习方法及其在视觉检测中的应用研究[D].成都:电子科技大学,2013.TAN Zhiying.Researches on kernel machine learning methods and its application in vision inspection[D].Chengdu:University of Electronic Science and Technology of China,2013.(in Chinese)
[17]刘凯.核机器学习在地图自动综合中的道路网智能选取研究[D].南京:南京大学,2017.LIU Kai.Research on intelligent selection of road network automatic generalization based on kernel-based machine learning[D].Nanjing:Nanjing University,2017.(in Chinese)
[18]MAJI S,BERG A C,MALIK J.Classification using intersection kernel support vector machines is efficient[C]∥IEEEConference on Computer Vision&Pattern Recognition.IEEE,2008.
[19]魏丽冉,岳峻,李振波,等.基于核函数支持向量机的植物叶部病害多分类检测方法[J/OL].农业机械学报,2017,48(增刊):166-171.WEI Liran,YUE Jun,LI Zhenbo,et al.Multi-classification detection method of plant leaf disease based on kernel function[J/OL].Transactions of the Chinese Society for Agricultural Machinery,2017,48(Supp.):166-171.http:∥www.j-csam.org/jcsam/ch/reader/view_abstract.aspx?flag=1&file_no=2017s027&journal_id=jcsam.DOI:10.6041/j.issn.1000-1298.2017.S0.027.(in Chinese)
[20]张新林,谢晶,郝楷,等.不同低温条件下三文鱼的品质变化[J].食品工业科技,2016,37(17):316-321.ZHANG Xinlin,XIE Jing,HAO Kai,et al.Effects of different cold storage conditions on quality of salmon[J].Science and Technology of Food Industry,2016,37(17):316-321.(in Chinese)
[21]丁婷.三文鱼新鲜度综合评价和货架期模型的建立[D].锦州:渤海大学,2015.DING Ting.Comprehensive evaluation of freshness and establishment of the shelf-life model of salmon[D].Jinzhou:Bohai University,2015.(in Chinese)
[22]包海蓉,张奎.不同冷藏温度对生鲜三文鱼品质变化的影响[J].食品工业科技,2012,33(14):344-347.BAO Hairong,ZHANG Kui.Effect of different refrigeration temperatures on quality changes of fresh salmon[J].Science and Technology of Food Industry,2012,33(14):344-347.(in Chinese)
[23]奉轲,花中秋,伍萍辉,等.用于检测糖尿病标志物的电子鼻优化设计[J].传感技术学报,2018,31(1):13-18.FENG Ke,HUA Zhongqiu,WU Pinghui,et al.Optimal design of electronic nose for detecting diabetes markers[J].Chinese Journal of Sensors and Actuators,2018,31(1):13-18.(in Chinese)
[24]KUANG F J,ZHANG S Y,JIN Z,et al.A novel SVM by combining kernel principal component analysis and improved chaotic particle swarm optimization for intrusion detection[J].Soft Computing,2015,19(5):1187-1199.
[25]赵丽娟,王慧琴,王可,等.基于多核支持向量回归的光谱反射率重建方法[J].液晶与显示,2018,33(12):1008-1018.ZHAO Lijuan,WANG Huiqin,WANG Ke,et al.Spectral reflectance reconstruction based on multi-kernel support vector regression[J].Chinese Journal of Liquid Crystals and Displays,2018,33(12):1008-1018.(in Chinese)
[2]KIM H W,HONG Y J,JO J I,et al.Raw ready-to-eat seafood safety:microbiological quality of the various seafood species available in fishery,hyper and online markets[J].Letters in Applied Microbiology,2017,64(1):27-34.
[3]王一帆,宋晓燕,刘宝林.冷藏期间温度波动对三文鱼片品质的影响[J].食品与发酵科技,2016,52(1):24-27,32.WANG Yifan,SONG Xiaoyan,LIU Baolin.Effect of different temperature fluctuations on quality changes of salmon fillets during the cold storage[J].Food and Fermentation Technology,2016,52(1):24-27,32.(in Chinese)
[4]KAALE L D,EIKEVIK TM,RUSTAD T,et al.Changes in water holding capacity and drip loss of Atlantic salmon(Salmo salar)muscle during superchilled storage[J].LWT-Food Science and Technology,2014,55(2):528-535.
