基于电子鼻和电子舌的樱桃番茄汁品质检测方法研究
|
摘要
近年来,消费者越来越青睐高品质、无添加、新鲜营养和少加工破坏的食物。鲜榨果汁的出现,正好符合消费者这个需求。本研究以樱桃番茄汁为对象,采用电子鼻和电子舌技术对樱桃番茄从榨汁前整果新鲜度、榨汁前处理、制汁、不同品质果汁混合、灭菌后放置的整个流程进行检测和评估,鉴定不同原料新鲜度、不同前处理方式、榨汁灭菌后放置不同时间和不同混合比例的樱桃番茄汁品质。本文从探索樱桃番茄汁的电子鼻和电子舌数据结构出发,比较基于单独电子鼻和电子舌的樱桃番茄汁品质鉴别方法的性能,然后利用数据融合方法优化樱桃番茄汁品质鉴别方法,最后提出半监督分类算法改善樱桃番茄汁品质分类模型。主要结论如下：
(1)采用谱聚类、SL聚类法(Single Linkage clustering, SL)、CL聚类法(Complete Linkage clustering, CL)、Ward's聚类法、FCM聚类法(Fuzzy c-means, FCM)、κ-means聚类法和ISODATA聚类法(Iterative Selforganizing Data Analysis Techniques Algorithm, ISODATA),分别对3个电子鼻和电子舌数据集底层结构进行探索。2维主成分分析(Principal Components Analysis, PCA)图和3个聚类有效性评价指标(Precision, Mutual Information和Rand Index)都表明,本研究提出的谱聚类算法能比传统的聚类法更好地反映出真实数据结构。
(2)采用直接电子鼻检测、水汽处理后再电子鼻检测和电子舌检测,对4组不同混合比例的樱桃番茄汁品质进行鉴定。PCA、CDA (Canonical Discriminant Analysis, CDA)、LVQ (Learning Vector Quantization, LVQ), SVM (Support Vector Machines, SVM)和PCR (Principal Component Regression, PCR)结果表明,水汽处理后再进行电子鼻检测并不能提高对4组樱桃番茄汁的区分,而单独电子鼻或电子舌基本可以实现对混合果汁的分类和品质指标预测。
(3)分别采用电子鼻和电子舌对不同原果新鲜度(4℃下储藏16天,25℃下储藏8天)的樱桃番茄汁进行检测。结果表明,单独电子鼻或电子舌可以辨识不同原果新鲜度的果汁,且基于电子舌数据建立的不同原果新鲜度果汁的分类和理化指标预测模型,都比基于电子鼻的好。
(4)采用6种数据融合方式(直接融合法、PCA降维融合法、不同阈值的factor F选择法和逐步选择法)建立原果新鲜度追溯模型。结果表明,基于单个仪器建立的回归模型都缺乏泛化性,而数据融合后则可以对验证集样本的理化指标进行很好地预测。
(5)比较cluster-then-label半监督分类法和有监督的PNN (Probabilistic Neural Networks, PNN)与LVQ建立的分类器性能。结果发现,对于不同原果新鲜度和不同混合比例的樱桃蕃茄汁数据集,基于谱聚类和FCM的Cluster-then-Label法的测试集正确率都高于两种有监督分类法,且半监督分类器对已知训练集和未知测试集的分类正确率差不多,其模型更稳定更具有泛化性。
通过以上结论可知,利用电子鼻和电子舌技术对果汁品质进行鉴别是可行的。选用谱聚类算法可以更好了解果汁的电子鼻和电子舌数据集结构,且基于谱聚类的Cluster-then-Label半监督分类法能在只有少量有标签数据的情况下建立可靠分类模型。同时,当选择合适的特征提取方法后,数据融合比单独使用电子鼻和电子舌都要好。
Nowadays, consumers demand high-quality, additive-free, minimally-processed, nutritious, and fresh-like products. Freshly-squeezed fruit juice labeled as100%fruit is typically one of these products. This research employed an electronic nose (e-nose) and an electronic tongue (e-tongue) to detect the quality of cherry tomato juices. The tasks of tracing material freshness, discriminating pretreatments, evaluating sterilization persistence and indenfying adulteration levels were considered. The whole structure of this paper is as follows:(a) explore data structure of the e-nose and e-tongue datasets of cherry tomato juices;(b) establish quality evaluation models for cherry tomato juices based on the e-nose and e-tongue detections, respectively;(c) optimize those quality evaluation models by combining the e-nose and e-tongue signals; and (d) present a semi-supervised approach to improve the quality discrimination classifiers. The main conclusions of this research are as follows:
(1) Spectral clustering, single Linkage clustering (SL), complete Linkage clustering (CL), Ward's clustering, Fuzzy c-means (FCM), κ-means clustering and iterative selforganizing data analysis techniques algorithm (ISODATA) were employed to explore the underlying data structure of three e-nose and three e-tongue datasets. Both2D principal components analysis (PCA) plots and three cluster validation criteria (CVC)-precision, mutual information (MI) and rand index (RI)-demonstrated that the spectral clustering outperformed traditional clustering methods at reflecting the real underlying structure of datasets.
(2) The e-nose and e-tongue were applied to authenticate cherry tomato juices with different adulteration levels. In addition to directly e-nose measurement, a pretreatment of employing anhydrous sodium carbonate as desiccant was also conducted to observe if reducing of water vapor would improve the authentication ability of e-nose. The results of PCA, canonical discriminant analysis (CDA), learning vector quantization (LVQ), support vector machines (SVM) and principal component regression (PCR) all demonstrate that employing anhydrous sodium carbonate as desiccant did not improve the performance of e-nose when detecting liquid samples; on the contrary, directly e-nose measurement was better than e-nose with desiccant at authenticating cherry tomato juices. Meanwhile, either the e-tongue or the direct e-nose could authenticate cherry tomato juices as well as predict quality indices (pH and solube solid contents (SSC)).
(3) The e-nose and e-tongue were applied to measure the freshness of cherry tomato under different storage conditions (16days at4℃and8days at25℃). Both qualitative and quantitative results demonstrate it is possible to trace the freshness of original cherry tomatoes through detecting the squeezed juices. Meanwhile, freshness discrimination models as well as quality indices prediction models built based on the e-tongue were better than those based on the e-nose.
(4) A combination of the e-nose and e-tongue was tried to trace the freshness of cherry tomatoes by detecting the squeezed juices. Six data fusion approaches-simple concatenation, stepwise selection, PCA, factor F with Log F values higher than3,2.5and2, respectively-were employed. A second batch of experiments was conducted to produce an independent dataset for validation of the material freshness tracing models. The results demonstrated that quality regression models built based on single usage of e-nose or e-tongue were lack of generalization. On the contrary, models built based on fusion datasets could predict quality indices (pH, SSC, vitamin C and firmness) for the second batch of experimental data.
(5) A semi-supervised classification approach-cluster-then-label-was compared with supervised approaches-probabilistic neural networks (PNN) and LVQ. In both cases of tracing material freshness and authenticating adulteration levels, cherry tomato juice quality evaluation models built using spectral clustering and FCM based cluster-then-label approaches outperformed the supervised approaches. In the cases that only a few labeled data is available for training, supervised classifiers tend to overfit the particular training dataset and thus lacking generalization ability, i.e., it tends to fail to classify unknown data. On the contrary, the semi-supervised classifier is more stable and of generalization. Classification accuracy for the training and testing datasets were almost the same.
In consideration of the above conclusions, it is obvious that establishing quality evaluation models for cherry tomato juices based on the e-nose and e-tongue techniques is possible. The proposed spectral clustering offers a better approach to explore underlying structures of e-nose and e-tongue datasets; and based on this clustering approach, the semi-supervised cluster-then-lable approach could build a reliable classifier with only a few labeled training data. Meanwhile, with appropriate feacture extraction approaches, the fusion use of both instruements could be better than individual usage of the e-nose and e-tongue.
