Application of principal component-radial basis function neural networks (PC-RBFNN) for the detection of water-adulterated bayberry juice by near-infrared spectroscopy

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.

NIR Spectroscopic Properties of Aqueous Acids Solutions

“…From their work, 920 nm and 990–995 nm are the most suitable wavelengths for pH measurement. On the other hand, there are also several studies on the measurement of organic acids that have been conducted on fruit juices such as a research conducted by Xie et al [ 20 ] where they have applied high performance liquid chromatography (HPLC) and NIR spectroscopy between 800–2,400 nm for the measurement of citric and malic acids to detect water-adulterated bayberry juice. Likewise, Li et al [ 21 ] have applied standard enzymatic assays techniques and NIR spectroscopy between 1,100–2,500 nm for the measurement of citric acid in orange juices.…”

Scanner Digital Images Combined with Color Parameters: A Case Study to Detect Adulterations in Liquid Cow’s Milk

“…The digital images were obtained from a commercial table scanner, and two examples were illustrated using liquid cow milk: (1) water addition for volume gain and (2) NaOH addition in sour milk. Regression models were established for water concentration determination, and the results were compared with near-infrared (NIR) spectroscopy, which was used as a reference technique due to the fact that it has been successfully applied for adulteration determination in several contributions reported in the literature (Gayo et al 2006;Gayo and Hale 2007;Kuriakose et al 2010;Xie et al 2008), and one of them was related to milk adulteration with water (Kasemsumran et al 2007) and with other adulterants such as NaOH (Jha and Matsuoka 2004).…”

Quality and Authenticity Control of Fruit Juices-A Review

“…NIR spectrometry, combined with chemometric techniques (PCA, Principal component-radial basis function neural networks, PC-RBFNN) was used to discriminate pure bayberry juice with juice adulterated with water. After employing multiplicative scatter correction (MSC) and standard normal variate (SNV) transformation to pre-process NIR spectra, the results indicated that PC-RBFNN can distinguish authentic bayberry juice samples to water-adulterated samples (recognition rate: 97.6%) but cannot clearly estimate the levels of water in the adulterated bayberry juice [56]. The differentiation of grape juice varieties was reported by Cozzolino et al using NIR and MIR spectroscopy combined with pattern recognition methods.…”