Simultaneous feature selection and parameter optimisation using an artificial ant colony: case study of melting point prediction

O’Boyle, Noel M.; Palmer, David Scott; Nigsch, Florian; Mitchell, John B. O.

doi:10.1186/1752-153x-2-21

Cited by 31 publications

(19 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To consider the complex behaviour of this hybrid situation, meta-heuristic optimization methods have been widely proposed in literature (Huang and Wang, 2006;Lin et al, 2008b;Huang, 2009). Most of these methods are based on GA (Zhuo et al, 2008), PSO (Lin et al, 2008b), and ACO (O'Boyle et al, 2008;Huang, 2009).…”

Section: Classification and Simultaneous Feature Selection And Svm Pamentioning

confidence: 99%

See 1 more Smart Citation

Simultaneous feature selection and SVM parameter determination in classification of hyperspectral imagery using Ant Colony Optimization

Samadzadegan

Hasani

Schenk

2012

Canadian Journal of Remote Sensing

View full text Add to dashboard Cite

Section: Classification and Simultaneous Feature Selection And Svm Pamentioning

confidence: 99%

“…O'Boyle et al (2008) considered a binary format for feature selection and discretized SVM parameters in a specified range with a particular step size. In this section a hybrid optimization strategy based on BACO is presented.…”

Section: Classification and Simultaneous Feature Selection And Svm Pamentioning

confidence: 99%

Simultaneous feature selection and SVM parameter determination in classification of hyperspectral imagery using Ant Colony Optimization

Samadzadegan

Hasani

Schenk

2012

Canadian Journal of Remote Sensing

View full text Add to dashboard Cite

“…However, as the lattice energy depends on the strength of intermolecular interaction forces, it can be stipulated that the effect of these intermolecular forces on solubility can be accounted for by the calculated molecular descriptors such as polarizability, dipole moment and hydrogen bonding descriptors. In fact, several models have been proposed for the estimation of melting point using calculated descriptors (O'Boyle et al, 2008;Bergström et al, 2003), which show some level of predictivity, at least for a qualitative classification of the melting point (Bergström et al, 2003).…”

Section: Introductionmentioning

confidence: 99%

Estimation of drug solubility in water, PEG 400 and their binary mixtures using the molecular structures of solutes

Ghafourian

Bozorgi

2010

European Journal of Pharmaceutical Sciences

View full text Add to dashboard Cite

With the aim of solubility estimation in water, polyethylene glycol 400 (PEG) and their binary mixtures, Quantitative Structure -Property Relationships (QSPRs) were investigated to relate the solubility of a large number of compounds to the descriptors of the molecular structures. The relationships were quantified using linear regression analysis (with descriptors selected by stepwise regression) and Formal Inference -based Recursive Modeling (FIRM). The models were compared in terms of the solubility prediction accuracy for the validation set. The resulting regression and FIRM models employed a diverse set of molecular descriptors explaining crystal lattice energy, molecular size, and solute -solvent interactions. Significance of molecular shape in compound's solubility was evident from several shape descriptors being selected by FIRM and stepwise regression analysis. Some of these influential structural features, e.g. connectivity indexes and Balaban topological index, were found to be related to the crystal lattice energy. The results showed that regression models outperformed most FIRM models and produced higher prediction accuracy. However, the most accurate estimation was achieved by the use of a combination of FIRM and regression models. The results also showed that the use of melting point in regression models improves the estimation accuracy especially for solubility in higher concentrations of PEG. Aqueous or PEG/water solubilities can be estimated by these models with root mean square error of below 0.70.

show abstract

“…Some other application of various versions of ACO in descriptor selection of QSPR/QSAR can be found in [265][266][267][268][269][270].…”

Section: Accepted Manuscriptmentioning

confidence: 99%

Chemometrics tools in QSAR/QSPR studies: A historical perspective

Yousefinejad

Hemmateenejad

2015

Chemometrics and Intelligent Laboratory Systems

117

View full text Add to dashboard Cite

Simultaneous feature selection and parameter optimisation using an artificial ant colony: case study of melting point prediction

Abstract: We also test its ability to perform feature selection on a support vector machine model for the same dataset.

Cited by 31 publications

References 34 publications

Simultaneous feature selection and SVM parameter determination in classification of hyperspectral imagery using Ant Colony Optimization

Simultaneous feature selection and SVM parameter determination in classification of hyperspectral imagery using Ant Colony Optimization

Estimation of drug solubility in water, PEG 400 and their binary mixtures using the molecular structures of solutes

Chemometrics tools in QSAR/QSPR studies: A historical perspective

Contact Info

Product

Resources

About