Geographical discrimination of Asian red pepper powders using 1 H NMR spectroscopy and deep learning-based convolution neural networks

This study investigated an innovative approach to discriminate the geographical origins of Asian red pepper powders by analyzing one-dimensional H NMR spectra through a deep learning-based convolution neural network (CNN). H NMR spectra were collected from 300 samples originating from China, Korea,...

Full description

Saved in:
Bibliographic Details
Published inFood chemistry Vol. 439; p. 138082
Main Authors Hoon Yun, Byung, Yu, Hyo-Yeon, Kim, Hyeongmin, Myoung, Sangki, Yeo, Neulhwi, Choi, Jongwon, Sook Chun, Hyang, Kim, Hyeonjin, Ahn, Sangdoo
Format Journal Article
LanguageEnglish
Published England 01.05.2024
Subjects
Geographical discrimination
Red pepper powder
H NMR
Artificial intelligence
Deep learning-based CNN
Online AccessGet full text

Cover

More Information
Summary:This study investigated an innovative approach to discriminate the geographical origins of Asian red pepper powders by analyzing one-dimensional H NMR spectra through a deep learning-based convolution neural network (CNN). H NMR spectra were collected from 300 samples originating from China, Korea, and Vietnam and used as input data. Principal component analysis - linear discriminant analysis and support vector machine models were employed for comparison. Bayesian optimization was used for hyperparameter optimization, and cross-validation was performed to prevent overfitting. As a result, all three models discriminated the origins of the test samples with over 95 % accuracy. Specifically, the CNN models achieved a 100 % accuracy rate. Gradient-weighted class activation mapping analysis verified that the CNN models recognized the origins of the samples based on variations in metabolite distributions. This research demonstrated the potential of deep learning-based classification of H NMR spectra as an accurate and reliable approach for determining the geographical origins of various foods.
ISSN:1873-7072