Predicting solubility in supercritical fluid extraction using a neural network

Paul Battersby; John Dean; William Tomlinson; Steven Hitchen; Peter Myers

doi:10.1039/AN9941900925

Predicting solubility in supercritical fluid extraction using a neural network

Paul Battersby, John Dean, William Tomlinson, Steven Hitchen, Peter Myers

Research output: Contribution to journal › Article › peer-review

9 Citations (Scopus)

Abstract

A neural network has been constructed for prediction of the solubility of analytes in supercritical carbon dioxide. Preliminary studies for the input of molecular structure into the network indicates that connectivity indices are adequate to provide structural information in a condensed form. This allows neural networks, which would otherwise be very extensive, to have reduced training times; it also reduces the possibility of memorization of the training data and over-training of the network.

Original language	English
Pages (from-to)	925-928
Journal	Analyst
Volume	119
Issue number	5
DOIs	https://doi.org/10.1039/AN9941900925
Publication status	Published - 1994

Keywords

Supercritical fluid extraction
solubility prediction
neural networks
connectivity indices

Access to Document

10.1039/AN9941900925

Cite this

@article{3425386eadbb4d1aaa1a50bb8e2fb316,

title = "Predicting solubility in supercritical fluid extraction using a neural network",

abstract = "A neural network has been constructed for prediction of the solubility of analytes in supercritical carbon dioxide. Preliminary studies for the input of molecular structure into the network indicates that connectivity indices are adequate to provide structural information in a condensed form. This allows neural networks, which would otherwise be very extensive, to have reduced training times; it also reduces the possibility of memorization of the training data and over-training of the network.",

keywords = "Supercritical fluid extraction, solubility prediction, neural networks, connectivity indices",

author = "Paul Battersby and John Dean and William Tomlinson and Steven Hitchen and Peter Myers",

year = "1994",

doi = "10.1039/AN9941900925",

language = "English",

volume = "119",

pages = "925--928",

journal = "Analyst",

issn = "0003-2654",

publisher = "Royal Society of Chemistry",

number = "5",

}

TY - JOUR

T1 - Predicting solubility in supercritical fluid extraction using a neural network

AU - Battersby, Paul

AU - Dean, John

AU - Tomlinson, William

AU - Hitchen, Steven

AU - Myers, Peter

PY - 1994

Y1 - 1994

N2 - A neural network has been constructed for prediction of the solubility of analytes in supercritical carbon dioxide. Preliminary studies for the input of molecular structure into the network indicates that connectivity indices are adequate to provide structural information in a condensed form. This allows neural networks, which would otherwise be very extensive, to have reduced training times; it also reduces the possibility of memorization of the training data and over-training of the network.

AB - A neural network has been constructed for prediction of the solubility of analytes in supercritical carbon dioxide. Preliminary studies for the input of molecular structure into the network indicates that connectivity indices are adequate to provide structural information in a condensed form. This allows neural networks, which would otherwise be very extensive, to have reduced training times; it also reduces the possibility of memorization of the training data and over-training of the network.

KW - Supercritical fluid extraction

KW - solubility prediction

KW - neural networks

KW - connectivity indices

UR - https://www.scopus.com/pages/publications/0343100899

U2 - 10.1039/AN9941900925

DO - 10.1039/AN9941900925

M3 - Article

SN - 0003-2654

SN - 0144-557X

SN - 1359-7337

SN - 1364-5528

VL - 119

SP - 925

EP - 928

JO - Analyst

JF - Analyst

IS - 5

ER -

Predicting solubility in supercritical fluid extraction using a neural network

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this