期刊
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS
卷 114, 期 -, 页码 132-142出版社
ELSEVIER
DOI: 10.1016/j.chemolab.2012.03.013
关键词
Oil spill fingerprint; IR spectroscopy; Partial Least Squares Discriminant Analysis; Kernel-PLS; Counterpropagation Artificial Neural Networks; Support Vector Machines
类别
资金
- EU
Supervised pattern recognition methods had scarcely been applied to assess the origin of hydrocarbons lumps arrived at the coastline. In this work eight supervised multivariate methods based on quite different principles (Discriminant Analysis, Principal Components Analysis combined to Discriminant Analysis, Soft Independent Modelling of Class Analogy, K-Nearest Neighbours, Partial Least Squares Discriminant Analysis (PLS-DA), kernel-PLS (radial basis functions-PLS), Counterpropagation Artificial Neural Networks (CPANN) and Support Vector Machines with linear, radial basis function and polynomial kernels) and a 'consensus' approach were used to discriminate between the aliquots of six oil spillages monitored on time by mid-IR spectroscopy. Further, a set of 45 unknowns collected in Galician beaches after a major shipwreck were analyzed by both the IR-chemometric-based method and an international oil fingerprinting standard protocol (the European Guideline CEN/TR 15522-2 guide) to set their 'true' assignations. Classification of the controlled spillages yielded almost 100% successful classification ratios (precision, sensitivity and specificity) whereas less than 5% false positives and false negatives were obtained when the 45 samples were classified. SVM with polynomial kernels had only 1 misclassification and outperformed the other approaches, including the 'consensus' approach. CPANN, radial basis functions-PLS and the consensus approach were the second best models with 93.3% agreement with the standard protocol. On the other hand, linear PLS-DA yielded the worst classification model. (C) 2012 Elsevier B.V. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据