Sensitive and fast recognition of explosives using fluorescent polymer sensors and pattern recognition analysis

An optical sensor array consisting four fluorescent polymer thin films was investigated to recognize nitro containing explosive, TNT (2,4,6-trinitro toluene) and its simulants. The fluorescence quenching behaviour in presence of these analyte vapors was measured at peak emission of fluorescent materials upon excitation at 440 nm under ambient conditions. The time-dependence of fluorescence intensity for each polymer was obtained in presence of the analyte vapors. Feature patterns, like fluorescence quenching percentage at a certain time, were extracted from the time-dependent fluorescence intensity curve and were used as the input for pattern recognition tools. Even though the explosives were not distinguishable by principle component analysis (PCA) in 2s, support vector machine (SVM) neural network showed 90% recognition rate. However, the recognition rate of SVM neural network was improved to 100% in 5s whereas the fuzzy ARTMAP network had a perfect recognition rate in 6s. Furthermore. the developed recognition system showed robustness to additive noise and can detect and discriminate between simulants and the explosive TNT within 10s at sub parts per billion (ppb) level. (C) 2011 Elsevier B.V. All rights reserved.