2004
DOI: 10.1002/aic.10116
|View full text |Cite
|
Sign up to set email alerts
|

Estimation of infinite dilution activity coefficients of organic compounds in water with neural classifiers

Abstract: A new approach is presented for the development of quantitative structure-property relations (QSPR) based on the extraction of relevant molecular features with self-organizing

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
19
0

Year Published

2006
2006
2022
2022

Publication Types

Select...
7
1

Relationship

0
8

Authors

Journals

citations
Cited by 28 publications
(19 citation statements)
references
References 75 publications
(135 reference statements)
0
19
0
Order By: Relevance
“…The hydrocarbon content can be correlated with the molecular surface area [6], the different group contributions or fragment structure information [7]. These QSPRs can also involve self-organizing maps (SOMs) and fuzzy ARTMAP neural systems, as in the work of Giralt et al, developed to estimate infinite dilution activity coefficients of organics compounds in water [8].…”
Section: Introductionmentioning
confidence: 99%
“…The hydrocarbon content can be correlated with the molecular surface area [6], the different group contributions or fragment structure information [7]. These QSPRs can also involve self-organizing maps (SOMs) and fuzzy ARTMAP neural systems, as in the work of Giralt et al, developed to estimate infinite dilution activity coefficients of organics compounds in water [8].…”
Section: Introductionmentioning
confidence: 99%
“…Figure 3. Comparison between the infinite dilution activity coefficient values predicted using the COSMO-RS model and the experimental data of Giralt et al [17] The line represents the equality between predicted and experimental data. The labelled numbers denote the corresponding molecules in Table 3.…”
Section: Predicted Formation Properties Results At Infinite Dilution mentioning
confidence: 94%
“…To do so, one can either use experimental γi data (if there are available) or use a predictive model like COSMO‐RS. In the present study all γi,exp values were taken from the work of Giralt et al and have been combined with the experimental μi0,gas values taken from the DIPPR database in order to determine experimental μi0, values. Likewise, the predicted μi0, have been calculated by combining the predicted γi,CRS values and the μi0,gas values predicted using the method introduced in the previous section.…”
Section: Methodsmentioning
confidence: 99%
“…Alternatively, the quantitative structure-property relationship (QSPR) provides a promising method for the estimation of ∞ based on descriptors derived solely from the molecular structure to fit experimental data [14][15][16][17][18]. The QSPR is based on the assumption that the variation of the behavior of the compounds, as expressed by any measured physicochemical properties, can be correlated with numerical changes in structural features of all compounds, termed "molecular descriptors" [19][20][21][22][23].…”
Section: Introductionmentioning
confidence: 99%