Detection of bacterial contamination in milk using NIR spectroscopy and two classification methods-SIMCA and neuro-fuzzy classifier
Agricontrol, Volume # 3 | Part# 1
Veleva-Doneva, Petya; Draganova, Tsvetelina; Atanasova, Stefka; Tsenkova, Roumiana
Digital Object Identifier (DOI)
Potential of near-infrared spectrocopy combined with multivarite classification methods for detection of bacteria in cow milk was investigated. Spectra of milk samples were obtained in a region from 600 to 1880nm. Presence of Staphylococcus aureus, Streptococcus agalactiae and other bacteria samples by classical microbiological methods. One hundred milk samples negative for bacteria (class healthy) and one hundred milk samples with presence of bacteria (class contaminated) were used in the investigation. Two classification methods - Soft Independent Modeling of Class Analogy (SIMCA) and adaptive Neuro - Fuzzy Inference System (ANFIS) were implemented. SIMCA develops models for each class based on principal components (PC) that describe the variations of the spectral data. One each class has its own model, new samples could be classified to one or another classes according to their spectra. The inputs to ANFIS were several principal components. ANFIS had only one output node, the class type. One-half of samples from each class were used as a training set for creation of SIMCA models or trained the ANFIS. The rest of the samples were used as test set for verification theo btained classifiers. SIMCA models, based on 7 PC correct classified 90% of samples from class contaminated and 88% of samples from class healthy for training data set. The results for testing the models with samples from test set were as follow: 90% of samples from class contaminated and 86% of samples from class healthy were correct classified. The average testing error for ANFIS classifier was 0.058% for class healthy was 0,032% for class contaminated. Results of the presented experiments showed possibility to establish classifiers for identification of raw milk samples, infected with bacteria. Near infrared spectroscopy in combination with multivariate classification techniques offers an alternative appraoch to traditional methods with large potentials for a rapid and reliable application in microbiology, bio-diagnostics and food control.
 Dayhoff, J.E. (1990). Neural Networks Principles. Prentice-Hall Internatioanal. USA.  Farkas, I., Remenyi, P., Biro, A. (2000). A neural network topology for modelling grain drying. Computers and Electronics in Agriculture, 26, 147-158.  Forina, M., Lanteri, S. (1984). Data Analysis in Food Chemistry. In B.R. Kowalski, (ed.), Chemometrics. Mathematics and Statistics in Chemistry, D. Reidel Publishing Company, 305-349.  Forina, M., Lanteri, S., Casale, M. (2007). Multivariate calibration. Journal of Chromatography A, 1158, 61-93.  Hamann, J. and Kroemker, V. (1997). Potential of specific milk composition variables for cow health management, Livest. Prod. Sci., 48, 201-208.  Harmon, R.J. (1994). Physiology of mastitis and factors affecting somatic cell counts, J. Dairy Sci., 77, 2103- 2112.  Heise, H.M. (2000). Clinical application of near-and mid-infrared spectoscopy. In H. Gremlich and B. Yan. Marsel Dekker (ed.), Infrared and Raman Spectoscopy of Biological Materials, New York, 259-322.  Khanna, T. (1990). Foundations of Neural Networks. Addison-Wesley Publishing Company. USA.  Martens, H., Naes, T. (1991). Multivariate Calibration, Wiley, Chichester.  Naes, T. (1992). In: K.I. Hildrum, T. Isaksson, T. Naes, A. Tandberg (ed.), Near Infrared Spectroscopy. Bridging the Gap Between Data Analysis and NIR Applications, Ellis Horwood Limited, Chichester, West Sussex, UK, 51-60.  Naes, T., Isaksson, T., Fearn, T., Davies, A. (2002). A User-friendly Guide to Multivariate Calibration and Classification, NIR Publications, Chichester, UK.  Naumann, D., Helm, D. and Labischinski, H. (1991). Microbial characterizations by FT-IR spectroscopy, Nature, 351, 81-82.  Oberreuter, H., Brodbeck, A., von Stetten, S., Goerges, S., Scherer, S. (2003). Fourier-transform infrared (FT-IR) spectroscopy is a promising tool for monitoring the population dynamics of microorganisms in food stuff. Europ. Food Research and Technol., 216, 434-439.  Perez-Marin, D., Garrido-Varo, A., Guerrero, J.E. (2007). Non - linear regression methods in NIRS quantitative analysis, Talanta, 72, 28-42.  Pyorala, S. (2003). Indicators of inflammation in the diagnosis of mastitis, Vet. Res., 34, 565-578.  Reneau, J.K. and Packard, V.S. (1991). Monitoring mastitis, milk quality and economic losses in dairy fields, Dairy, Food and Environmental Sanitation, 11, 4-11.  Saranwong, S. and Kawano, S. (2008). Interpretation of near infrared calibration structure for determinating the total aerobic bacteria count of raw milk: interaction between bacterial metabolites and water absorptions, J. Near Infrared Spectroscopic, 16, 497-504.  Tsenkova, R., Atanassova, S., Kavano, S., and Toyoda, K. (2001). Somatic cell count determination in cow's milk by near-infrared spectroscopy: A new diagnostic tool, J. Anim. Sci., 79, 2550-2557.  Tsenkova, R., Atanassova, S., Morita, H., Ikuta, K., Toyoda, K., Iordanova, I., and Hakogi, E. (2006). Near infrared spectra of cow's milk for milk quality evaluation: diesease diagnosis and pathogen identification, J. Near Infrared Spectroscopic, 14, 363-370.  Quinn, P., Carter, M.E., Markey, B.K., and Carter, G.R. (1999). Clinical Veterinary Microbiology, Mastitis, 327- 344.  Wold, S. (1976). Pattern Recognition by Means of Disjoint Principal Components Models, Pattern Recognition, 8, 127-139.