[5]江艳华,许东勤,姚琳,等.噬菌体复配抑菌剂对三文鱼中沙门氏菌的抑制与保鲜作用[J].农业工程学报,2018,34(16):287-293.JIANG Yanhua,XU Dongqin,YAO Lin,et al.Effects of combination of bacteriophage with other bacteriostatic agents on Salmonella control and freshness preservation of raw salmon[J].Transactions of the CSAE,2018,34(16):287-293.(in Chinese)
[6]李婷婷,丁婷,邹朝阳,等.顶空固相微萃取-气质联用技术结合电子鼻分析4℃冷藏过程中三文鱼片挥发性成分的变化[J].现代食品科技,2015,31(2):249-260.LI Tingting,DING Ting,ZOU Zhaoyang,et al.Analysis of changes in volatile components of salmon fillets during refrigerated storage by the HS-SPME-GC-MS technique combined with electronic nose[J].Modern Food Science&Technology,2015,31(2):249-260.(in Chinese)
[7]陈新伟,王俊,沈睿谦.基于GPRS的远程检测无线电子鼻系统[J/OL].农业机械学报,2015,46(4):238-245.CHEN Xinwei,WANG Jun,SHEN Ruiqian.Wireless electronic nose based on GPRS and its application on mangos[J/OL].Transactions of the Chinese Society for Agricultural Machinery,2015,46(4):238-245.http:∥www.j-csam.org/jcsam/ch/reader/view_abstract.aspx?flag=1&file_no=20150435&journal_id=jcsam.DOI:10.6041/j.issn.1000-1298.2015.04.035.(in Chinese)
[8]HONG E J,PARK S J,CHOI J Y,et al.Discrimination of palm olein oil and palm stearin oil mixtures using a mass spectrometry based electronic nose[J].Food Science&Biotechnology,2011,20(3):809-816.
[9]徐赛,陆华忠,周志艳,等.基于理化指标和电子鼻的果园荔枝成熟度识别方法[J/OL].农业机械学报,2015,46(12):226-232.XU Sai,LU Huazhong,ZHOU Zhiyan,et al.Identification of litchi's maturing stage in orchard based on physicochemical indexes and electronic nose[J/OL].Transactions of the Chinese Society for Agricultural Machinery,2015,46(12):226-232.http:∥www.j-csam.org/jcsam/ch/reader/view_abstract.aspx?flag=1&file_no=20151230&journal_id=jcsam DOI:10.6041/j.issn.1000-1298.2015.12.030.(in Chinese)
[10]HONG X,WANG J,HAI Z.Discrimination and prediction of multiple beef freshness indexes based on electronic nose[J].Sensors and Actuators:B Chemical,2012,161(1):381-389.
[11]傅润泽,沈建,王锡昌,等.基于神经网络及电子鼻的虾夷扇贝鲜活品质评价及传感器的筛选[J].农业工程学报,2016,32(6):268-275.FU Runze,SHEN Jian,WANG Xichang,et al.Quality evaluation of live Yesso scallop and sensor selection based on artificial neural network and electronic nose[J].Transactions of the CSAE,2016,32(6):268-275.(in Chinese)
[12]殷勇,薛俊莉,于慧春,等.基于KFDA的食醋电子鼻鉴别方法[J/OL].农业机械学报,2014,45(9):236-240.YIN Yong,XUE Junli,YU Huichun,et al.Identification method of electronic nose based on KFDA for different vinegar samples[J/OL].Transactions of the Chinese Society for Agricultural Machinery,2014,45(9):236-240.http:∥www.jcsam.org/jcsam/ch/reader/view_abstract.aspx?flag=1&file_no=20140938&journal_id=jcsam.DOI:10.6041/j.issn.1000-1298.2014.09.038.(in Chinese)
[13]SHAO Xiaolong,LI Hui,WANG Nan,et al.Comparison of different classification methods for analyzing electronic nose data to characterize sesame oils and blends[J].Sensors,2015,15(10):26726-26742.
