Aflatoxin rapid detection based on hyperspectral with 1D-convolution neural network in the pixel level.

Journal: Food chemistry
PMID:

Abstract

Aflatoxin is commonly exists in moldy foods, it is classified as a class one carcinogen by the World Health Organization. In this paper, we used one dimensional convolution neural network (1D-CNN) to classify whether a pixel contains aflatoxin. Firstly we found the best combination of 1D-CNN parameters were epoch = 30, learning rate = 0.00005 and 'relu' for active function, the highest test accuracy reached 96.35% for peanut, 92.11% for maize and 94.64% for mix data. Then we compared 1D-CNN with feature selection and methods in other papers, result shows that neural network has greatly improved the detection efficiency than feature selection. Finally we visualized the classification result of different training 1D-CNN networks. This research provides the core algorithm for the intelligent sorter with aflatoxin detection function, which is of positive significance for grain processing and the prenatal detoxification of foreign trade enterprises.

Authors

  • Jiyue Gao
    School of Science and Information Science, Qingdao Agricultural University, Qingdao, China.
  • Longgang Zhao
    Department of Technology, Qingdao Agricultural University, Qingdao, China.
  • Juan Li
    Department of Hygienic Inspection, School of Public Health, Jilin University 1163 Xinmin Street Changchun 130021 Jilin China songxiuling@jlu.edu.cn li_juan@jlu.edu.cn jinmh@jlu.edu.cn +86 43185619441.
  • Limiao Deng
    School of Science and Information Science, Qingdao Agricultural University, Qingdao, China.
  • Jiangong Ni
    School of Science and Information Science, Qingdao Agricultural University, Qingdao, China.
  • Zhongzhi Han
    School of Science and Information, Qingdao Agricultural University, Qingdao 266109, China.