M. Simpson et al., USE OF PATTERN-RECOGNITION FOR SIGNATURES GENERATED BY LASER-DESORPTION ION MOBILITY SPECTROMETRY OF POLYMERIC MATERIALS, Analyst, 118(10), 1993, pp. 1293-1298
This paper describes the use of an artificial neural network (ANN) for
pattern recognition of ion mobility signatures of polymeric materials
produced by the method known as laser ablation-ion mobility spectrome
try (LA-IMS). This technique has been used to examine a wide range of
polymer-based materials. Mobilization of the sample was achieved using
a laser and the ion mobility spectrometer gave characteristic signatu
res for materials introduced as vapours. The application of the ANN to
the analysis of the IMS signatures has resulted in a novel method for
discriminating polymeric materials. Initial pattern recognition resul
ts obtained from several polymers showed an accuracy of 100% in both t
he test and use domains. Negative ion mobility signatures are presente
d to demonstrate how the signatures were treated before analysis using
the ANN. Future development of the technique is discussed, including
the use of mass spectrometry to identify the species produced by the a
ction of the laser and the use of on-line neural network pattern recog
nition techniques. The ANN approach is applicable to other process and
environmental monitoring situations.