Multi‐layer feature selection incorporating weighted score‐based expert knowledge toward modeling materials with targeted properties

Simple item page
dc.contributor.authorLiu, Yen_AU
dc.contributor.authorWu, JMen_AU
dc.contributor.authorAvdeev, Men_AU
dc.contributor.authorShi, SQen_AU
dc.date.accessioned2021-03-16T05:12:35Zen_AU
dc.date.available2021-03-16T05:12:35Zen_AU
dc.date.issued2020-01-15en_AU
dc.date.statistics2021-03-16en_AU
dc.descriptionThis article also appears in: Progress in Machine Learning. First published: 1 October 2018, Last updated: 8 September 2020en_AU
dc.description.abstractSelecting proper descriptors or features is one of the central problems in exploring structure–activity relationships of materials using machine learning models. The current feature selection algorithms usually require tedious hyperparameter tuning and do not actively consider the prior knowledge of domain experts about the features. Here, this work proposes a data‐driven multi‐layer feature selection method incorporating domain expert knowledge named DML‐FSdek, which is automated, with users entering training data without manual tuning of the hyperparameters. The domain expert knowledge is quantified by means of weighted scoring and integrated into the selection process to eliminate the risk of crucial features being removed. The test studies on ten material properties datasets demonstrate the potential of the approach to automatically search for a reduced feature set with lower root mean square errors than those for the initial feature set. Essentially, the most relevant material features, the number of which is much smaller than that in the original feature set, are automatically selected to establish a closer and more accurate structure–activity relationship for the materials of interest. As a result, the method represents the targeted properties of materials with a smaller and more interpretable set of features while ensuring equal or better prediction accuracy. © 2020 The Authors. Published by WILEY‐VCH Verlag GmbH & Co. KGaA, Weinheimen_AU
dc.identifier.articlenumber1900215en_AU
dc.identifier.citationLiu, Y., Wu, J.- M., Avdeev, M., Shi, S.- Q. (2020). Multi‐layer feature selection incorporating weighted score‐based expert knowledge toward modeling materials with targeted properties. Advanced Theory and Simulations, 3(2), 1900215. doi:10.1002/adts.201900215en_AU
dc.identifier.issn2513-0390en_AU
dc.identifier.issue2en_AU
dc.identifier.journaltitleAdvanced Theory and Simulationsen_AU
dc.identifier.urihttps://doi.org/10.1002/adts.201900215en_AU
dc.identifier.urihttps://apo.ansto.gov.au/dspace/handle/10238/10550en_AU
dc.identifier.volume3en_AU
dc.language.isoenen_AU
dc.publisherWileyen_AU
dc.subjectSimulationen_AU
dc.subjectAlgorithmsen_AU
dc.subjectAutomationen_AU
dc.subjectPhysical propertiesen_AU
dc.subjectPrediction equationsen_AU
dc.subjectLithium ion batteriesen_AU
dc.titleMulti‐layer feature selection incorporating weighted score‐based expert knowledge toward modeling materials with targeted propertiesen_AU
dc.typeJournal Articleen_AU
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
adts.201900215.pdf
Size:
3.14 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
1.63 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Journal Articles