The NeuroDeveloper®:: a tool for modular neural classification of spectroscopic data

被引：31

作者：

Udelhoven, T ^{[1
]}

Novozhilov, M ^{[1
]}

Schmitt, J ^{[1
]}

机构：

[1] Synthon KG, D-69118 Heidelberg, Germany

来源：

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS | 2003年 / 66卷 / 02期

关键词：

neural networks; modular ANNs; classification; feature selection; spectroscopic data;

D O I：

10.1016/S0169-7439(02)00161-2

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

The NeuroDeveloper(R) is a high-performance software tool for the classification of spectroscopic data using artificial neural networks (ANNs). The software consists of four specialized modules, each constructed for one step within the classification procedure. The FeatureDeveloper offers a user-friendly visualization of the raw-spectra, uni- or multivariate methods for wavelength selection and compression, as well as standard tools for spectra preprocessing. The NeuroSimulator performs the neural network training. The identification of a suited network architecture is supported by an automation tool. The development of modular and hierarchically organized neural networks of any degree of complexity is done in the ModuleDeveloper. Finally, the evaluation of new data by trained ANNs is achieved by the Classification module with a complete documentation via printout and log-files. (C) 2003 Elsevier Science B.V. All rights reserved.

引用

页码：219 / 226

页数：8

共 13 条

[1]

[Anonymous], [No title captured]

[2]

BISHOP CM, 1985, NEURAL NETWORKS PATT, P482

[3]

Bortz J., 1999, STAT SOZIALWISSENSCH, P836

[4] Advantages of a hierarchical system of neural-networks for the interpretation of infrared spectra in structure determination [J].