Discriminant Analysis of Countries Growing Wakame Seaweeds: A Preliminary Comparison of Visible-Near Infrared Spectra Using Soft Independent Modelling,Randomforests and Classification and Regression Trees

Abstract

Concerns about the labelling of fisheries products at production centres is now increasing. After the outbreak of bovine spongiform encephalopathy (BSE) occurred, problems relating to clam or wakame and other products have attracted more attention than before. We developed a scientific method for discriminating the production countries of wakame seaweeds using soft independent modelling for class analogy (SIMCA). However, the validation of the obtained SIMCA model was not very good. Therefore, we tried one of the non-parametric classification methods, Randomforests, based on classification and regression trees (CART). We found that Randomforests could be a potent classification method for visible and near infrared spectra. We suggest a preliminary interpretation for the basis of classification conditions by using CART.

Keywords

near infrared (NIR) spectroscopy visible spectroscopy wakame production centre discriminating analysis classification SIMCA Randomforests CART

Get full access to this article

View all access options for this article.

References

Sato

, “Central objective of wakame related industry”, Jpn. J. Phycol. 49, 43 (2001).

Koshino

Kunisaki

Watanabe

Matsumoto

, “Chemical components and quality estimations of boiled and salted wakame”, Report by Specification Inspection Center of Ministry of Agriculture and Foresty of Japan. 11, 119 (1987).

Wold

Sjöström

, “SIMCA: A Method for Analyzing Chemical Data in Terms of Similarity Analogy”, in Chemometrics: Theory and Publications, Ed by Kowalski

B.R.

, American Chemical Society, Washington, USA, p. 243 (1977).

Kaihara

Inaba

Kikuchi

Sato

, “Prediction of wakame production centers using near infrared spectroscopy”, Summaries of nondestructive analysis symposium. 20, 162 (2004).

Kaihara

Inaba

Kikuchi

Sato

, “Feasibility study of the discrimination of production centers of wakame”, Sanrikusogokenkyu 28, 67 (2006).

Breiman

Friedman

Olshen

Stone

, Classification and Regression Trees. Chapman & Hall/CRC, USA (1984).

Fearn

, “Chemometric Space: CART”, NIR news 17(6), 13 (2006).

Breiman

, “Random forests”, Machine Learning 45, 5 (2001). doi: https://dx-doi-org.web.bisu.edu.cn/10.1023/A:1010933404324

Breiman

Cutler

, “Random forests”, Home Page [cited 30 April 2007]. Available from:http://www.stat.berkeley.edu/∼breiman/RandomForests/

10.

Osborne

B.G.

Fearn

, Near Infrared Spectroscopy in Food Analysis. Longman Scientific & Technical, Harlow, Essex, UK (1986).

11.

Salford Systems Inc., “CART”, Home Page [cited 19 September 2006]. Available from:http://www.sal-fordsystems.com/cart.php)

12.

StatSoft, Inc., “Classification trees”, Home Page [cited 19 September 2006]. Available from:http://www.stat-soft.com/textbook/stclatre.html

13.

Steinberg

Horie

Ohotaki

, Applied Tree Based Method by CART. JUSE Press, Japan (1998).