Food Powder Classification Using a Portable Visible-Near-Infrared Spectrometer
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...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
The Korean Institute of Electromagnetic Engineering and Science
2017-10-01
|
Series: | Journal of the Korean Institute of Electromagnetic Engineering and Science |
Subjects: | |
Online Access: | http://jees.kr/upload/pdf/jees-2017-17-4-186.pdf |
id |
doaj-f24ca4e1c7fb4c3d83c9e9eee5434745 |
---|---|
record_format |
Article |
spelling |
doaj-f24ca4e1c7fb4c3d83c9e9eee54347452020-11-24T21:08:04ZengThe Korean Institute of Electromagnetic Engineering and ScienceJournal of the Korean Institute of Electromagnetic Engineering and Science2234-84092234-83952017-10-0117418619010.26866/jees.2017.17.4.1863279Food Powder Classification Using a Portable Visible-Near-Infrared SpectrometerHanjong You0Youngsik Kim1Jae-Hyung Lee2Byung-Jun Jang3Sunwoong Choi4 Department of Secured Smart Electric Vehicle, Kookmin University, Seoul, Korea Stratio Inc., San Jose, CA, USA Stratio Inc., San Jose, CA, USA Department of Electrical Engineering, Kookmin University, Seoul, Korea Department of Secured Smart Electric Vehicle, Kookmin University, Seoul, KoreaVisible-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.http://jees.kr/upload/pdf/jees-2017-17-4-186.pdfClassificationFood PowderMachine LearningNear Infrared SpectroscopyPortable VIS-NIR Spectrometer |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Hanjong You Youngsik Kim Jae-Hyung Lee Byung-Jun Jang Sunwoong Choi |
spellingShingle |
Hanjong You Youngsik Kim Jae-Hyung Lee Byung-Jun Jang Sunwoong Choi Food Powder Classification Using a Portable Visible-Near-Infrared Spectrometer Journal of the Korean Institute of Electromagnetic Engineering and Science Classification Food Powder Machine Learning Near Infrared Spectroscopy Portable VIS-NIR Spectrometer |
author_facet |
Hanjong You Youngsik Kim Jae-Hyung Lee Byung-Jun Jang Sunwoong Choi |
author_sort |
Hanjong You |
title |
Food Powder Classification Using a Portable Visible-Near-Infrared Spectrometer |
title_short |
Food Powder Classification Using a Portable Visible-Near-Infrared Spectrometer |
title_full |
Food Powder Classification Using a Portable Visible-Near-Infrared Spectrometer |
title_fullStr |
Food Powder Classification Using a Portable Visible-Near-Infrared Spectrometer |
title_full_unstemmed |
Food Powder Classification Using a Portable Visible-Near-Infrared Spectrometer |
title_sort |
food powder classification using a portable visible-near-infrared spectrometer |
publisher |
The Korean Institute of Electromagnetic Engineering and Science |
series |
Journal of the Korean Institute of Electromagnetic Engineering and Science |
issn |
2234-8409 2234-8395 |
publishDate |
2017-10-01 |
description |
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. |
topic |
Classification Food Powder Machine Learning Near Infrared Spectroscopy Portable VIS-NIR Spectrometer |
url |
http://jees.kr/upload/pdf/jees-2017-17-4-186.pdf |
work_keys_str_mv |
AT hanjongyou foodpowderclassificationusingaportablevisiblenearinfraredspectrometer AT youngsikkim foodpowderclassificationusingaportablevisiblenearinfraredspectrometer AT jaehyunglee foodpowderclassificationusingaportablevisiblenearinfraredspectrometer AT byungjunjang foodpowderclassificationusingaportablevisiblenearinfraredspectrometer AT sunwoongchoi foodpowderclassificationusingaportablevisiblenearinfraredspectrometer |
_version_ |
1716760983617142784 |