(1)采用谱聚类、SL聚类法(Single Linkage clustering, SL)、CL聚类法(Complete Linkage clustering, CL)、Ward's聚类法、FCM聚类法(Fuzzy c-means, FCM)、κ-means聚类法和ISODATA聚类法(Iterative Selforganizing Data Analysis Techniques Algorithm, ISODATA),分别对3个电子鼻和电子舌数据集底层结构进行探索。2维主成分分析(Principal Components Analysis, PCA)图和3个聚类有效性评价指标(Precision, Mutual Information和Rand Index)都表明,本研究提出的谱聚类算法能比传统的聚类法更好地反映出真实数据结构。
(2)采用直接电子鼻检测、水汽处理后再电子鼻检测和电子舌检测,对4组不同混合比例的樱桃番茄汁品质进行鉴定。PCA、CDA (Canonical Discriminant Analysis, CDA)、LVQ (Learning Vector Quantization, LVQ), SVM (Support Vector Machines, SVM)和PCR (Principal Component Regression, PCR)结果表明,水汽处理后再进行电子鼻检测并不能提高对4组樱桃番茄汁的区分,而单独电子鼻或电子舌基本可以实现对混合果汁的分类和品质指标预测。
(3)分别采用电子鼻和电子舌对不同原果新鲜度(4℃下储藏16天,25℃下储藏8天)的樱桃番茄汁进行检测。结果表明,单独电子鼻或电子舌可以辨识不同原果新鲜度的果汁,且基于电子舌数据建立的不同原果新鲜度果汁的分类和理化指标预测模型,都比基于电子鼻的好。
(4)采用6种数据融合方式(直接融合法、PCA降维融合法、不同阈值的factor F选择法和逐步选择法)建立原果新鲜度追溯模型。结果表明,基于单个仪器建立的回归模型都缺乏泛化性,而数据融合后则可以对验证集样本的理化指标进行很好地预测。
(5)比较cluster-then-label半监督分类法和有监督的PNN (Probabilistic Neural Networks, PNN)与LVQ建立的分类器性能。结果发现,对于不同原果新鲜度和不同混合比例的樱桃蕃茄汁数据集,基于谱聚类和FCM的Cluster-then-Label法的测试集正确率都高于两种有监督分类法,且半监督分类器对已知训练集和未知测试集的分类正确率差不多,其模型更稳定更具有泛化性。
通过以上结论可知,利用电子鼻和电子舌技术对果汁品质进行鉴别是可行的。选用谱聚类算法可以更好了解果汁的电子鼻和电子舌数据集结构,且基于谱聚类的Cluster-then-Label半监督分类法能在只有少量有标签数据的情况下建立可靠分类模型。同时,当选择合适的特征提取方法后,数据融合比单独使用电子鼻和电子舌都要好。
Nowadays, consumers demand high-quality, additive-free, minimally-processed, nutritious, and fresh-like products. Freshly-squeezed fruit juice labeled as100%fruit is typically one of these products. This research employed an electronic nose (e-nose) and an electronic tongue (e-tongue) to detect the quality of cherry tomato juices. The tasks of tracing material freshness, discriminating pretreatments, evaluating sterilization persistence and indenfying adulteration levels were considered. The whole structure of this paper is as follows:(a) explore data structure of the e-nose and e-tongue datasets of cherry tomato juices;(b) establish quality evaluation models for cherry tomato juices based on the e-nose and e-tongue detections, respectively;(c) optimize those quality evaluation models by combining the e-nose and e-tongue signals; and (d) present a semi-supervised approach to improve the quality discrimination classifiers. The main conclusions of this research are as follows:
(1) Spectral clustering, single Linkage clustering (SL), complete Linkage clustering (CL), Ward's clustering, Fuzzy c-means (FCM), κ-means clustering and iterative selforganizing data analysis techniques algorithm (ISODATA) were employed to explore the underlying data structure of three e-nose and three e-tongue datasets. Both2D principal components analysis (PCA) plots and three cluster validation criteria (CVC)-precision, mutual information (MI) and rand index (RI)-demonstrated that the spectral clustering outperformed traditional clustering methods at reflecting the real underlying structure of datasets.
(2) The e-nose and e-tongue were applied to authenticate cherry tomato juices with different adulteration levels. In addition to directly e-nose measurement, a pretreatment of employing anhydrous sodium carbonate as desiccant was also conducted to observe if reducing of water vapor would improve the authentication ability of e-nose. The results of PCA, canonical discriminant analysis (CDA), learning vector quantization (LVQ), support vector machines (SVM) and principal component regression (PCR) all demonstrate that employing anhydrous sodium carbonate as desiccant did not improve the performance of e-nose when detecting liquid samples; on the contrary, directly e-nose measurement was better than e-nose with desiccant at authenticating cherry tomato juices. Meanwhile, either the e-tongue or the direct e-nose could authenticate cherry tomato juices as well as predict quality indices (pH and solube solid contents (SSC)).
(3) The e-nose and e-tongue were applied to measure the freshness of cherry tomato under different storage conditions (16days at4℃and8days at25℃). Both qualitative and quantitative results demonstrate it is possible to trace the freshness of original cherry tomatoes through detecting the squeezed juices. Meanwhile, freshness discrimination models as well as quality indices prediction models built based on the e-tongue were better than those based on the e-nose.
(4) A combination of the e-nose and e-tongue was tried to trace the freshness of cherry tomatoes by detecting the squeezed juices. Six data fusion approaches-simple concatenation, stepwise selection, PCA, factor F with Log F values higher than3,2.5and2, respectively-were employed. A second batch of experiments was conducted to produce an independent dataset for validation of the material freshness tracing models. The results demonstrated that quality regression models built based on single usage of e-nose or e-tongue were lack of generalization. On the contrary, models built based on fusion datasets could predict quality indices (pH, SSC, vitamin C and firmness) for the second batch of experimental data.
(5) A semi-supervised classification approach-cluster-then-label-was compared with supervised approaches-probabilistic neural networks (PNN) and LVQ. In both cases of tracing material freshness and authenticating adulteration levels, cherry tomato juice quality evaluation models built using spectral clustering and FCM based cluster-then-label approaches outperformed the supervised approaches. In the cases that only a few labeled data is available for training, supervised classifiers tend to overfit the particular training dataset and thus lacking generalization ability, i.e., it tends to fail to classify unknown data. On the contrary, the semi-supervised classifier is more stable and of generalization. Classification accuracy for the training and testing datasets were almost the same.
In consideration of the above conclusions, it is obvious that establishing quality evaluation models for cherry tomato juices based on the e-nose and e-tongue techniques is possible. The proposed spectral clustering offers a better approach to explore underlying structures of e-nose and e-tongue datasets; and based on this clustering approach, the semi-supervised cluster-then-lable approach could build a reliable classifier with only a few labeled training data. Meanwhile, with appropriate feacture extraction approaches, the fusion use of both instruements could be better than individual usage of the e-nose and e-tongue.
引文
[1]陈志明.我国鲜榨果汁消费与发展趋势[J].农产品加工,2005,1：12-14.
[2]Faria, M., Magalhaes, A., Nunes, M.,& Oliveira, M. (2013). High resolution melting of trnL amplicons in fruit juices authentication. Food Control,33(1),136-141.
[3]高利萍,王俊,崔绍庆.不同成熟度草莓鲜榨果汁的电子鼻和电子舌检测[J].浙江大学学报(农业与生命科学版),2012,38(6)：715-724.
[4]陈冬梅,周媛.电子舌技术及其在食品工业中的应用[J].现代农业科技,2010,7：26-29.
[5]Berna, A. Z., Lammertyn, J., Saevels, S., et al. Electronic nose systems to study shelf life and cultivar effect on tomato aroma profile [J]. Sensors and Actuators B:Chemical,2004,97(2): 324-333.
[6]Baldwin, E., Scott, J., Einstein, M., et al. Relationship between sensory and instrumental analysis for tomato flavor [J]. Journal of the American Society for Horticultural Science,1998, 123(5):906-915.
[7]Gardner J W, Bartlett P N. A brief history of electronic nose [J]. Sensors and Actuators B,1994, 18(19):211-220.
[8]Ciosek, P., Wróblewski, W. Performance of selective and partially selective sensors in the recognition of beverages [J]. Talanta,2007,71(2):738-746.
[9]Tian, S.Y., Deng, S.P., Chen, Z.X. Multifrequency large amplitude pulse voltammetry:a novel electrochemical method for electronic tongue [J]. Sensors and Actuators B,2007,123:1049-1056.
[10]Vlasov, Y.G., Legin, A.V., Rudnitskaya, A.M., et al. Electronic tongue-new analytical tool for liquid analysis on the basis of non-specific sensors and methods of pattern recognition [J]. Sensors and Actuators B,2000,65:235-236.
[11]Benady, M., Simon, J.E., Charles, D.J., et al. Fruit ripeness determination by electronic sensing of aromatic volatiles [J]. Transaction of the ASAE,1995,38:251-257.
[12]Oshita, S., Shima, K., Haruta, T., et al. Discrimination of odours emanating from 'La France' pear by semi-conducting polymer sensors [J]. Computer and Electronic in Agriculture,2000,26: 209-216.
[13]Saevels, S., Lammertyn, J., Berna, A.Z., et al. Electronic nose as a non-destructive tool to evaluate the optimal harvest date of apples [J]. Postharvest Biology Technology,2003,30:3-14.
