Abstract

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).

Mobile recognition and positioning for multiple visible light communication cells using a convolutional neural network

Xiaoxiao Du, Yanyu Zhang, Chao Wang, Penghui Fan, and Yijun Zhu
Opt. Lett. 48(24) 6468-6471 (2023)

Application of laser photofragmentation-resonance enhanced multiphoton ionization to ion mobility spectrometry

Jeffrey M. Headrick, Thomas A. Reichardt, Thomas B. Settersten, Ray P. Bambha, and Dahv A. V. Kliner
Appl. Opt. 49(11) 2204-2214 (2010)

Discrimination of blood species using Raman spectroscopy combined with a recurrent neural network

Peng Wang, Liangsheng Guo, Yubing Tian, Jiansheng Chen, Shan Huang, Ce Wang, Pengli Bai, Daqing Chen, Weipei Zhu, Hongbo Yang, Wenming Yao, and Jing Gao
OSA Continuum 4(2) 672-687 (2021)

Mixture model analysis of transition edge sensor pulse height spectra

Kevin J. Coakley, Jolene Splett, and Thomas Gerrits
J. Opt. Soc. Am. B 39(1) 137-144 (2022)

Neural network pattern recognition of thermal-signature spectra for chemical defense

Arthur H. Carrieri and Pascal I. Lim
Appl. Opt. 34(15) 2623-2635 (1995)