Intelligent Material Data Preparation Mechanism Based on Ensemble Learning for AI‐Based Ceramic Material Analysis
- Authors
- Imran,; Iqbal, Naeem; Kim, Do‐Hyeun
- Issue Date
- Nov-2022
- Publisher
- WILEY-V C H VERLAG GMBH
- Keywords
- ceramic data pre-processing; ceramic material; data imputation; material analysis; material data preparation
- Citation
- Advanced Theory and Simulations, v.5, no.11
- Journal Title
- Advanced Theory and Simulations
- Volume
- 5
- Number
- 11
- URI
- https://scholarworks.bwise.kr/gachon/handle/2020.sw.gachon/86100
- DOI
- 10.1002/adts.202200517
- ISSN
- 2513-0390
- Abstract
- Research interest in ceramic materials increased due to their extensive environmental, biomedical, and electronic applications. Increased demand for ceramics with specialized experimental conditions and limited resources has resulted in a higher cost for scientific practices and applications. Enormous material data is accumulated from traditional and high-tech experimentation, but the manual recording process has shown inconsistencies in the analysis results. Recently, application based on artificial intelligence (AI) and machine learning has been able to address the issues of traditional scientific experiments in material science. However, no machine learning mechanisms are proposed for sophisticated data preparation and AI-based discovery application of ceramics. This paper proposed an intelligent material data preparation mechanism based on ensemble learning for AI-assisted material screening and discovery. The current method can potentially resolve the problems of missing and inconsistent material data. As a case study, a material data preparation platform for ceramic material data pre-processing is developed. For performance evaluation of the proposed mechanism, machine learning regression models are trained before and after the imputation techniques applied to the data. Performance analysis shows that the ensemble model of deep learning network (DNN) and automated machine learning (autoML) performed better as compared to previously reported imputation approaches. © 2022 Wiley-VCH GmbH.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - ETC > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/gachon/handle/2020.sw.gachon/86100)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.