[14]Zhang, H.M., Chang, M.X., Wang, J., et al. Evaluation of peach quality indices using an electronic nose by MLR, QPST and BP network [J]. Sensors and Actuators B:Chemical,2008, 134(1):332-338.
[15]Rebecca, N., Bleibaum, H.S., Tsung, T., et al. Comparison of sensory and consumer results with electronic nose and tongue sensors for apple juices [J]. Food Quality and Preference,2002,13: 409-422.
[16]Piroska H., Istvan D. Physical-chemical and sensory properties of pulsed electric field and high hydrostatic pressure treated citrus juices [J]. Innovative Food Science and Emerging Technologies,2011,12(3):1-21.
[17]Hans, R., Fritz, S., Otmar, Z. Citrus juice classification by SPME-GC-MS and electronic nose measurements [J]. LWT-Food Science and Technology,2008,41:1906-1912.
[18]Philip, E., Shaw, R.L., Rouseff, K.L., et al. Comparison of headspace GC and electronic sensor techniques for classication of processed orange juices [J]. LWT-Food Science and Technology, 2000,33(5):331-334.
[19]Persaud, K., Dodd, G. Analysis of discrimination mechanisms in the mammalian olfactory system using a model nose [J]. Nature,1982,299:352.
[20]James, D., Scott, S.M., Ali, Z., et al. Chemical sensors for electronic nose systems [J]. Microchemical Acta,2005,149(1-2):1-17.
[21]海铮.基于电子鼻的牛肉新鲜度检测：[硕士学位论文],浙江：浙江大学,2006.
[22]Yu, Y., Wang, J., Zhou, M. Research developments of electronic nose and its application in processing of agriculture products [J]. Journal of Zhejiang University:Agriculture & Life Sciences,2003,29(5):579-584. (in Chinese)
[23]洪雪珍,王俊,周博,等.猪肉储藏时间的电子鼻区分方法[J].浙江大学学报：农业与生命科学版,201,36(5)：568-572.
[24]Schmidt-Zhang, P., Zhang, W., Gerlach, F., et al. Electrochemical investigations on multi-metallic electrodes for amperometric NO gas sensors [J]. Sensors and Actuators B:Chemical,2005, 108(1):797-802.
[25]祝佳婧.电子鼻传感器技术的研制进展[J].北京生物医学工程,2002,21(4)：298-301.
[26]鲁小利.基于电子舌的黄酒品质检测：[硕士学位论文].浙江：浙江大学,2007.
[27]Ciosek, P., Brzozka, Z., Wroblewski, W. Classification of beverages using a reduced sensor array [J]. Sensors and Actuators B:Chemical,2004,103(1-2):76-83.
[28]Berna, A.Z., Lammertyn, J., Saevels, S. et al. Electronic nose systems to study shelf life and cultivar effect on tomato aroma profile [J]. Sensors and Actuators B:Chemical,2004,97(2-3): 324-333.
[29]周亦斌,王俊.基于电子鼻的番茄成熟度及贮藏时间评价的研究[J].农业工程学报,2005,21(4)：113-117.
[30]Dias, L.G., Peres, A.M., Barcelos, T.P., et al. Semi-quantitative and quantitative analysis of soft drinks using an electronic tongue [J]. Sensors and Actuators B:Chemical,2011,154(2):111-118.
[31]Cosio, M.S., Ballabio, D., Benedetti, S., et al. Evaluation of different storage conditions of extra virgin olive oils with an innovative recognition tool built by means of electronic nose and electronic tongue [J]. Food Chemistry,2007,101(2):485-491.
[32]Gil-Sanchez, L., Soto, J., Martinez-Mán(~)ez, R., et al. A novel humid electronic nose combined with an electronic tongue for assessing deterioration of wine [J]. Sensors and Actuators A: Physical,2001,171(2):152-158.
[33]Bleibaum, R. N., Stone, H., Tan, T., et al. Comparison of sensory and consumer results with electronic nose and tongue sensors for apple juices [J]. Food Quality and Preference,2002,13(6): 409-422.
[34]Buratti, S. Characterization and classification of Italian Barbera wines by using an electronic nose and amperometric electronic togue [J]. Analytica Chimica Acta,2004,525:133-139.
[35]Toko, K., Iyota, T., Mizota, Y., et al. Heat effect on the taste of milk studied using a taste sensor [J]. Japanese Journal of Applphys,1995,34:6287-6291.
[36][USDA] US Department of Agriculture. United States standards for grades of fresh tomatoes. 1997.
[37]Hong, X.Z., Wang, J. Detection of adulteration in cherry tomato juices based on electronic nose and tongue:comparison of different data fusion approaches [J]. Journal of Food Engineering, 2014,126:89-97.
[38]Brezmes, J., Ferreras, B., Llobet, E., et al. Neural network based electronic nose for the classification of aromatic species [J]. Analytica chimica acta,1997,348(1):503-509.
[39]贾洪雷,王增辉,马成林,等.玉米秸秆切碎抛送装置的试验研究[J].农业机械学报,2003,34(6)：96-99。
[40]Scott, S.M., James, D., Ali, Z. Data analysis for electronic nose systems [J]. Microchim Acta, 2006,156:183-207.
[41]Rokach, L., Maimon, O. Clustering methods, Data Mining and Knowledge Discovery Handbook, Springer,2005, pp.321-352。
[42]Almeida, J., Barbosa,L., Pais, A., et al. Improving hierarchical cluster analysis:A new method with outlier detection and automatic clustering [J]. Chemometrics and Intelligent Laboratory Systems,2007,87(2):208-217.
[43]Smolinski, A., Walczak, B., Einax, J. Hierarchical clustering extended with visual complements of environmental data set [J]. Chemometrics and Intelligent Laboratory Systems,2002,64: 45-54.
[44]Jain, A.K., Murty, M.N., Flynn, P.J. Data clustering:a review [J]. ACM Computer Survery,1999, 31:264-323.
[45]Tran, T.N., Wehrens, R., Buydens, L. SpaRef:a clustering algorithm for multispectral images [J]. Analytica Chimica Acta,2003,490(1):303-312.
[46]Steinbach, M., Ertoz, L., Kumar, V. The challenges of clustering high dimensional data, New Directions in Statistical Physics, Springer,2004, pp.273-309.
[47]Hervada-Sala, C, Jarauta-Bragulat, E. A program to perform Ward's clustering method on several regionalized variables [J]. Computers & geosciences,2004,30(8):881-886.
[48]Ward Jr, J. H. Hierarchical grouping to optimize an objective function [J]. Journal of the American statistical association,1963,58(301):236-244.
[49]Dhillon, I.S., Modha, D.S. Concept decompositions for large sparse text data using clustering [J]. Machine Learning,2001,42:143-175.
[50]Sabin, M. J. Convergence and consistency of fuzzy c-means/ISODATA algorithms [J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,1987, (5):661-668.
[51]Xia,T., Cao, J., Zhang, Y.-d., et al. On defining affinity graph for spectral clustering through ranking on manifolds [J]. Neurocomputing,2009,72:3203-3211.
[52]Nock, R., Vaillant, P., Henry, C, et al. Soft memberships for spectral clustering, with application to permeable language distinction [J]. Pattern Recognition,2009,42:43-53.
[53]Ducournau, A., Bretto, A., Rital, S., et al. A reductive approach to hypergraph clustering:An application to image segmentation [J]. Pattern Recognition,2012,45:2788-2803.
[54]Symeonidis, P., Iakovidou, N., Mantas, N. et al. From biological to social networks:Link prediction based on multi-way spectral clustering [J]. Data Knowledge. Eng.2013,87:226-242.
[55]Fujiwara, K., Kano, M., Hasebe, S. Correlation-based spectral clustering for flexible process monitoring. Journal of Process Control,2001,21(10):1438-1448.
[56]Yang, F., Grigsby, P. W. Delineation of FDG-PET tumors from heterogeneous background using spectral clustering. European journal of radiology,2012,81(11):3535-3541.
[57]Von Luxburg, U. A tutorial on spectral clustering [J]. Statistics and computing,2007,17(4): 395-416.
[58]Falasconi, M., Pardo, M., Vezzoli, M., et al. Cluster validation for electronic nose data. Sensors and Actuators B:Chemical,2007,125(2):596-606.
[59]Gómez, A.H., Wang, J., Hu, G. et al. Electronic nose technique potential monitoring mandarin maturity [J]. Sensors and Actuators B:Chemical,2006,113:347-353.
[60]Dragonieri, S., Brinkman, P., Mouw, E., et al. An electronic nose discriminates exhaled breath of patients with untreated pulmonary sarcoidosis from controls [J]. Respiratory medicine,2007, 107(7):1073-1078.
