Mass spectral search method using the neural network approach

Chong Sze TONG*, K. C. Cheng

*Corresponding author for this work

Research output: Contribution to journalJournal articlepeer-review

29 Citations (Scopus)


This paper explores the use of neural networks as a novel approach in the implementation of spectral library search for gas chromatography mass spectrometry which is a common and powerful analytic tool for the forensic drug chemists nowadays. A total of 28 drugs currently under control in Hong Kong were chosen for the study. Real forensic data, which represents mass spectra obtained under various conditions ranging from good to poor, were used for training and testing. Salient features from the spectral data were extracted using Simpson's diversity index, and such features were presented to various neural networks as input. A total of 355 spectra were used for training the neural networks, and a further set of 163 spectra was used for evaluation. All the neural networks performed well, with recognition rates above 97.5%. Moreover, the best performing neural network achieved perfect recognition. Copyright (C) 1999 Elsevier Science B.V.

Original languageEnglish
Pages (from-to)135-150
Number of pages16
JournalChemometrics and Intelligent Laboratory Systems
Issue number2
Publication statusPublished - 4 Oct 1999

Scopus Subject Areas

  • Analytical Chemistry
  • Software
  • Process Chemistry and Technology
  • Spectroscopy
  • Computer Science Applications

User-Defined Keywords

  • Gas chromatography mass spectrometry
  • Identification of illicit drugs
  • Neural networks


Dive into the research topics of 'Mass spectral search method using the neural network approach'. Together they form a unique fingerprint.

Cite this