Busca avançada
Ano de início
Entree


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

Texto completo
Autor(es):
Barbon Jr, Sylvio ; Ayub da Costa Barbon, Ana Paula ; Mantovani, Rafael Gomes ; Barbin, Douglas Fernandes
Número total de Autores: 4
Tipo de documento: Artigo Científico
Fonte: JOURNAL OF SPECTROSCOPY; v. 2018, p. 12-pg., 2018-01-01.
Resumo

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 L* a*b*, chroma, and hue), water holding capacity (WHO, 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 77.2% precision. The selected wavelengths could lead to potential simple multispectral acquisition devices. (AU)

Processo FAPESP: 15/24351-2 - Análise de imagens e espectroscopia de infravermelho próximo (NIR) na avaliação de qualidade e autenticação de alimentos
Beneficiário:Douglas Fernandes Barbin
Modalidade de apoio: Auxílio à Pesquisa - Jovens Pesquisadores