[61]Cerrato Oliveros, M. C, Pérez Pavón, J. L., Garcia Pinto, C., et al. Electronic nose based on metal oxide semiconductor sensors as a fast alternative for the detection of adulteration of virgin olive oils. Analytica Chimica Acta,2002,459(2):219-228.
[62]Buratti, S., Benedetti, S., Scampicchio, M., et al. Characterization and classification of Italian Barbera wines by using an electronic nose and an amperometric electronic tongue [J]. Analytica Chimica Acta,2004,525(1):133-139.
[63]Ballabio, D., Mauri, A., Todeschini, R, et al. Geographical classification of wine and olive oil by means of classification and influence matrix analysis (CAIMAN) [J]. Analytica chimica acta, 2006,570(2):249-258.
[64]Brudzewski, K., Osowski, S., Markiewicz, T. Classification of milk by means of an electronic nose and SVM neural network [J]. Sensors and Actuators B:Chemical,2004,98:291-298.
[65]Liu, M., Wang, M.J., Wang, J., et al. Comparison of random forest, support vector machine and back propagation neural network for electronic tongue data classification:Application to the recognition of orange beverage and Chinese vinegar [J]. Sensors and Actuators B:Chemical, 2012,177:970-980.
[66]Zhou, B., Wang, J. Discrimination of different types damage of rice plants by electronic nose [J]. Biosystems Engineering,2011,109 (4):250-257.
[67]Tian, X., Wang, J., Cui, S. Analysis of pork adulteration in minced mutton using electronic nose of metal oxide sensors [J]. Journal of Food Engineering,2013,119(4):744-749.
[68]Hong, X.Z., Wang, J., Hai, Z. Discrimination and prediction of multiple beef freshness indexes based on electronic nose [J]. Sensors and Actuators B:Chemical,2012,16:381-389.
[69]Tudu, B., Shaw, L., Jana, A., et al. Instrumental testing of tea by combining the responses of electronic nose and tongue [J]. Journal of food engineering,2012,110(3):356-363.
[70]Hou, C, Lei, J., Huo, D., et al. Discrimination of lung cancer related volatile organic compounds with a colorimetric sensor array [J]. Analytical Letters,2013,46(13):2048-2059.
[71]周红标,张新荣,耿忠华.基于遗传小波神经网络的白酒识别电子鼻[J].计算机工程与应用,2013,05：254-257.
[72]Lozano, J., Santos, J. P., Horrillo, M. C. Classification of white wine aromas with an electronic nose. Talanta,2005,67(3):610-616.
[73]Oliveri, P., Casale, M., Casolino, M. C., et al. Comparison between classical and innovative class-modelling techniques for the characterisation of a PDO olive oil [J]. Analytical and bioanalytical chemistry,2011,399(6):2105-2113.
[74]Wu, W., Mallet, Y., Walczak, B., et al. Comparison of regularized discriminant analysis linear discriminant analysis and quadratic discriminant analysis applied to NIR data [J]. Analytica Chimica Acta,1996,329(3):257-265.
[75]陈晓琴.基于概率神经网络的潜在客户数据挖掘应用研究：[博士学位论文].重庆：重庆交通大学,2011.
[76]Unay, D., Gosselin, B. Automatic defect segmentation of 'Jonagold'apples on multi-spectral images:A comparative study [J]. Postharvest Biology and Technology,2006,42(3):271-279.
[77]Gómez-Sanchis, J., Blasco, J., Soria-Olivas, E., et al. Hyperspectral LCTF-based system for classification of decay in mandarins caused by Penicillium digitatum and Penicillium italicum using the most relevant bands and non-linear classifiers [J]. Postharvest Biology and Technology, 2012,82:76-86.
[78]Wei, Z., Wang, J. Detection of antibiotic residues in bovine milk by a voltammetric electronic tongue system [J]. Analytica Chimica Acta,2012,694(1):46-56.
[79]Brudzewski, K., Osowski, S., Markiewicz, T. Classification of milk by means of an electronic nose and SVM neural network [J]. Sensors and Actuators B:Chemical,2014,98(2):291-298.
[80]Szollo(＂)si, D., Denes, D. L., Firtha, F., et al. Comparison of six multiclass classifiers by the use of different classification performance indicators [J]. Journal of Chemometrics,2012,26(3-4): 76-84.
[81]Broadhurst, D., Goodacre, R., Jones, A., et al. Genetic algorithms as a method for variable selection in multiple linear regression and partial least squares regression, with applications to pyrolysis mass spectrometry [J]. Analytica Chimica Acta,1997,348(1):71-86.
[82]何晓群,刘文卿.应用回归分析[M].北京：中国人民大学出版社,2011.
[83]Depczynski, U., Frost, V., Molt, K. Genetic algorithms applied to the selection of factors in principal component regression [J]. Analytica Chimica Acta,2000,420:217-27.
[84]Smola, A J., Scholkopf, B. A tutorial on support vector regression [J]. Statistics and computing, 2004,14(3):199-222.
[85]Zhu, X., Goldberg, A.B. Introduction to semi-supervised learning, Synthesis lectures on artificial intelligence and machine learning 3 (2009) 1-130.
[86]Ciosek, P., Brzózka, Z., Wróblewski, W. Classification of beverages using a reduced sensor array [J]. Sensors and Actuators B:Chemical,2004,103(1):76-83.
[87]Derksen, S., Keselman, H. Backward, forward and stepwise automated subset selection algorithms:Frequency of obtaining authentic and noise variables [J]. British Journal of Mathematical and Statistical Psychology,1992,45(2):265-282.
[88]Estivill-Castro, V., Yang, J. A Fast and robust general purpose clustering algorithm. Pacific Rim International Conference on Artificial Intelligence, pp.208-218,2000.
[89]Falasconi, M., Pardo, M., Vezzoli, M., et al. Cluster validation for electronic nose data [J]. Sensors and Actuators B:Chemical,2007,125(2):596-606.
[90]M. Penza, G. Cassano, F. Tortorella, G. Zaccaria, Classification of food, beverages and perfumes by WO3 thin-film sensors array and pattern recognition techniques [J]. Sensors and Actuators B: Chemical,2001,73:76-87.
[91]Zhang, Q., Zhang, S., Xie, C, et al. Characterization of Chinese vinegars by electronic nose [J]. Sensors and Actuators B:Chemical,2006,119(2):538-546.
[92]Yang, Z., Dong, F., Shimizu, K., et al. Identification of coumarin-enriched Japanese green teas and their particular flavor using electronic nose [J]. Journal of food engineering,2009,92(3): 312-316.
[93]Liu, M., Han, X., Tu, K., et al. Application of electronic nose in Chinese spirits quality control and flavour assessment [J]. Food Control,2012,26(2):564-570.
[94]Zhou, B., Wang, J. Discrimination of different types damage of rice plants by electronic nose [J]. Biosystem Engineering,2011,109:250-257.
[95]Yu, H., Wang, J., Yao, C, et al. Quality grade identification of green tea using E-nose by CA and ANN [J]. LWT-Food Science and Technology,2008,41(7):1268-1273.
[96]Lopez de Lerma, N., Bellincontro, A., Mencarelli, F., et al. Use of electronic nose, validated by GC-MS, to establish the optimum off-vine dehydration time of wine grapes [J]. Food Chemistry, 2012,130(2):447-452.
[97]Fend, R., Bessant, C., Williams, A. J., et al. Monitoring haemodialysis using electronic nose and chemometrics [J]. Biosensors and Bioelectronics,2004,19(12):1581-1590.
[98]Sahgal, N., Magan, N. Fungal volatile fingerprints:discrimination between dermatophyte species and strains by means of an electronic nose [J]. Sensors and Actuators B:Chemical,2008,131(1): 117-120.
[99]Berna, A. Z., Lammertyn, J., Buysens, S., et al. Mapping consumer liking of tomatoes with fast aroma profiling techniques [J]. Postharvest biology and technology,2005,38(2):115-127.
[100]Naraghi, K., Sahgal, N., Adriaans, B., et al. Use of volatile fingerprints for rapid screening of antifungal agents for efficacy against dermatophyte Trichophyton species [J]. Sensors and Actuators B:Chemical,2010,146(2):521-526.
[101]Guadarrama, A., Rodnguez-Mendez, M. L., De Saja, J. A. Conducting polymer-based array for the discrimination of odours from trim plastic materials used in automobiles [J]. Analytica ChimicaActa,2002,455(1):41-47.
[102]Li, C., Krewer, G. W., Ji, P., et al. Gas sensor array for blueberry fruit disease detection and classification [J]. Postharvest biology and technology,2010,55(3):144-149.
