Application of principal component-radial basis function neural networks (PC-RBFNN) for the detection of water-adulterated bayberry juice by near-infrared spectroscopy / 浙江大学学报(英文版)(B辑:生物医学和生物技术)
Journal of Zhejiang University. Science. B
;
(12): 982-989, 2008.
Artículo
en Inglés
| WPRIM
| ID: wpr-359332
ABSTRACT
Near-infrared (NIR) spectroscopy combined with chemometrics techniques was used to classify the pure bayberry juice and the one adulterated with 10% (w/w) and 20% (w/w) water. Principal component analysis (PCA) was applied to reduce the dimensions of spectral data, give information regarding a potential capability of separation of objects, and provide principal component (PC) scores for radial basis function neural networks (RBFNN). RBFNN was used to detect bayberry juice adulterant. Multiplicative scatter correction (MSC) and standard normal variate (SNV) transformation were used to preprocess spectra. The results demonstrate that PC-RBFNN with optimum parameters can separate pure bayberry juice samples from water-adulterated bayberry at a recognition rate of 97.62%, but cannot clearly detect water levels in the adulterated bayberry juice. We conclude that NIR technology can be successfully applied to detect water-adulterated bayberry juice.
Texto completo:
Disponible
Índice:
WPRIM (Pacífico Occidental)
Asunto principal:
Bebidas
/
Contaminación de Alimentos
/
Redes Neurales de la Computación
/
Espectroscopía Infrarroja Corta
/
Análisis de Componente Principal
/
Myrica
/
Métodos
Tipo de estudio:
Estudio diagnóstico
/
Estudio pronóstico
Idioma:
Inglés
Revista:
Journal of Zhejiang University. Science. B
Año:
2008
Tipo del documento:
Artículo
Similares
MEDLINE
...
LILACS
LIS