Classification of jaboticaba fruits at three maturity stages using NIRS and LDA

Autor(es)

Costa, Rosangela Camara ^[1] ; Cunha Junior, Luis C. ^[2] ; Morgenstern, Thayara Bittencourt ^[3] ; de Almeida Teixeira, Gustavo Henrique ^[4] ; Gomes de Lima, Kassio Michell ^[1]

Afiliação do(s) autor(es)

^[1] Fed Univ Rio Grande do Norte UFRN, Inst Chem, PPGQ, Biol Chem & Chemometr, BR-59072970 Natal, RN - Brazil

^[2] Univ Fed Goias, EA, Setor Horticultura, Ave Esperanca S-N, Campus Univ, BR-74690000 Goiania, Go - Brazil

^[3] Univ Sao Paulo, FMRP, Ave Cafe S-N, BR-14040903 Ribeirao Preto, SP - Brazil

^[4] Univ Estadual Paulista UNESP, Fac Ciencias Agr & Vet, Dept Prod Vegetal, Via Acesso Prof Paulo Donato Castellane S-N, BR-14884900 Sao Paulo - Brazil

• Tipo de documento: Artigo Científico
• Fonte: ANALYTICAL METHODS; v. 8, n. 11, p. 2533-2538, 2016.
• Citações Web of Science: 0

Resumo

This study proposes a rapid and non-destructive method of jaboticaba {[}Myrciaria cauliflora (Mart.) O. Berg] fruit classification at three maturity stages based on the skin colour (immature - fruit completely green, physiologically mature - fruit turning from green to purple, and ripe - fruit completely purple) using Near-Infrared Reflectance Spectroscopy (NIRS) combined with principal component analysis-linear discriminant analysis (PCA-LDA), and variable selection techniques employing a successive projection algorithm (SPA-LDA) or genetic algorithm (GA-LDA). One hundred eighty jaboticaba fruit samples in three maturity stages were used and the multivariate classification accuracy results were tested based on sensitivity, specificity, positive (or precision) and negative predictive values, Youden index, and positive and negative likelihood ratios. In the immature stage the classification models PCA-LDA, GA-LDA and SPA-LDA achieved a sensitivity of 100% in the validation set. The results obtained in this study suggest that the proposed method is a promising alternative for assessing the jaboticaba fruit maturity, opening the possibility for automation in packing houses. (AU)

• Processo FAPESP: 12/00426-5 - Uso da espectroscopia do infravermelho próximo (NIRS) como método não destrutivo no controle de qualidade de frutos íntegros de jaboticabeira: sólidos solúveis e antocianina total
• Beneficiário: Thayara Bittencourt Morgenstern Carlos
• Modalidade de apoio: Bolsas no Brasil - Iniciação Científica
• Processo FAPESP: 08/51408-1 - Desenvolvimento de uma metodologia utilizando a espectroscopia do infravermelho próximo (NIRS) para a seleção e classificação de frutos íntegros de açaizeiro (Euterpe oleracea Mart.) e palmiteiro-jussara (Euterpe edulis Mart.)
• Beneficiário: Gustavo Henrique de Almeida Teixeira
• Modalidade de apoio: Auxílio à Pesquisa - Jovens Pesquisadores