[103]Drake, M. A., Gerard, P. D., Kleinhenz, J. P., et al. Application of an electronic nose to correlate with descriptive sensory analysis of aged Cheddar cheese [J]. LWT-Food Science and Technology,2003,36(1):13-20.
[104]Feng, T., Zhuang, H., Ye, R., et al. Analysis of volatile compounds of Mesona Blumes gum/rice extrudates via GC-MS and electronic nose [J]. Sensors and Actuators B:Chemical,2011, 160(1):964-973.
[105]Canhoto, O., Pinzari, F., Fanelli, C., et al. Application of electronic nose technology for the detection of fungal contamination in library paper [J]. International biodeterioration & biodegradation,2004,54(4):303-309.
[106]Alizadeh, T. Chemiresistor sensors array optimization by using the method of coupled statistical techniques and its application as an electronic nose for some organic vapors recognition [J]. Sensors and Actuators B:Chemical,2010,143:740-749.
[107]Canhoto, O., Magan, N. Electronic nose technology for the detection of microbial and chemical contamination of potable water [J]. Sensors and Actuators B:Chemical,2005,106:3-6.
[108]Mensing, J. P., Wisitsoraat, A., Tuantranont, A., et al. Inkjet-printed sol-gel films containing metal phthalocyanines/porphyrins for opto-electronic nose applications [J]. Sensors and Actuators B:Chemical,2013,176:428-436.
[109]Needham, R., Williams, J., Beales, N., et al. Early detection and differentiation of spoilage of bakery products [J]. Sensors and Actuators B:Chemical,2005,106(1):20-23.
[110]Haddi, Z., Alarm, H., El Bari, N., et al. Electronic nose and tongue combination for improved classification of Moroccan virgin olive oil profiles [J]. Food Research International,2013,54(2): 1488-1498.
[111]Wei, Z.B., Wang, J. Classification of monofloral honeys by voltammetric electronic tongue with chemometrics method [J]. Electrochimica Acta,2011,56(13):4907-4915.
[112]Tian, X., Wang, J., Zhang, X. Discrimination of preserved licorice apricot using electronic tongue [J]. Mathematical and Computer Modelling,2013,58(3):743-751.
[113]Wei, Z., Wang, J., Zhang, X. Monitoring of quality and storage time of unsealed pasteurized milk by voltammetric electronic tongue [J]. Electrochimica Acta,2013,88:231-239.
[114]Wei, Z., Wang, J., Ye, L. Classification and prediction of rice wines with different marked ages by using a voltammetric electronic tongue [J]. Biosensors and Bioelectronics,2011,26(12): 4767-4773.
[115]Wei, Z., Wang, J., Liao, W. Technique potential for classification of honey by electronic tongue [J]. Journal of food engineering,2009,94(3):260-266.
[116]Bueno, L., Paixao, T. R. A copper interdigitated electrode and chemometrical tools used for the discrimination of the adulteration of ethanol fuel with water [J]. Talanta,2011,87:210-215.
[117]Riul Jr, A., de Sousa, H. C., Malmegrim, R. R. Wine classification by taste sensors made from ultra-thin films and using neural networks [J]. Sensors and Actuators B:Chemical,2004,98(1): 77-82.
[118]Salles, M. O., Bertotti, M., Paixao, T. R. Use of a gold microelectrode for discrimination of gunshot residues [J]. Sensors and Actuators B:Chemical,2012,166:848-852.
[119]Heras, J. Y., Pallarola, D., Battaglini, F. Electronic tongue for simultaneous detection of endotoxins and other contaminants of microbiological origin [J]. Biosensors and Bioelectronics, 2010,25(11):2470-2476.
[120]Rodriguez, S. D., Monge, M. E., Olivieri, A. C., et al. Time dependence of the aroma pattern emitted by an encapsulated essence studied by means of electronic noses and chemometric analysis [J]. Food research international,2010,43(3):797-804.
[121]Snopok, B. A., Kruglenko, I. V. Nonexponential relaxations in sensor arrays:forecasting strategy for electronic nose performance [J]. Sensors and Actuators B:chemical,2005,106(1): 101-113.
[122]Iliev, B., Lindquist, M., Robertsson, L., et al. A fuzzy technique for food-and water quality assessment with an electronic tongue. Fuzzy Sets and Systems,2006,157(9):1155-1168.
[123]Wilson, D. M., Dunman, K., Roppel, T., et al. Rank extraction in tin-oxide sensor arrays [J]. Sensors and Actuators B:Chemical,2000,62(3):199-210.
[124]Wehrens, R., Putter, H., Buydens, L. The bootstrap:a tutorial. Chemometrics and intelligent laboratory systems,2000,54(1):35-52.
[125]Raffo, A., Leonardi, C., Fogliano, V., et al. Nutritional value of cherry tomatoes (Lycopersicon esculentum cv. Naomi F1) harvested at different ripening stages [J]. Journal of Agricultural and Food Chemistry,2002,50(22):6550-6556.
[126]Reinhard, H., Sager, F., Zoller, O. Citrus juice classification by SPME-GC-MS and electronic nose measurements [J]. LWT-Food Science and Technology,2008,10(41):1906-1912.
[127]Gomez, A. H., Wang, J., Hu, G., et al. Monitoring storage shelf life of tomato using electronic nose technique [J]. Journal of Food Engineering,2008,85(4):625-631.
[128]Cole, M., Covington, J. A., Gardner, J. W. Combined electronic nose and tongue for a flavour sensing system [J]. Sensors and Actuators B:Chemical,2011,156(2:832-839.
[129]Gomez-Sanchis, J., Blasco, J., Soria-Olivas, E., et al. Hyperspectral LCTF-based system for classification of decay in mandarins caused by Penicillium digitatum and Penicillium italicum using the most relevant bands and non-linear classifiers [J]. Postharvest Biology and Technology,2013,82:76-86.
[130]Di Natale, C., Macagnano, A., Martinelli, E., et al. The evaluation of quality of post-harvest oranges and apples by means of an electronic nose [J]. Sensors and Actuators B:Chemical, 2011,78(1):26-31.
[131]Kantor, D. B., Hitka, G., Fekete, A., et al. Electronic tongue for sensing taste changes with apricots during storage [J]. Sensors and Actuators B:Chemical,2008,131(1):43-47.
[132]Torri, L., Sinelli, N., Limbo, S. Shelf life evaluation of fresh-cut pineapple by using an electronic nose [J]. Postharvest Biology and Technology,2011,56(3):239-245.
[133]Di Natale, C., Paolesse, R., Macagnano, A., et al. Electronic nose and electronic tongue integration for improved classification of clinical and food samples [J]. Sensors and Actuators B:Chemical,2000,64(1):15-21.
[134]Cole, M., Covington, J. A., Gardner, J. W. Combined electronic nose and tongue for a flavour sensing system [J]. Sensors and Actuators B:Chemical,2011,156(2):832-839.
[135]Tudu, B., Shaw, L., Jana, A., et al. Instrumental testing of tea by combining the responses of electronic nose and tongue [J]. Journal of Food Engineering,2012,110(3):356-363.
[136]Cosio, M. S., Ballabio, D., Benedetti, S., et al. Evaluation of different storage conditions of extra virgin olive oils with an innovative recognition tool built by means of electronic nose and electronic tongue [J]. Food Chemistry,2007,101(2):485-491.
[137]Gan, H., Sang, N., Huang, R., et al. Using clustering analysis to improve semi-supervised classification [J]. Neurocomputing,2013,101:290-298
[2]Faria, M., Magalhaes, A., Nunes, M.,& Oliveira, M. (2013). High resolution melting of trnL amplicons in fruit juices authentication. Food Control,33(1),136-141.
[3]高利萍,王俊,崔绍庆.不同成熟度草莓鲜榨果汁的电子鼻和电子舌检测[J].浙江大学学报(农业与生命科学版),2012,38(6)：715-724.
[4]陈冬梅,周媛.电子舌技术及其在食品工业中的应用[J].现代农业科技,2010,7：26-29.
[5]Berna, A. Z., Lammertyn, J., Saevels, S., et al. Electronic nose systems to study shelf life and cultivar effect on tomato aroma profile [J]. Sensors and Actuators B:Chemical,2004,97(2): 324-333.
[6]Baldwin, E., Scott, J., Einstein, M., et al. Relationship between sensory and instrumental analysis for tomato flavor [J]. Journal of the American Society for Horticultural Science,1998, 123(5):906-915.
[7]Gardner J W, Bartlett P N. A brief history of electronic nose [J]. Sensors and Actuators B,1994, 18(19):211-220.
[8]Ciosek, P., Wróblewski, W. Performance of selective and partially selective sensors in the recognition of beverages [J]. Talanta,2007,71(2):738-746.
