abs

학술발표회초록보기

Inquiry on Abstract abstract@kcsnet.or.kr

Inquiry on Payment member@kcsnet.or.kr

현재 가능한 작업은 아래와 같습니다.
  • 03월 02일 17시 이후 : 초록수정 불가능, 일정확인 및 검색만 가능

129th General Meeting of Korean Chemical Society & Exposition Artificial intelligence analysis of 1H NMR spectra for discriminating the geographical origin of Asian red pepper powder

Submission Date :
2 / 28 / 2022 , 16 : 16 : 44
Abstract Number :
129022828358
Presenting Type:
Poster Presentation
Presenting Area :
Analytical Chemistry
Authors :
Sangdoo Ahn*, Byung Hoon Yun, Hyeong Min Kim, Hyo-Yeon Yu
Department of Chemistry, Chung-Ang University, Korea
Assigned Code :
ANAL.P-339 Assigend Code Guideline
Presenting Time :
April 14 (THU) 11:00~13:00
The purpose of this study is to develop a method to identify the geographical origin of Asian red pepper powder based on artificial intelligence analysis of 1H NMR spectrum. A support vector machine (SVM) and convolutional neural network (CNN) deep learning models were employed to analyze the 600 MHz 1H NMR spectral data of 300 red pepper powder samples, 100 each from Korea, China, and Vietnam respectively, distributed in Korea. Since the 1H NMR spectrum of red pepper powder appears in a very complex pattern due to the various metabolites of red pepper powder, the spectrum was divided into several parts and analyzed to compare the identification accuracy according to the spectrum range. The optimized SVM and CNN deep learning models showed higher accuracy in discriminating the geographical origin of red pepper powders than the data processing methods using statistical techniques. These results demonstrated the feasibility that artificial intelligence techniques can be effectively used to discriminate NMR spectra of foods, which are difficult to completely distinguish with conventional statistical means.