ATTENTION: This site is down for maintenance in read-only mode.

The following is an abstract for the selected article. A PDF download of the full text of this article is available here. Members may download full texts at no charge. Non-members may be charged a small fee for certain articles.

Discriminant Analysis of Fused Positive and Negative Ion Mobility Spectra Using Multivariate Self-Modeling Mixture Analysis and Neural Networks

Volume 62, Number 2 (Feb. 2008) Page 133-141

Chen, Ping; Harrington, Peter B.

A new method coupling multivariate self-modeling mixture analysis and pattern recognition has been developed to identify toxic industrial chemicals using fused positive and negative ion mobility spectra (dual scan spectra). A Smiths lightweight chemical detector (LCD), which can measure positive and negative ion mobility spectra simultaneously, was used to acquire the data. Simple-to-use interactive self-modeling mixture analysis (SIMPLISMA) was used to separate the analytical peaks in the ion mobility spectra from the background reactant ion peaks (RIP). The SIMPLSIMA analytical components of the positive and negative ion peaks were combined together in a butterfly representation (i.e., negative spectra are reported with negative drift times and reflected with respect to the ordinate and juxtaposed with the positive ion mobility spectra). Temperature constrained cascade-correlation neural network (TCCCN) models were built to classify the toxic industrial chemicals. Seven common toxic industrial chemicals were used in this project to evaluate the performance of the algorithm. Ten bootstrapped Latin partitions demonstrated that the classification of neural networks using the SIMPLISMA components was statistically better than neural network models trained with fused ion mobility spectra (IMS).