[9]Tian, S.Y., Deng, S.P., Chen, Z.X. Multifrequency large amplitude pulse voltammetry:a novel electrochemical method for electronic tongue [J]. Sensors and Actuators B,2007,123:1049-1056.
[10]Vlasov, Y.G., Legin, A.V., Rudnitskaya, A.M., et al. Electronic tongue-new analytical tool for liquid analysis on the basis of non-specific sensors and methods of pattern recognition [J]. Sensors and Actuators B,2000,65:235-236.
[11]Benady, M., Simon, J.E., Charles, D.J., et al. Fruit ripeness determination by electronic sensing of aromatic volatiles [J]. Transaction of the ASAE,1995,38:251-257.
[12]Oshita, S., Shima, K., Haruta, T., et al. Discrimination of odours emanating from 'La France' pear by semi-conducting polymer sensors [J]. Computer and Electronic in Agriculture,2000,26: 209-216.
[13]Saevels, S., Lammertyn, J., Berna, A.Z., et al. Electronic nose as a non-destructive tool to evaluate the optimal harvest date of apples [J]. Postharvest Biology Technology,2003,30:3-14.
[14]Zhang, H.M., Chang, M.X., Wang, J., et al. Evaluation of peach quality indices using an electronic nose by MLR, QPST and BP network [J]. Sensors and Actuators B:Chemical,2008, 134(1):332-338.
[15]Rebecca, N., Bleibaum, H.S., Tsung, T., et al. Comparison of sensory and consumer results with electronic nose and tongue sensors for apple juices [J]. Food Quality and Preference,2002,13: 409-422.
[16]Piroska H., Istvan D. Physical-chemical and sensory properties of pulsed electric field and high hydrostatic pressure treated citrus juices [J]. Innovative Food Science and Emerging Technologies,2011,12(3):1-21.
[17]Hans, R., Fritz, S., Otmar, Z. Citrus juice classification by SPME-GC-MS and electronic nose measurements [J]. LWT-Food Science and Technology,2008,41:1906-1912.
[18]Philip, E., Shaw, R.L., Rouseff, K.L., et al. Comparison of headspace GC and electronic sensor techniques for classication of processed orange juices [J]. LWT-Food Science and Technology, 2000,33(5):331-334.
[19]Persaud, K., Dodd, G. Analysis of discrimination mechanisms in the mammalian olfactory system using a model nose [J]. Nature,1982,299:352.
[20]James, D., Scott, S.M., Ali, Z., et al. Chemical sensors for electronic nose systems [J]. Microchemical Acta,2005,149(1-2):1-17.
[21]海铮.基于电子鼻的牛肉新鲜度检测：[硕士学位论文],浙江：浙江大学,2006.
[22]Yu, Y., Wang, J., Zhou, M. Research developments of electronic nose and its application in processing of agriculture products [J]. Journal of Zhejiang University:Agriculture & Life Sciences,2003,29(5):579-584. (in Chinese)
[23]洪雪珍,王俊,周博,等.猪肉储藏时间的电子鼻区分方法[J].浙江大学学报：农业与生命科学版,201,36(5)：568-572.
[24]Schmidt-Zhang, P., Zhang, W., Gerlach, F., et al. Electrochemical investigations on multi-metallic electrodes for amperometric NO gas sensors [J]. Sensors and Actuators B:Chemical,2005, 108(1):797-802.
[25]祝佳婧.电子鼻传感器技术的研制进展[J].北京生物医学工程,2002,21(4)：298-301.
[26]鲁小利.基于电子舌的黄酒品质检测：[硕士学位论文].浙江：浙江大学,2007.
[27]Ciosek, P., Brzozka, Z., Wroblewski, W. Classification of beverages using a reduced sensor array [J]. Sensors and Actuators B:Chemical,2004,103(1-2):76-83.
[28]Berna, A.Z., Lammertyn, J., Saevels, S. et al. Electronic nose systems to study shelf life and cultivar effect on tomato aroma profile [J]. Sensors and Actuators B:Chemical,2004,97(2-3): 324-333.
[29]周亦斌,王俊.基于电子鼻的番茄成熟度及贮藏时间评价的研究[J].农业工程学报,2005,21(4)：113-117.
[30]Dias, L.G., Peres, A.M., Barcelos, T.P., et al. Semi-quantitative and quantitative analysis of soft drinks using an electronic tongue [J]. Sensors and Actuators B:Chemical,2011,154(2):111-118.
[31]Cosio, M.S., Ballabio, D., Benedetti, S., et al. Evaluation of different storage conditions of extra virgin olive oils with an innovative recognition tool built by means of electronic nose and electronic tongue [J]. Food Chemistry,2007,101(2):485-491.
[32]Gil-Sanchez, L., Soto, J., Martinez-Mán(~)ez, R., et al. A novel humid electronic nose combined with an electronic tongue for assessing deterioration of wine [J]. Sensors and Actuators A: Physical,2001,171(2):152-158.
[33]Bleibaum, R. N., Stone, H., Tan, T., et al. Comparison of sensory and consumer results with electronic nose and tongue sensors for apple juices [J]. Food Quality and Preference,2002,13(6): 409-422.
[34]Buratti, S. Characterization and classification of Italian Barbera wines by using an electronic nose and amperometric electronic togue [J]. Analytica Chimica Acta,2004,525:133-139.
[35]Toko, K., Iyota, T., Mizota, Y., et al. Heat effect on the taste of milk studied using a taste sensor [J]. Japanese Journal of Applphys,1995,34:6287-6291.
[36][USDA] US Department of Agriculture. United States standards for grades of fresh tomatoes. 1997.
[37]Hong, X.Z., Wang, J. Detection of adulteration in cherry tomato juices based on electronic nose and tongue:comparison of different data fusion approaches [J]. Journal of Food Engineering, 2014,126:89-97.
[38]Brezmes, J., Ferreras, B., Llobet, E., et al. Neural network based electronic nose for the classification of aromatic species [J]. Analytica chimica acta,1997,348(1):503-509.
[39]贾洪雷,王增辉,马成林,等.玉米秸秆切碎抛送装置的试验研究[J].农业机械学报,2003,34(6)：96-99。
[40]Scott, S.M., James, D., Ali, Z. Data analysis for electronic nose systems [J]. Microchim Acta, 2006,156:183-207.
[41]Rokach, L., Maimon, O. Clustering methods, Data Mining and Knowledge Discovery Handbook, Springer,2005, pp.321-352。
[42]Almeida, J., Barbosa,L., Pais, A., et al. Improving hierarchical cluster analysis:A new method with outlier detection and automatic clustering [J]. Chemometrics and Intelligent Laboratory Systems,2007,87(2):208-217.
[43]Smolinski, A., Walczak, B., Einax, J. Hierarchical clustering extended with visual complements of environmental data set [J]. Chemometrics and Intelligent Laboratory Systems,2002,64: 45-54.
[44]Jain, A.K., Murty, M.N., Flynn, P.J. Data clustering:a review [J]. ACM Computer Survery,1999, 31:264-323.
[45]Tran, T.N., Wehrens, R., Buydens, L. SpaRef:a clustering algorithm for multispectral images [J]. Analytica Chimica Acta,2003,490(1):303-312.
[46]Steinbach, M., Ertoz, L., Kumar, V. The challenges of clustering high dimensional data, New Directions in Statistical Physics, Springer,2004, pp.273-309.
[47]Hervada-Sala, C, Jarauta-Bragulat, E. A program to perform Ward's clustering method on several regionalized variables [J]. Computers & geosciences,2004,30(8):881-886.
[48]Ward Jr, J. H. Hierarchical grouping to optimize an objective function [J]. Journal of the American statistical association,1963,58(301):236-244.
[49]Dhillon, I.S., Modha, D.S. Concept decompositions for large sparse text data using clustering [J]. Machine Learning,2001,42:143-175.
[50]Sabin, M. J. Convergence and consistency of fuzzy c-means/ISODATA algorithms [J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,1987, (5):661-668.
[51]Xia,T., Cao, J., Zhang, Y.-d., et al. On defining affinity graph for spectral clustering through ranking on manifolds [J]. Neurocomputing,2009,72:3203-3211.
[52]Nock, R., Vaillant, P., Henry, C, et al. Soft memberships for spectral clustering, with application to permeable language distinction [J]. Pattern Recognition,2009,42:43-53.
[53]Ducournau, A., Bretto, A., Rital, S., et al. A reductive approach to hypergraph clustering:An application to image segmentation [J]. Pattern Recognition,2012,45:2788-2803.