[14]YAO Y,PAN S,FAN G,et al.Evaluation of volatile profile of Sichuan dongcai,a traditional salted vegetable,by SPME-GC-MSand E-nose[J].LWT-Food Science and Technology,2015,64(2):528-535.
[15]SHAO J D,RONG G,LEE J M.Learning a data-dependent kernel function for KPCA-based nonlinear process monitoring[J].Chemical Engineering Research and Design,2009,87(11):1471-1480.
[16]谭治英.核机器学习方法及其在视觉检测中的应用研究[D].成都:电子科技大学,2013.TAN Zhiying.Researches on kernel machine learning methods and its application in vision inspection[D].Chengdu:University of Electronic Science and Technology of China,2013.(in Chinese)
[17]刘凯.核机器学习在地图自动综合中的道路网智能选取研究[D].南京:南京大学,2017.LIU Kai.Research on intelligent selection of road network automatic generalization based on kernel-based machine learning[D].Nanjing:Nanjing University,2017.(in Chinese)
[18]MAJI S,BERG A C,MALIK J.Classification using intersection kernel support vector machines is efficient[C]∥IEEEConference on Computer Vision&Pattern Recognition.IEEE,2008.
[19]魏丽冉,岳峻,李振波,等.基于核函数支持向量机的植物叶部病害多分类检测方法[J/OL].农业机械学报,2017,48(增刊):166-171.WEI Liran,YUE Jun,LI Zhenbo,et al.Multi-classification detection method of plant leaf disease based on kernel function[J/OL].Transactions of the Chinese Society for Agricultural Machinery,2017,48(Supp.):166-171.http:∥www.j-csam.org/jcsam/ch/reader/view_abstract.aspx?flag=1&file_no=2017s027&journal_id=jcsam.DOI:10.6041/j.issn.1000-1298.2017.S0.027.(in Chinese)
[20]张新林,谢晶,郝楷,等.不同低温条件下三文鱼的品质变化[J].食品工业科技,2016,37(17):316-321.ZHANG Xinlin,XIE Jing,HAO Kai,et al.Effects of different cold storage conditions on quality of salmon[J].Science and Technology of Food Industry,2016,37(17):316-321.(in Chinese)
[21]丁婷.三文鱼新鲜度综合评价和货架期模型的建立[D].锦州:渤海大学,2015.DING Ting.Comprehensive evaluation of freshness and establishment of the shelf-life model of salmon[D].Jinzhou:Bohai University,2015.(in Chinese)
[22]包海蓉,张奎.不同冷藏温度对生鲜三文鱼品质变化的影响[J].食品工业科技,2012,33(14):344-347.BAO Hairong,ZHANG Kui.Effect of different refrigeration temperatures on quality changes of fresh salmon[J].Science and Technology of Food Industry,2012,33(14):344-347.(in Chinese)
[23]奉轲,花中秋,伍萍辉,等.用于检测糖尿病标志物的电子鼻优化设计[J].传感技术学报,2018,31(1):13-18.FENG Ke,HUA Zhongqiu,WU Pinghui,et al.Optimal design of electronic nose for detecting diabetes markers[J].Chinese Journal of Sensors and Actuators,2018,31(1):13-18.(in Chinese)
[24]KUANG F J,ZHANG S Y,JIN Z,et al.A novel SVM by combining kernel principal component analysis and improved chaotic particle swarm optimization for intrusion detection[J].Soft Computing,2015,19(5):1187-1199.
[25]赵丽娟,王慧琴,王可,等.基于多核支持向量回归的光谱反射率重建方法[J].液晶与显示,2018,33(12):1008-1018.ZHAO Lijuan,WANG Huiqin,WANG Ke,et al.Spectral reflectance reconstruction based on multi-kernel support vector regression[J].Chinese Journal of Liquid Crystals and Displays,2018,33(12):1008-1018.(in Chinese)
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |