Analysis and pattern recognition of HPLC trace organic impurity patterns in phase space

Tetyana I. Aksyonova, Alla A. Patiokha, Alessandro E.P. Villa, William J. Welsh, Igor V. Tetko, Alexey G. Ivakhnenko, Walter L. Zielinski, David J. Livingstone

Research output: Contribution to conferencePaperpeer-review

Abstract

A general method for constructing analytical fingerprints and pattern recognition of HPLC (High Performance Liquid Chromatography) trace organic impurity patterns is proposed. The approach considers signals in phase space and accounts for additive (distortion of the relative magnitude of peak signals) and perturbative noise (distortions of the time scale of the trace organic impurity patterns and non-stationarity of signal in time domain) in analyzed data samples. The elaborated method is based on nonlinear models of signals and it enables detection and comparison of similar signal segments realized at different retention times. The classification rate of the method applied to sample chromatographic data remains about 95% even when the number of available data in the training sets are reduced by a factor of 5. The current approach provides a simple yet comprehensive interpretation of the calculated results and, thus, represents a useful technique to be used for practical application in the analysis, monitoring and classification of complex analytical data.

Original languageEnglish (US)
Pages935-940
Number of pages6
StatePublished - 1999
Externally publishedYes
EventProceedings of the 1999 Artificial Neural Networks in Engineering Conference (ANNIE '99) - St. Louis, MO, USA
Duration: Nov 7 1999Nov 10 1999

Other

OtherProceedings of the 1999 Artificial Neural Networks in Engineering Conference (ANNIE '99)
CitySt. Louis, MO, USA
Period11/7/9911/10/99

All Science Journal Classification (ASJC) codes

  • Software

Fingerprint Dive into the research topics of 'Analysis and pattern recognition of HPLC trace organic impurity patterns in phase space'. Together they form a unique fingerprint.

Cite this