Prediction of the transition temperature of bent-core liquid crystals using fuzzy "digital thermometer" model based on artificial neural networks
Abstract
A dataset containing transition temperature values for 243 bent-core liquid crystal (LC) compounds was used to develop quantitative structure property relationship (QSPR) models using only 2D molecular descriptors and general regression neural network (GRNN). Beside a standard analogue GRNN model, another GRNN model with fuzzy digital response was created with the aim to estimate the prediction error for each compound. Two approaches for the selection of most relevant subset of descriptors, namely the partial mutual information (PMI) and self-organizing maps combined with chi square ranking, were also compared. The best results were obtained using analogue GRNN model based on PMI selected subset (R-2 = 0.91), with the mean absolute error (MAE) lower in comparison with previously published corresponding QSPR models. The digital PMI-GRNN model enabled distinction between high and low accurate predictions, i.e. ones with absolute error higher than mean absolute error (MAE) and others with... absolute error lt = MAE, with the accuracy of 81%.
Keywords:
Digital GRNN model / Prediction error estimation / SOM feature selection / QSPRSource:
Engineering Applications of Artificial Intelligence, 2018, 71, 251-258Publisher:
- Pergamon-Elsevier Science Ltd, Oxford
Funding / projects:
- Development and Application of Methods and Materials for Monitoring New Organic Contaminants, Toxic Compounds and Heavy Metals (RS-172007)
- Study of the Synthesis, Structure and Activity of Natural and Synthetic Organic Compounds (RS-172013)
DOI: 10.1016/j.engappai.2018.03.009
ISSN: 0952-1976
WoS: 000436213000020
Scopus: 2-s2.0-85044440493
Institution/Community
Tehnološko-metalurški fakultetTY - JOUR AU - Antanasijević, Davor AU - Antanasijević, Jelena AU - Pocajt, Viktor PY - 2018 UR - http://TechnoRep.tmf.bg.ac.rs/handle/123456789/3873 AB - A dataset containing transition temperature values for 243 bent-core liquid crystal (LC) compounds was used to develop quantitative structure property relationship (QSPR) models using only 2D molecular descriptors and general regression neural network (GRNN). Beside a standard analogue GRNN model, another GRNN model with fuzzy digital response was created with the aim to estimate the prediction error for each compound. Two approaches for the selection of most relevant subset of descriptors, namely the partial mutual information (PMI) and self-organizing maps combined with chi square ranking, were also compared. The best results were obtained using analogue GRNN model based on PMI selected subset (R-2 = 0.91), with the mean absolute error (MAE) lower in comparison with previously published corresponding QSPR models. The digital PMI-GRNN model enabled distinction between high and low accurate predictions, i.e. ones with absolute error higher than mean absolute error (MAE) and others with absolute error lt = MAE, with the accuracy of 81%. PB - Pergamon-Elsevier Science Ltd, Oxford T2 - Engineering Applications of Artificial Intelligence T1 - Prediction of the transition temperature of bent-core liquid crystals using fuzzy "digital thermometer" model based on artificial neural networks EP - 258 SP - 251 VL - 71 DO - 10.1016/j.engappai.2018.03.009 ER -
@article{ author = "Antanasijević, Davor and Antanasijević, Jelena and Pocajt, Viktor", year = "2018", abstract = "A dataset containing transition temperature values for 243 bent-core liquid crystal (LC) compounds was used to develop quantitative structure property relationship (QSPR) models using only 2D molecular descriptors and general regression neural network (GRNN). Beside a standard analogue GRNN model, another GRNN model with fuzzy digital response was created with the aim to estimate the prediction error for each compound. Two approaches for the selection of most relevant subset of descriptors, namely the partial mutual information (PMI) and self-organizing maps combined with chi square ranking, were also compared. The best results were obtained using analogue GRNN model based on PMI selected subset (R-2 = 0.91), with the mean absolute error (MAE) lower in comparison with previously published corresponding QSPR models. The digital PMI-GRNN model enabled distinction between high and low accurate predictions, i.e. ones with absolute error higher than mean absolute error (MAE) and others with absolute error lt = MAE, with the accuracy of 81%.", publisher = "Pergamon-Elsevier Science Ltd, Oxford", journal = "Engineering Applications of Artificial Intelligence", title = "Prediction of the transition temperature of bent-core liquid crystals using fuzzy "digital thermometer" model based on artificial neural networks", pages = "258-251", volume = "71", doi = "10.1016/j.engappai.2018.03.009" }
Antanasijević, D., Antanasijević, J.,& Pocajt, V.. (2018). Prediction of the transition temperature of bent-core liquid crystals using fuzzy "digital thermometer" model based on artificial neural networks. in Engineering Applications of Artificial Intelligence Pergamon-Elsevier Science Ltd, Oxford., 71, 251-258. https://doi.org/10.1016/j.engappai.2018.03.009
Antanasijević D, Antanasijević J, Pocajt V. Prediction of the transition temperature of bent-core liquid crystals using fuzzy "digital thermometer" model based on artificial neural networks. in Engineering Applications of Artificial Intelligence. 2018;71:251-258. doi:10.1016/j.engappai.2018.03.009 .
Antanasijević, Davor, Antanasijević, Jelena, Pocajt, Viktor, "Prediction of the transition temperature of bent-core liquid crystals using fuzzy "digital thermometer" model based on artificial neural networks" in Engineering Applications of Artificial Intelligence, 71 (2018):251-258, https://doi.org/10.1016/j.engappai.2018.03.009 . .