A new approach to chemical agent detection, classification, and estimation

Tao Qian; Genshe Chen; Erik Blasch; Robert Lynch; Yongwei Qi

doi:10.1117/12.778501

17 March 2008 A new approach to chemical agent detection, classification, and estimation

Tao Qian, Genshe Chen, Erik Blasch, Robert Lynch, Yongwei Qi

Proceedings Volume 6973, Data Mining, Intrusion Detection, Information Assurance, and Data Networks Security 2008; 69730K (2008) https://doi.org/10.1117/12.778501
Event: SPIE Defense and Security Symposium, 2008, Orlando, Florida, United States

Abstract

Chemical and biological agent detection has gained a great deal of interest in various applications. We present a new approach to vapor classification and concentration estimation in spacecraft environment. The approach consists of two steps. First, a classifier based on a Support Vector Machine (SVM) is used to identify the presence of toxic vapors. Second, once the vapors are classified, a cubic spline fitting and linear additive model for mixtures based concentration estimation algorithm is used to estimate the concentration of vapor. Once trained, the estimation algorithm can accurately estimate vapor concentrations for both single and mixture vapors under different humidity conditions. Extensive performance evaluations were performed by using e-nose data collected at NASA KCS. We achieved more than 99% accuracy for single vapors and 98% for binary mixture vapors. The classification success rate was 87% using the linear discriminant method. Comparative studies were conducted between the SVM classifier and other classifiers such as Probability Neural Network (PNN) and Learning Vector Quantization (LVQ). In all cases, the SVM classifier showed superior performance over other classifiers. In the concentration estimation part, we achieved less than 3% error in single vapor cases and less than 10% error in mixture cases.

Citation Download Citation

Tao Qian, Genshe Chen, Erik Blasch, Robert Lynch, and Yongwei Qi "A new approach to chemical agent detection, classification, and estimation", Proc. SPIE 6973, Data Mining, Intrusion Detection, Information Assurance, and Data Networks Security 2008, 69730K (17 March 2008); https://doi.org/10.1117/12.778501

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