[54]Symeonidis, P., Iakovidou, N., Mantas, N. et al. From biological to social networks:Link prediction based on multi-way spectral clustering [J]. Data Knowledge. Eng.2013,87:226-242.
[55]Fujiwara, K., Kano, M., Hasebe, S. Correlation-based spectral clustering for flexible process monitoring. Journal of Process Control,2001,21(10):1438-1448.
[56]Yang, F., Grigsby, P. W. Delineation of FDG-PET tumors from heterogeneous background using spectral clustering. European journal of radiology,2012,81(11):3535-3541.
[57]Von Luxburg, U. A tutorial on spectral clustering [J]. Statistics and computing,2007,17(4): 395-416.
[58]Falasconi, M., Pardo, M., Vezzoli, M., et al. Cluster validation for electronic nose data. Sensors and Actuators B:Chemical,2007,125(2):596-606.
[59]Gómez, A.H., Wang, J., Hu, G. et al. Electronic nose technique potential monitoring mandarin maturity [J]. Sensors and Actuators B:Chemical,2006,113:347-353.
[60]Dragonieri, S., Brinkman, P., Mouw, E., et al. An electronic nose discriminates exhaled breath of patients with untreated pulmonary sarcoidosis from controls [J]. Respiratory medicine,2007, 107(7):1073-1078.
[61]Cerrato Oliveros, M. C, Pérez Pavón, J. L., Garcia Pinto, C., et al. Electronic nose based on metal oxide semiconductor sensors as a fast alternative for the detection of adulteration of virgin olive oils. Analytica Chimica Acta,2002,459(2):219-228.
[62]Buratti, S., Benedetti, S., Scampicchio, M., et al. Characterization and classification of Italian Barbera wines by using an electronic nose and an amperometric electronic tongue [J]. Analytica Chimica Acta,2004,525(1):133-139.
[63]Ballabio, D., Mauri, A., Todeschini, R, et al. Geographical classification of wine and olive oil by means of classification and influence matrix analysis (CAIMAN) [J]. Analytica chimica acta, 2006,570(2):249-258.
[64]Brudzewski, K., Osowski, S., Markiewicz, T. Classification of milk by means of an electronic nose and SVM neural network [J]. Sensors and Actuators B:Chemical,2004,98:291-298.
[65]Liu, M., Wang, M.J., Wang, J., et al. Comparison of random forest, support vector machine and back propagation neural network for electronic tongue data classification:Application to the recognition of orange beverage and Chinese vinegar [J]. Sensors and Actuators B:Chemical, 2012,177:970-980.
[66]Zhou, B., Wang, J. Discrimination of different types damage of rice plants by electronic nose [J]. Biosystems Engineering,2011,109 (4):250-257.
[67]Tian, X., Wang, J., Cui, S. Analysis of pork adulteration in minced mutton using electronic nose of metal oxide sensors [J]. Journal of Food Engineering,2013,119(4):744-749.
[68]Hong, X.Z., Wang, J., Hai, Z. Discrimination and prediction of multiple beef freshness indexes based on electronic nose [J]. Sensors and Actuators B:Chemical,2012,16:381-389.
[69]Tudu, B., Shaw, L., Jana, A., et al. Instrumental testing of tea by combining the responses of electronic nose and tongue [J]. Journal of food engineering,2012,110(3):356-363.
[70]Hou, C, Lei, J., Huo, D., et al. Discrimination of lung cancer related volatile organic compounds with a colorimetric sensor array [J]. Analytical Letters,2013,46(13):2048-2059.
[71]周红标,张新荣,耿忠华.基于遗传小波神经网络的白酒识别电子鼻[J].计算机工程与应用,2013,05：254-257.
[72]Lozano, J., Santos, J. P., Horrillo, M. C. Classification of white wine aromas with an electronic nose. Talanta,2005,67(3):610-616.
[73]Oliveri, P., Casale, M., Casolino, M. C., et al. Comparison between classical and innovative class-modelling techniques for the characterisation of a PDO olive oil [J]. Analytical and bioanalytical chemistry,2011,399(6):2105-2113.
[74]Wu, W., Mallet, Y., Walczak, B., et al. Comparison of regularized discriminant analysis linear discriminant analysis and quadratic discriminant analysis applied to NIR data [J]. Analytica Chimica Acta,1996,329(3):257-265.
[75]陈晓琴.基于概率神经网络的潜在客户数据挖掘应用研究：[博士学位论文].重庆：重庆交通大学,2011.
[76]Unay, D., Gosselin, B. Automatic defect segmentation of 'Jonagold'apples on multi-spectral images:A comparative study [J]. Postharvest Biology and Technology,2006,42(3):271-279.
[77]Gómez-Sanchis, J., Blasco, J., Soria-Olivas, E., et al. Hyperspectral LCTF-based system for classification of decay in mandarins caused by Penicillium digitatum and Penicillium italicum using the most relevant bands and non-linear classifiers [J]. Postharvest Biology and Technology, 2012,82:76-86.
[78]Wei, Z., Wang, J. Detection of antibiotic residues in bovine milk by a voltammetric electronic tongue system [J]. Analytica Chimica Acta,2012,694(1):46-56.
[79]Brudzewski, K., Osowski, S., Markiewicz, T. Classification of milk by means of an electronic nose and SVM neural network [J]. Sensors and Actuators B:Chemical,2014,98(2):291-298.
[80]Szollo(＂)si, D., Denes, D. L., Firtha, F., et al. Comparison of six multiclass classifiers by the use of different classification performance indicators [J]. Journal of Chemometrics,2012,26(3-4): 76-84.
[81]Broadhurst, D., Goodacre, R., Jones, A., et al. Genetic algorithms as a method for variable selection in multiple linear regression and partial least squares regression, with applications to pyrolysis mass spectrometry [J]. Analytica Chimica Acta,1997,348(1):71-86.
[82]何晓群,刘文卿.应用回归分析[M].北京：中国人民大学出版社,2011.
[83]Depczynski, U., Frost, V., Molt, K. Genetic algorithms applied to the selection of factors in principal component regression [J]. Analytica Chimica Acta,2000,420:217-27.
[84]Smola, A J., Scholkopf, B. A tutorial on support vector regression [J]. Statistics and computing, 2004,14(3):199-222.
[85]Zhu, X., Goldberg, A.B. Introduction to semi-supervised learning, Synthesis lectures on artificial intelligence and machine learning 3 (2009) 1-130.
[86]Ciosek, P., Brzózka, Z., Wróblewski, W. Classification of beverages using a reduced sensor array [J]. Sensors and Actuators B:Chemical,2004,103(1):76-83.
[87]Derksen, S., Keselman, H. Backward, forward and stepwise automated subset selection algorithms:Frequency of obtaining authentic and noise variables [J]. British Journal of Mathematical and Statistical Psychology,1992,45(2):265-282.
[88]Estivill-Castro, V., Yang, J. A Fast and robust general purpose clustering algorithm. Pacific Rim International Conference on Artificial Intelligence, pp.208-218,2000.
[89]Falasconi, M., Pardo, M., Vezzoli, M., et al. Cluster validation for electronic nose data [J]. Sensors and Actuators B:Chemical,2007,125(2):596-606.
[90]M. Penza, G. Cassano, F. Tortorella, G. Zaccaria, Classification of food, beverages and perfumes by WO3 thin-film sensors array and pattern recognition techniques [J]. Sensors and Actuators B: Chemical,2001,73:76-87.
[91]Zhang, Q., Zhang, S., Xie, C, et al. Characterization of Chinese vinegars by electronic nose [J]. Sensors and Actuators B:Chemical,2006,119(2):538-546.
[92]Yang, Z., Dong, F., Shimizu, K., et al. Identification of coumarin-enriched Japanese green teas and their particular flavor using electronic nose [J]. Journal of food engineering,2009,92(3): 312-316.
[93]Liu, M., Han, X., Tu, K., et al. Application of electronic nose in Chinese spirits quality control and flavour assessment [J]. Food Control,2012,26(2):564-570.
[94]Zhou, B., Wang, J. Discrimination of different types damage of rice plants by electronic nose [J]. Biosystem Engineering,2011,109:250-257.
[95]Yu, H., Wang, J., Yao, C, et al. Quality grade identification of green tea using E-nose by CA and ANN [J]. LWT-Food Science and Technology,2008,41(7):1268-1273.
[96]Lopez de Lerma, N., Bellincontro, A., Mencarelli, F., et al. Use of electronic nose, validated by GC-MS, to establish the optimum off-vine dehydration time of wine grapes [J]. Food Chemistry, 2012,130(2):447-452.
[97]Fend, R., Bessant, C., Williams, A. J., et al. Monitoring haemodialysis using electronic nose and chemometrics [J]. Biosensors and Bioelectronics,2004,19(12):1581-1590.
