HUSCAP logo Hokkaido Univ. logo

Hokkaido University Collection of Scholarly and Academic Papers >
農学院・農学研究院  >
雑誌発表論文等  >

Chemometric amylose modeling and sample selection for global calibration using artificial neural networks

CAJE_Shimizu-1.pdf323.05 kBPDF見る/開く

タイトル: Chemometric amylose modeling and sample selection for global calibration using artificial neural networks
著者: Shimizu, N. 著作を一覧する
Okadome, H. 著作を一覧する
Wada, D. 著作を一覧する
Kimura, T. 著作を一覧する
Ohtsubo, K. 著作を一覧する
キーワード: amglose
artificial neural network
発行日: 2008年 8月
出版者: 食品科学網
誌名: 食品科学
巻: 29
号: 8
開始ページ: 118
終了ページ: 124
抄録: Chemometric amylose modeling for global calibration, using whole grain near infrared transmittance spectra and sample selection, was used in an artificial neural network (ANN), to assess the global and local models generated, based on samples of newly bred Indica, Japonica and rice. Global samples sets had a wide range of sample variation for amylose content and a narrow sample variation (amylose; 12.3 to 21%). For sample selection the CENTER algorithm was applied to generate calibration, validation and stop sample sets. Spectral preprocessing was found to reduce the optimum number of partial least squares (PLS) components for amylose content and thus enhance the robustness of the local calibration. The best model was found to be an ANN global calibration with spectral preprocessing; the next was a PLS global calibration using standard spectra. These results pose the question whether an ANN algorithm with spectral preprocessing could be developed for global and local calibration models or whether PLS without spectral preprocessing should be developed for global calibration models. We suggest that global calibration models incorporating an ANN may be used as a universal calibration model.
資料タイプ: article (author version)
出現コレクション:雑誌発表論文等 (Peer-reviewed Journal Articles, etc)

提供者: 清水 直人


本サイトに関するご意見・お問い合わせは repo at へお願いします。 - 北海道大学