Indices for the evaluation of neural network performance as classifier: Application to structural elucidation in infrared spectroscopy

Sbirrazzuoli, Nicolas; Cachet, Claude; Cabrol‐Bass, Daniel; Forrest, Tom

doi:10.1007/bf02098740

Cited by 13 publications

(14 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The following indices are used to evaluate and compare network performance. For a complete discussion of the reliability of these indices see reference [25]. Each index is relative to a specific substructure class.…”

Section: Performance Evaluationmentioning

confidence: 99%

Clustering of infrared spectra with Kohonen networks

Cleva

Cachet²,

Cabrol‐Bass³

1999

Analusis

Self Cite

View full text Add to dashboard Cite

Abstract. The design of systems for spectral data interpretation requires clustering of chemical compounds based on their spectral characteristics. Kohonen networks have been shown to be efficient tools to achieve this clustering. These auto-organising systems perform a mapping between a high-dimensional variable space and a two-dimensional one. An application to infrared spectra of organic compounds is presented here. The non-supervised learning algorithm used allows classification of compounds by spectral characteristics without a priori knowledge. An analysis of the distribution of spectra on the resulting maps is used to build models for predicting the presence or absence of specific structural features. The performance of the models in recognising structural features is discussed and compared with the prediction of a multilayered feed forward network (MLFFN). Localisation of compounds wrongly classified by the MLFFN on the Kohonen maps allows to establish a link between the supervised and the unsupervised approaches.

show abstract

Section: Performance Evaluationmentioning

confidence: 99%

Clustering of infrared spectra with Kohonen networks

Cleva

Cachet²,

Cabrol‐Bass³

1999

Analusis

Self Cite

View full text Add to dashboard Cite

show abstract

“…This in turn involved deciding upon a performance metric [5] by which the overall performance of the network could be judged. Any performance metric is in general specific to the problem with which the network is dealing, and gives a measure of how well the network performs on previously unseen data.…”

Section: Post-processingmentioning

confidence: 99%

A neural network to predict attendance of paediatric patients at outpatient clinics

Snowden

Weech

McClure

et al. 1995

Neural Comput & Applic

View full text Add to dashboard Cite

“…Certains indices, en particulier le taux global de rCponses exactes, dCpendent de la probabilitk a priori de trouver le ou les motifs structuraux considCrCs, donc de leurs proportions dans les populations CtudiCes, et donnent souvent une image exagCrCment flatteuse des performances rCelles du rCseau. La question de la validation et de I'Cvaluation des rCseaux est discutCe dans la rCfCrence 3 1; pour une revue critique des indices utilisCs voir Sbirrazzuoli et al (29).…”

Section: Evaluation Des Performancesunclassified

“…A titre d'exemple, nous utiliserons les rksultats obtenus avec deux rCseaux : l'un traitant les spectres infrarouge (29), l'autre les spectres de masse3 qui permettent de reconnaitre des motifs structuraux assez gCnCraux figurant dans le tableau 3.…”

Section: Dosunclassified

Application pratique des réseaux neuro mimétiques aux données spectroscopiques (infrarouge et masse) en vue de l'élucidation structurale

Cabrol‐Bass¹,

Cachet²,

Cleva³

et al. 1995

Can. J. Chem.

Self Cite

View full text Add to dashboard Cite

In the last few years, intensive research by several groups has shown that neural networks can be used to analyse spectral data for structural elucidation, and that their performance approaches that of an expert in the field. The construction of such networks, their training and evaluation, requires large structural and spectral databases and significant computational resources and time. However, once the network has been completed it can be used very effectively for practical applications on an ordinary desktop computer. In this article we describe the methodology for creating such a network for infrared and mass spectra, and present a program for use on a personal computer, either connected to a spectrometer or independently. The program accepts data in ASCII format, both for the network description and for the spectral information. This approach permits the use of neural networks in an analytical laboratory with limited computational resources. Keywords: neural networks, infrared spectroscopy, mass spectroscopy, structure determination.

show abstract

Indices for the evaluation of neural network performance as classifier: Application to structural elucidation in infrared spectroscopy

Cited by 13 publications

References 27 publications

Clustering of infrared spectra with Kohonen networks

Clustering of infrared spectra with Kohonen networks

A neural network to predict attendance of paediatric patients at outpatient clinics

Application pratique des réseaux neuro mimétiques aux données spectroscopiques (infrarouge et masse) en vue de l'élucidation structurale

Contact Info

Product

Resources

About