Machine Learning Applied to Near-Infrared Spectra for Chicken Meat Classification

Identification of chicken quality parameters is often inconsistent, time-consuming, and laborious. Near-infrared (NIR) spectroscopy has been used as a powerful tool for food quality assessment. However, the near-infrared (NIR) spectra comprise a large number of redundant information. Determining wavelengths relevance and selecting subsets for classification and prediction models are mandatory for the development of multispectral systems. A combination of both attribute and wavelength selection for NIR spectral information of chicken meat samples was investigated. Decision Trees and Decision Table predictors exploit these optimal wavelengths for classification tasks according to different quality grades of poultry meat. The proposed methodology was conducted with a support vector machine algorithm (SVM) to compare the precision of the proposed model. Experiments were performed on NIR spectral information (1050 wavelengths), colour (CIE , chroma, and hue), water holding capacity (WHC), and pH of each sample analyzed. Results show that the best method was the REPTree based on 12 wavelengths, allowing for classification of poultry samples according to quality grades with precision. The selected wavelengths could lead to potential simple multispectral acquisition devices.

[1]  Bjarne K. Ersbøll,et al.  Supervised feature selection for linear and non-linear regression of L⁎a⁎b⁎ color from multispectral images of meat , 2014, Eng. Appl. Artif. Intell..

[2]  S. Amirhassan Monadjemi,et al.  A New Decision Tree for Recognition of Persian Handwritten Characters , 2012 .

[3]  Tom Fearn,et al.  Practical Nir Spectroscopy With Applications in Food and Beverage Analysis , 1993 .

[4]  Reinhold Carle,et al.  On-line application of near infrared (NIR) spectroscopy in food production , 2015 .

[5]  George-John E. Nychas,et al.  A comparison of Raman and FT-IR spectroscopy for the prediction of meat spoilage , 2013 .

[6]  Piotr Boniecki,et al.  Marbling classification of lambs carcasses with the artificial neural image analysis , 2015, Digital Image Processing.

[7]  Patrick De Causmaecker,et al.  Real-world production scheduling for the food industry: An integrated approach , 2012, Eng. Appl. Artif. Intell..

[8]  Sylvio Barbon Junior,et al.  Storage time prediction of pork by Computational Intelligence , 2016, Comput. Electron. Agric..

[9]  Piotr Zapotoczny,et al.  Evaluation of the quality of cold meats by computer-assisted image analysis , 2016 .

[10]  Vassilis S. Kodogiannis,et al.  An adaptive neuro-fuzzy identification model for the detection of meat spoilage , 2014, Appl. Soft Comput..

[11]  Girish H. Subramanian,et al.  A comparison of the decision table and tree , 1992, CACM.

[12]  Nour El Islem Karabadji,et al.  Improved decision tree construction based on attribute selection and data sampling for fault diagnosis in rotating machines , 2014, Eng. Appl. Artif. Intell..

[13]  F. Deatherage,et al.  CHANGES IN HYDRATION, SOLUBILITY AND CHARGES OF MUSCLE PROTEINS DURING HEATING OF MEAT , 1960 .

[14]  M Novič,et al.  Classification of dry-cured hams according to the maturation time using near infrared spectra and artificial neural networks. , 2014, Meat science.

[15]  Sylvio Barbon Junior,et al.  Digital image analyses as an alternative tool for chicken quality assessment , 2016 .

[16]  S. Sathiya Keerthi,et al.  Improvements to Platt's SMO Algorithm for SVM Classifier Design , 2001, Neural Computation.

[17]  Robyn D. Warner,et al.  Influence of high pre-rigor temperature and fast pH fall on muscle proteins and meat quality: a review , 2014 .

[18]  Pavel Turčínek,et al.  Usage of data mining techniques on marketing research data , 2012 .

[19]  Wang Haibin,et al.  Study on hyperspectral image technology based on manifold fuzzy clustering for pork quality classification. , 2015 .

[20]  George-John E. Nychas,et al.  Rapid qualitative and quantitative detection of beef fillets spoilage based on Fourier transform infrared spectroscopy data and artificial neural networks , 2010 .

[21]  Sylvio Barbon Junior,et al.  Comparison of SVM and REPTRee for Classification of Poultry Quality , 2016 .

[22]  Stephen Marshall,et al.  Quantitative Prediction of Beef Quality Using Visible and NIR Spectroscopy with Large Data Samples Under Industry Conditions , 2015 .

[23]  Xiao Li,et al.  Dependence maximization based label space dimension reduction for multi-label classification , 2015, Eng. Appl. Artif. Intell..

[24]  Xichang Wang,et al.  Prediction of total viable counts on chilled pork using an electronic nose combined with support vector machine. , 2012, Meat science.

[25]  Pei-Chann Chang,et al.  A CBR-based fuzzy decision tree approach for database classification , 2010, Expert Syst. Appl..

[26]  Janez Demsar,et al.  Statistical Comparisons of Classifiers over Multiple Data Sets , 2006, J. Mach. Learn. Res..

[27]  Tom J. Moir,et al.  Comparison of multiclass SVM classification techniques in an audio surveillance application under mismatched conditions , 2014, 2014 19th International Conference on Digital Signal Processing.

[28]  Albert Gan,et al.  Prediction of Lane Clearance Time of Freeway Incidents Using the M5P Tree Algorithm , 2011, IEEE Transactions on Intelligent Transportation Systems.

[29]  K. Honikel,et al.  Reference methods for the assessment of physical characteristics of meat. , 1998, Meat science.

[30]  Douglas Fernandes Barbin,et al.  Prediction of chicken quality attributes by near infrared spectroscopy. , 2015, Food chemistry.

[31]  Lixiang Shen,et al.  Fault diagnosis based on Rough Set Theory , 2003 .

[32]  Huan Liu,et al.  Efficient Feature Selection via Analysis of Relevance and Redundancy , 2004, J. Mach. Learn. Res..

[33]  อนิรุธ สืบสิงห์,et al.  Data Mining Practical Machine Learning Tools and Techniques , 2014 .

[34]  Haibiao Ding,et al.  Identification of broiler chicken meat using a visible/near-infrared spectroscopic technique , 1999 .

[35]  Y. Zhao,et al.  Comparison of decision tree methods for finding active objects , 2007, 0708.4274.

[36]  S. Oshita,et al.  Non-invasive analytical technology for the detection of contamination, adulteration, and authenticity of meat, poultry, and fish: a review. , 2015, Analytica chimica acta.

[37]  George-John E. Nychas,et al.  Sensory and microbiological quality assessment of beef fillets using a portable electronic nose in tandem with support vector machine analysis , 2013 .

[38]  S. Prasher,et al.  Prediction of drip-loss, pH, and color for pork using a hyperspectral imaging technique. , 2007, Meat science.

[39]  Jun Wang,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 , 2013 .

[40]  Noel D.G. White,et al.  Classification of contaminants from wheat using near-infrared hyperspectral imaging , 2015 .