Detection and Classification of Organophosphate Nerve Agent Simulants Using Support Vector Machines with Multiarray Sensors
The need for rapid and accurate detection systems is expanding and the utilization of cross-reactive sensor arrays to detect chemical warfare agents in conjunction with novel computational techniques may prove to be a potential solution to this challenge. We have investigated the detection, predicti...
Saved in:
Published in | Journal of Chemical Information and Computer Sciences Vol. 44; no. 2; pp. 499 - 507 |
---|---|
Main Authors | , , , , , , , |
Format | Journal Article |
Language | English |
Published |
United States
American Chemical Society
01.03.2004
|
Online Access | Get full text |
Cover
Loading…
Summary: | The need for rapid and accurate detection systems is expanding and the utilization of cross-reactive sensor arrays to detect chemical warfare agents in conjunction with novel computational techniques may prove to be a potential solution to this challenge. We have investigated the detection, prediction, and classification of various organophosphate (OP) nerve agent simulants using sensor arrays with a novel learning scheme known as support vector machines (SVMs). The OPs tested include parathion, malathion, dichlorvos, trichlorfon, paraoxon, and diazinon. A new data reduction software program was written in MATLAB V. 6.1 to extract steady-state and kinetic data from the sensor arrays. The program also creates training sets by mixing and randomly sorting any combination of data categories into both positive and negative cases. The resulting signals were fed into SVM software for “pairwise” and “one” vs all classification. Experimental results for this new paradigm show a significant increase in classification accuracy when compared to artificial neural networks (ANNs). Three kernels, the S2000, the polynomial, and the Gaussian radial basis function (RBF), were tested and compared to the ANN. The following measures of performance were considered in the pairwise classification: receiver operating curve (ROC) A z indices, specificities, and positive predictive values (PPVs). The ROC A z values, specifities, and PPVs increases ranged from 5% to 25%, 108% to 204%, and 13% to 54%, respectively, in all OP pairs studied when compared to the ANN baseline. Dichlorvos, trichlorfon, and paraoxon were perfectly predicted. Positive prediction for malathion was 95%. |
---|---|
Bibliography: | istex:2B5A780DD3E8CD0391FB317759C4F680892D5277 ark:/67375/TPS-829ZSZGF-V ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
ISSN: | 0095-2338 1549-960X |
DOI: | 10.1021/ci034220i |