[98]Sahgal, N., Magan, N. Fungal volatile fingerprints:discrimination between dermatophyte species and strains by means of an electronic nose [J]. Sensors and Actuators B:Chemical,2008,131(1): 117-120.
[99]Berna, A. Z., Lammertyn, J., Buysens, S., et al. Mapping consumer liking of tomatoes with fast aroma profiling techniques [J]. Postharvest biology and technology,2005,38(2):115-127.
[100]Naraghi, K., Sahgal, N., Adriaans, B., et al. Use of volatile fingerprints for rapid screening of antifungal agents for efficacy against dermatophyte Trichophyton species [J]. Sensors and Actuators B:Chemical,2010,146(2):521-526.
[101]Guadarrama, A., Rodnguez-Mendez, M. L., De Saja, J. A. Conducting polymer-based array for the discrimination of odours from trim plastic materials used in automobiles [J]. Analytica ChimicaActa,2002,455(1):41-47.
[102]Li, C., Krewer, G. W., Ji, P., et al. Gas sensor array for blueberry fruit disease detection and classification [J]. Postharvest biology and technology,2010,55(3):144-149.
[103]Drake, M. A., Gerard, P. D., Kleinhenz, J. P., et al. Application of an electronic nose to correlate with descriptive sensory analysis of aged Cheddar cheese [J]. LWT-Food Science and Technology,2003,36(1):13-20.
[104]Feng, T., Zhuang, H., Ye, R., et al. Analysis of volatile compounds of Mesona Blumes gum/rice extrudates via GC-MS and electronic nose [J]. Sensors and Actuators B:Chemical,2011, 160(1):964-973.
[105]Canhoto, O., Pinzari, F., Fanelli, C., et al. Application of electronic nose technology for the detection of fungal contamination in library paper [J]. International biodeterioration & biodegradation,2004,54(4):303-309.
[106]Alizadeh, T. Chemiresistor sensors array optimization by using the method of coupled statistical techniques and its application as an electronic nose for some organic vapors recognition [J]. Sensors and Actuators B:Chemical,2010,143:740-749.
[107]Canhoto, O., Magan, N. Electronic nose technology for the detection of microbial and chemical contamination of potable water [J]. Sensors and Actuators B:Chemical,2005,106:3-6.
[108]Mensing, J. P., Wisitsoraat, A., Tuantranont, A., et al. Inkjet-printed sol-gel films containing metal phthalocyanines/porphyrins for opto-electronic nose applications [J]. Sensors and Actuators B:Chemical,2013,176:428-436.
[109]Needham, R., Williams, J., Beales, N., et al. Early detection and differentiation of spoilage of bakery products [J]. Sensors and Actuators B:Chemical,2005,106(1):20-23.
[110]Haddi, Z., Alarm, H., El Bari, N., et al. Electronic nose and tongue combination for improved classification of Moroccan virgin olive oil profiles [J]. Food Research International,2013,54(2): 1488-1498.
[111]Wei, Z.B., Wang, J. Classification of monofloral honeys by voltammetric electronic tongue with chemometrics method [J]. Electrochimica Acta,2011,56(13):4907-4915.
[112]Tian, X., Wang, J., Zhang, X. Discrimination of preserved licorice apricot using electronic tongue [J]. Mathematical and Computer Modelling,2013,58(3):743-751.
[113]Wei, Z., Wang, J., Zhang, X. Monitoring of quality and storage time of unsealed pasteurized milk by voltammetric electronic tongue [J]. Electrochimica Acta,2013,88:231-239.
[114]Wei, Z., Wang, J., Ye, L. Classification and prediction of rice wines with different marked ages by using a voltammetric electronic tongue [J]. Biosensors and Bioelectronics,2011,26(12): 4767-4773.
[115]Wei, Z., Wang, J., Liao, W. Technique potential for classification of honey by electronic tongue [J]. Journal of food engineering,2009,94(3):260-266.
[116]Bueno, L., Paixao, T. R. A copper interdigitated electrode and chemometrical tools used for the discrimination of the adulteration of ethanol fuel with water [J]. Talanta,2011,87:210-215.
[117]Riul Jr, A., de Sousa, H. C., Malmegrim, R. R. Wine classification by taste sensors made from ultra-thin films and using neural networks [J]. Sensors and Actuators B:Chemical,2004,98(1): 77-82.
[118]Salles, M. O., Bertotti, M., Paixao, T. R. Use of a gold microelectrode for discrimination of gunshot residues [J]. Sensors and Actuators B:Chemical,2012,166:848-852.
[119]Heras, J. Y., Pallarola, D., Battaglini, F. Electronic tongue for simultaneous detection of endotoxins and other contaminants of microbiological origin [J]. Biosensors and Bioelectronics, 2010,25(11):2470-2476.
[120]Rodriguez, S. D., Monge, M. E., Olivieri, A. C., et al. Time dependence of the aroma pattern emitted by an encapsulated essence studied by means of electronic noses and chemometric analysis [J]. Food research international,2010,43(3):797-804.
[121]Snopok, B. A., Kruglenko, I. V. Nonexponential relaxations in sensor arrays:forecasting strategy for electronic nose performance [J]. Sensors and Actuators B:chemical,2005,106(1): 101-113.
[122]Iliev, B., Lindquist, M., Robertsson, L., et al. A fuzzy technique for food-and water quality assessment with an electronic tongue. Fuzzy Sets and Systems,2006,157(9):1155-1168.
[123]Wilson, D. M., Dunman, K., Roppel, T., et al. Rank extraction in tin-oxide sensor arrays [J]. Sensors and Actuators B:Chemical,2000,62(3):199-210.
[124]Wehrens, R., Putter, H., Buydens, L. The bootstrap:a tutorial. Chemometrics and intelligent laboratory systems,2000,54(1):35-52.
[125]Raffo, A., Leonardi, C., Fogliano, V., et al. Nutritional value of cherry tomatoes (Lycopersicon esculentum cv. Naomi F1) harvested at different ripening stages [J]. Journal of Agricultural and Food Chemistry,2002,50(22):6550-6556.
[126]Reinhard, H., Sager, F., Zoller, O. Citrus juice classification by SPME-GC-MS and electronic nose measurements [J]. LWT-Food Science and Technology,2008,10(41):1906-1912.
[127]Gomez, A. H., Wang, J., Hu, G., et al. Monitoring storage shelf life of tomato using electronic nose technique [J]. Journal of Food Engineering,2008,85(4):625-631.
[128]Cole, M., Covington, J. A., Gardner, J. W. Combined electronic nose and tongue for a flavour sensing system [J]. Sensors and Actuators B:Chemical,2011,156(2:832-839.
[129]Gomez-Sanchis, J., Blasco, J., Soria-Olivas, E., et al. Hyperspectral LCTF-based system for classification of decay in mandarins caused by Penicillium digitatum and Penicillium italicum using the most relevant bands and non-linear classifiers [J]. Postharvest Biology and Technology,2013,82:76-86.
[130]Di Natale, C., Macagnano, A., Martinelli, E., et al. The evaluation of quality of post-harvest oranges and apples by means of an electronic nose [J]. Sensors and Actuators B:Chemical, 2011,78(1):26-31.
[131]Kantor, D. B., Hitka, G., Fekete, A., et al. Electronic tongue for sensing taste changes with apricots during storage [J]. Sensors and Actuators B:Chemical,2008,131(1):43-47.
[132]Torri, L., Sinelli, N., Limbo, S. Shelf life evaluation of fresh-cut pineapple by using an electronic nose [J]. Postharvest Biology and Technology,2011,56(3):239-245.
[133]Di Natale, C., Paolesse, R., Macagnano, A., et al. Electronic nose and electronic tongue integration for improved classification of clinical and food samples [J]. Sensors and Actuators B:Chemical,2000,64(1):15-21.
[134]Cole, M., Covington, J. A., Gardner, J. W. Combined electronic nose and tongue for a flavour sensing system [J]. Sensors and Actuators B:Chemical,2011,156(2):832-839.
[135]Tudu, B., Shaw, L., Jana, A., et al. Instrumental testing of tea by combining the responses of electronic nose and tongue [J]. Journal of Food Engineering,2012,110(3):356-363.
[136]Cosio, M. S., Ballabio, D., Benedetti, S., et al. Evaluation of different storage conditions of extra virgin olive oils with an innovative recognition tool built by means of electronic nose and electronic tongue [J]. Food Chemistry,2007,101(2):485-491.
[137]Gan, H., Sang, N., Huang, R., et al. Using clustering analysis to improve semi-supervised classification [J]. Neurocomputing,2013,101:290-298