Identification of oil spills by near-infrared spectroscopy (NIR) and support vector machine (SVM)

Weihong Bi; Ailing Tan; Yong Zhao; Meijing Gao

doi:10.1117/12.838054

20 November 2009 Identification of oil spills by near-infrared spectroscopy (NIR) and support vector machine (SVM)

Weihong Bi, Ailing Tan, Yong Zhao, Meijing Gao

Proceedings Volume 7511, 2009 International Conference on Optical Instruments and Technology: Optoelectronic Measurement Technology and Systems; 75111R (2009) https://doi.org/10.1117/12.838054
Event: International Conference on Optical Instrumentation and Technology, 2009, Shanghai, China

Abstract

The identification of the spilled oil is an essential and important part in the investigation and handling of oil spill accidents. The combination of near-infrared spectroscopy (NIR) and chemometrics is ideal for such a situation. NIR spectroscopy is a powerful and effective technique and qualitative information can be obtained with classification models. Support vector machines (SVM) have been introduced recently in chemometrics and have proven to be powerful in NIR spectra classification tasks, such as material identification and food discrimination. In this work, the SVM is utilized to classify near infrared spectroscopy of simulated spilled oils of gasoline, diesel fuel and kerosene on the marine. A good classification performance is obtained :the identification rate were 100%, 96% and 98% on the test sets respectively.

Citation Download Citation

Weihong Bi, Ailing Tan, Yong Zhao, and Meijing Gao "Identification of oil spills by near-infrared spectroscopy (NIR) and support vector machine (SVM)", Proc. SPIE 7511, 2009 International Conference on Optical Instruments and Technology: Optoelectronic Measurement Technology and Systems, 75111R (20 November 2009); https://doi.org/10.1117/12.838054

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available