Application of Multilayer Feed-Forward Neural Networks to Automated Compound Identification in Low-Resolution Open-Path FT-IR Spectrometry

Abstract

A drawback of current open-path Fourier transform infrared (OP/FT-IR) systems is that they need a human expert to determine those compounds that may be quantified from a given spectrum. In this work, multilayer feed-forward neural networks with one hidden layer were used to automatically recognize compounds in an OP/FT-IR spectrum without compensation of absorption lines due to atmospheric H2O and CO2. The networks were trained by fast-back-propagation. The training set comprised spectra that were synthesized by digitally adding randomly scaled reference spectra to actual open-path background spectra measured over a variety of path lengths and temperatures. The reference spectra of 109 compounds were used to synthesize the training spectra. Each neural network was trained to recognize only one compound in the presence of up to 10 other interferences in an OP/FT-IR spectrum. Every compound in a database of vaporphase reference spectra can be encoded in an independent neural network so that a neural network library can be established. When these networks are used for the identification of compounds, the process is analogous to spectral library searching. The effect of learning rate and band intensities on the convergence of network training was examined. The networks were successfully used to recognize five alcohols and two chlorinated compounds in field-measured controlled-release OP/FT-IR spectra of mixtures of these compounds.

Reliable component identification in atmospheric open‐path FTIR spectroscopy by a cross‐correlation method

“…In Reference 10, two-and three-component mixtures were tested with the use of library spectra that were preprocessed by a Fourier transformation and a subsequent orthonormalization based on a principal-component analysis. Intensive computation is also needed within the training of neural networks, [2][3][4] in particular, when a large number of different compounds must be detected. Compound identification by our straightforward criterion can be implemented without intensive computer programming, but appropriate and component-characteristic spectral intervals have to be selected for routine work.…”

“…The latter technique has been employed for qualitative assays with the use of pattern-recognition techniques (e.g., digital filtering and piecewise-linear discriminant analysis techniques 1 or artificial neural network approaches. [2][3][4] The potential for chemical-warfare-agent detection has prompted the military community to contribute to the development of this technique.…”

Artificial Neural Networks and Their use in Chemistry

“…An interesting approach to interpretation uses a hierarchy of BP networks to "zero in" on the presence or absence of structural features.97 BP networks have also exhibited large improvements in speed and accuracy in searching IR spectral libraries.98-100 An application to matrix isolation IR spectra led to the development of the flashcard algorithm, which overrepresents cases that are difficult to learn.101 A BP network was applied to automatic compound identification in low resolution, open-path Fourier transform IR spectrometry. 102 Nuclear magnetic resonance (NMR) has also been a fruitful area of ANN BP application. [103][104][105][106][107][108][109][110][111] Most studies have dealt with either the simulation of 13C spectra or the prediction of 1% shifts,103-105,107-109 although one study focused on prediction of phosphorus shifts.106 A BP network was used to predict secondary protein structure, which was then used to assist in NMR assignment.…”

Combination of Neural Network and SBFM Algorithm for Monitoring VOCs Distribution by Open Path FTIR Spectrometry

“…[1] With the increasing concern for environmental quality, better monitoring techniques are required which should be able to detect numerous compounds by one instrument with high sensitivity, as well as selectivity, and provide real time, automated, in-situation measurements. The traditional technique of point sampling and later laboratory analysis is far from meeting the above requirements, while Open Path FTIR, which has most of these abilities, shows increasing importance in airborne pollutants detection.…”

“…The traditional technique of point sampling and later laboratory analysis is far from meeting the above requirements, while Open Path FTIR, which has most of these abilities, shows increasing importance in airborne pollutants detection. [1] In previous studies, [2 -10] Open Path FTIR spectrometry, combined with smooth basis function minimization (SBFM) algorithm has been deeply researched, and proved to be an effective and efficient way to reconstruct single component's concentration distribution in a horizontal plane.…”