A data-driven machine learning approach to predicting stacking faulting energy in austenitic steels

Chaudhary, Nayan; Abu-Odeh, Akram; Караман, И.; Arróyave, Raymundo

doi:10.1007/s10853-017-1252-x

Cited by 41 publications

(13 citation statements)

References 104 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some researchers favor using the output probability of the base learner as the input of the secondary learner. In addition, if some relatively simple learners are selected as primary learners and more complex learners are selected as metalearners, the stacking performance will be more robust in terms of classification accuracy [46,47]. Therefore, herein, we propose the novel The datasets selected in this experiment were diverse, including prognostic data, protein data, and two-category data.…”

Section: Discussionmentioning

confidence: 99%

Cancer Classification with a Cost-Sensitive Naive Bayes Stacking Ensemble

Xiong

2021

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

Ensemble learning combines multiple learners to perform combinatorial learning, which has advantages of good flexibility and higher generalization performance. To achieve higher quality cancer classification, in this study, the fast correlation-based feature selection (FCBF) method was used to preprocess the data to eliminate irrelevant and redundant features. Then, the classification was carried out in the stacking ensemble learner. A library for support vector machine (LIBSVM), K -nearest neighbor (KNN), decision tree C4.5 (C4.5), and random forest (RF) were used as the primary learners of the stacking ensemble. Given the imbalanced characteristics of cancer gene expression data, the embedding cost-sensitive naive Bayes was used as the metalearner of the stacking ensemble, which was represented as CSNB stacking. The proposed CSNB stacking method was applied to nine cancer datasets to further verify the classification performance of the model. Compared with other classification methods, such as single classifier algorithms and ensemble algorithms, the experimental results showed the effectiveness and robustness of the proposed method in processing different types of cancer data. This method may therefore help guide cancer diagnosis and research.

show abstract

Section: Discussionmentioning

confidence: 99%

Cancer Classification with a Cost-Sensitive Naive Bayes Stacking Ensemble

Xiong

2021

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

show abstract

“…While SFE cannot be experimentally measured, it can be inferred from transmission electron microscopy or diffraction techniques. However, running an experiment uses resources, Chaudhary et al [11] collected data from many different studies to form a combined dataset with chemical composition and experimentally measured SFE for austenitic steels. They apply a variety of machine learning techniques to predict SFE from steel composition.…”

Section: F I G U R Ementioning

confidence: 99%

Retracted: Multi‐model penalized regression

Wendelberger

Reich

2021

Statistical Analysis

View full text Add to dashboard Cite

Model fitting often aims to fit a single model, assuming that the imposed form of the model is correct. However, there may be multiple possible underlying explanatory patterns in a set of predictors that could explain a response. Model selection without regarding model uncertainty can fail to bring these patterns to light. We present multi-model penalized regression to acknowledge model uncertainty in the context of penalized regression. In the penalty form introduced here, we explore how different settings can promote either shrinkage or sparsity of coefficients in separate models. A choice of penalty form that enforces variable selection is applied to predict stacking fault energy from steel alloy composition. The aim is to identify multiple models with different subsets of covariates that explain a single type of response.

show abstract

“…However, if not based experimental data, the modelled predictions often fail in giving reasonable trends, and show a systematic offset [107]. Therefore, the SFE calculations must be combined with experimental studies [92] or supported by other approaches like multivariate linear regression [109] or data driven machine-learning [110] in order to be verified.…”

Section: Methods For Determination Of the Stacking Fault Energy (Sfe)...mentioning

confidence: 99%

Microstructure Aspects of the Deformation Mechanisms in Metastable Austenitic Steels

Rafaja

Ullrich

Motylenko

et al. 2020

Springer Series in Materials Science

View full text Add to dashboard Cite

This chapter presents microstructure features, which are responsible for transformation-induced and twinning-induced plasticity in austenitic steels, gives an overview of relevant microstructure defects and shows how the microstructure defects and their interactions affect the deformation behaviour of these steels. Numerous examples illustrate the capability of scanning and transmission electron microscopy and X-ray and electron diffraction to detect, to identify and to quantify dislocations, stacking faults, twins and their clusters. In this context, the benefits of the in situ techniques of microstructure analysis are emphasized. As the presence and arrangement of stacking faults in austenite play a central role in the plasticity of the austenitic steels, a large part of this chapter is devoted to the characterization and description of their formation, widening and ordering. A novel method for determination of the stacking fault energy is presented that utilizes in situ X-ray or synchrotron diffraction under deformation. Finally, the dependence of the stacking fault energy on the chemical composition of the steel and on the deformation temperature is addressed, and considered as an effective tool for design of steels with desirable mechanical properties.

show abstract

A data-driven machine learning approach to predicting stacking faulting energy in austenitic steels

Cited by 41 publications

References 104 publications

Cancer Classification with a Cost-Sensitive Naive Bayes Stacking Ensemble

Cancer Classification with a Cost-Sensitive Naive Bayes Stacking Ensemble

Retracted: Multi‐model penalized regression

Microstructure Aspects of the Deformation Mechanisms in Metastable Austenitic Steels

Contact Info

Product

Resources

About