• Journal of electromagnetic engineering and science
• /
• v.17 no.4
• /
• pp.186-190
• /
• 2017

Visible-near-infrared (VIS-NIR) spectroscopy is a fast and non-destructive method for analyzing materials. However, most commercial VIS-NIR spectrometers are inappropriate for use in various locations such as in homes or offices because of their size and cost. In this paper, we classified eight food powders using a portable VIS-NIR spectrometer with a wavelength range of 450-1,000 nm. We developed three machine learning models using the spectral data for the eight food powders. The proposed three machine learning models (random forest, k-nearest neighbors, and support vector machine) achieved an accuracy of 87%, 98%, and 100%, respectively. Our experimental results showed that the support vector machine model is the most suitable for classifying non-linear spectral data. We demonstrated the potential of material analysis using a portable VIS-NIR spectrometer.

• Food Engineering Progress
• /
• v.13 no.4
• /
• pp.297-301
• /
• 2009

This study was performed to develop a prediction model of sugar content for strawberry. Near-infrared (NIR) spectroscopy has been prevailed for on-line and portable applications for non-invasive quality assessment of intact fruit. This work presents effects of illumination method and coating of reflection surface of light source on prediction result of sugar content. Effect of preprocessing methods was also examined. A low-cost commercially available VIS/NIR spectrometer was used for estimation of total soluble solids content (Brix). To predict sugar contents of strawberry, the best results were obtained with the spectrum data measured under intensive illuminations at three locations induced from the light source with fiber optic bundles. Gold coating of reflection surface of light source lamp gave favorable effect to prediction result. The best results in validation of PLSR model were $r_{SEP}$ = 0.891 and SEP = 0.443 Brix under OSC preprocessing and those of PCR were $r_{SEP}$ = 0.845, SEP $r_{SEP}$= 0.520 Brix, under no preprocessing.