This paper demonstrates the feasibility and adΒ¨antages of ( ) using a self-organizing map SOM -type neural network classifier for electromagnetic target recognition. The classifier is supported by a noΒ¨el ( ) feature extraction unit in which the Wigner distribution WD , a timeα frequency representat
Classification of limonoids and protolimonoids using neural networks
β Scribed by Leigh-Anne Fraser; Dulcie A. Mulholland; David D. Fraser
- Publisher
- John Wiley and Sons
- Year
- 1997
- Tongue
- English
- Weight
- 197 KB
- Volume
- 8
- Category
- Article
- ISSN
- 0958-0344
No coin nor oath required. For personal study only.
β¦ Synopsis
A novel technique of classifying liminoids and protolimonoids using artificial neural networks is presented. The difficulties associated with natural product classification are discussed, as well as the relevance of artificial neural networks to the task of automated classification by computer. Data from the 13 C nuclear magnetic resonance spectra of the compounds is pre-processed using histogram binning. Neural networks are trained on this data correctly to classify the data as belonging to a "limonoid", "triterpenoid" or "other" category and to discriminate the protolimonoids from the rest of the triterpenoids in the "triterpenoid" data set. Finally, neural networks are trained to recognise each individual limonoid belonging to the "limonoid" data set. The accuracy of the neural networks is typically better than 90% on unseen or impure data.
π SIMILAR VOLUMES
## Abstract ChemInform is a weekly Abstracting Service, delivering concise information at a glance that was extracted from about 200 leading journals. To access a ChemInform Abstract, please click on HTML or PDF.