A Comparative study of Artificial Neural Networks Using Reinforcement learning and Multidimensional Bayesian Classification Using Parzen Density Estimation for Identification of GC-EIMS Spectra of Partially Methylated Alditol Acetates

TL;DR

This paper compares Bayesian classifiers with Parzen density estimation and reinforcement learning-based neural networks for identifying GC-EIMS spectra of PMAAs, demonstrating the neural network's superior performance on partial spectra.

Contribution

It introduces a web-based pattern recognition system for GC-EIMS spectra and compares two novel techniques, highlighting the neural network's advantages in handling partial data.

Findings

Both systems perform well with low noise levels.

Performance decreases as signal-to-noise ratio worsens.

Neural network outperforms Bayesian classifier on partial spectra.

Abstract

This study reports the development of a pattern recognition search engine for a World Wide Web-based database of gas chromatography-electron impact mass spectra (GC-EIMS) of partially methylated Alditol Acetates (PMAAs). Here, we also report comparative results for two pattern recognition techniques that were employed for this study. The first technique is a statistical technique using Bayesian classifiers and Parzen density estimators. The second technique involves an artificial neural network module trained with reinforcement learning. We demonstrate here that both systems perform well in identifying spectra with small amounts of noise. Both system's performance degrades with degrading signal-to-noise ratio (SNR). When dealing with partial spectra (missing data), the artificial neural network system performs better. The developed system is implemented on the world wide web, and is intended to identify PMAAs using submitted spectra of these molecules recorded on any GC-EIMS instrument. The system, therefore, is insensitive to instrument and column dependent variations in GC-EIMS spectra.