The use of principal component analysis (PCA) and partial least square (PLS) for designing new hard inverse perovskites materials

Saidi, F.; Khetari, Samia; Yahia, Ibrahim S.; Zahran, H. Y.; Hidouri, Tarek; Ameur, N. Ait Ben

doi:10.1016/j.cocom.2022.e00667

Cited by 10 publications

(7 citation statements)

References 149 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The boundary condition equations and PCA equations for the optimization area can be found in eqs (1)–(8) in the Supporting Information. It should be noted that the inverse projection technique of statistical pattern recognition can be used for the inverse design of materials . After the corresponding PCA values are acquired through the inverse projection of the optimization area sampling, the specific chemical formula can be obtained through the inverse transformation of the descriptor values using the PCA equations.…”

Section: Resultsmentioning

confidence: 99%

Machine Learning Combined with Weighted Voting Regression and Proactive Searching Progress to Discover ABO_3-δ Perovskites with High Oxide Ionic Conductivity

Xu,

Lu,

et al. 2023

J. Phys. Chem. C

View full text Add to dashboard Cite

ABO 3-δ -type perovskites are one of the important oxygen ion conductors because of the enhanced properties through adjustments to the composition via elemental doping. In this work, machine learning combined with weighted voting regression (WVR) and proactive searching progress (PSP) was used to develop a model with high accuracy for the prediction of the oxide ionic conductivity of doped ABO 3-δ perovskites. After feature selection, algorithm selection, and parameter optimization, Gradient Boosting regression (GBR), random forest regression (RFR), and extra trees regression (ETR) were determined to be the optimal methods for WVR in constructing the integrated model. The R values of leave-one-out cross-validation (LOOCV) and the test set for the integrated model M WVR could reach 0.812 and 0.920, respectively. After the PSP was conducted, a total of 179 perovskites with high oxide ionic conductivity were discovered. PSP searching identified 8 types of perovskites with high oxide ionic conductivity. Pattern recognition was employed to identify the optimization area that exhibited a high oxide ionic conductivity. Visualization of factor effects was used to visualize the effect of the doping element type and ratio on the oxide ionic conductivity. The Shapley Additive exPlanations (SHAP) analysis of the significant features revealed that R a /R b had the highest influence on the oxide ionic conductivity with a negative impact. The developed integrated model, explored patterns, and optimization areas in this work can serve as a valuable guide for the discovery and design of perovskites with high oxide ionic conductivity.

show abstract

Section: Resultsmentioning

confidence: 99%

Machine Learning Combined with Weighted Voting Regression and Proactive Searching Progress to Discover ABO_3-δ Perovskites with High Oxide Ionic Conductivity

Xu,

Lu,

et al. 2023

J. Phys. Chem. C

View full text Add to dashboard Cite

show abstract

“…PCA makes it possible to convert a set of correlated variables into a new set of uncorrelated variables called principal components. As a multivariate unsupervised statistical procedure, PCA is widely used as a data exploratory tool 36–39 . PCA is used when there are too many explanatory variables relative to the number of observations or the explanatory variables are highly correlated.…”

Section: Methodsmentioning

confidence: 99%

“…As a multivariate unsupervised statistical procedure, PCA is widely used as a data exploratory tool. [36][37][38][39] PCA is used when there are too many explanatory variables relative to the number of observations or the explanatory variables are highly correlated. Mathematical and geometrical basics of PCA algorithm including the methods of choosing the number of principal components are given in.…”

Section: Principal Components Analysismentioning

confidence: 99%

Method of raw materials selection for production of the MgO‐C bricks of comparable properties using PCA and K‐medoids

Sado

2023

Int J Applied Ceramic Tech

View full text Add to dashboard Cite

MgO‐C refractories are zonally installed in most of the key heat devices of steel and iron metallurgy with the exposure to various corrosive factors. One of the most significant factors is low‐temperature decarburization resulting in the oxidation of carbon in MgO‐C refractories and loss of its properties. Moreover MgO‐C materials are exposed for direct attack of liquid slag or steel melt which easily infiltrate the porous, decarburized hot face of the bricks. Cost of MgO‐C materials of high quality is important for refractories user. For this reason researches try to develop materials of high quality but with lower cost by substituting fused raw materials with sintered ones or with recycled MgO‐C. In this article method of selecting the raw materials for production of MgO‐C bricks with comparable properties is shown. 20 different variants of MgO‐C materials were prepared with the use of various quality raw materials. Basic properties of the industrially produced MgO‐C bricks were measured. To select recipes with similar quality PCA method and K‐medoids algorithm were applied. To verify the results corrosion resistance of selected MgO‐C materials were tested with the use of induction furnace of medium frequency.This article is protected by copyright. All rights reserved

show abstract

“…It is important to note that the eigenvectors of the covariance matrix are orthogonal in Principal Component Analysis. [49][50][51][52][53] The final stage of Principal Component Analysis involves evaluating the scores, which represent the projections of the variables onto a given principal component (PC), and the loads, which represent the eigenvectors of the diagonalized covariance matrix. The scores correspond to the eigenvalues of the diagonalized covariance matrix, while the loads correspond to its eigenvectors.…”

Section: Data Mining Detailsmentioning

confidence: 99%

DFT Investigation of Electronic and Mechanical Properties of Binary Magnesium-Rare Earth Alloys Examined with Data Mining Approach

Saidi,

Ouadah,

Ameur

2023

ECS J. Solid State Sci. Technol.

Self Cite

View full text Add to dashboard Cite

The study employed density functional theory (DFT) in conjunction with the generalized gradient approximation (GGA) to investigate the electronic, structural, and mechanical properties of twelve rare Earth-magnesium alloys. These alloys exhibit remarkable mechanical stability, with HoMg and ErMg displaying exceptional shear resistance and stiffness, making them promising candidates for demanding applications. Furthermore, our analysis using principal component analysis (PCA) revealed significant trends and correlations among the material properties of these alloys, offering insights into their potential industrial applications. This research not only advances our understanding of rare Earth-magnesium alloys but also contributes to the development of advanced materials in engineering and industry.

show abstract

The use of principal component analysis (PCA) and partial least square (PLS) for designing new hard inverse perovskites materials

Cited by 10 publications

References 149 publications

Machine Learning Combined with Weighted Voting Regression and Proactive Searching Progress to Discover ABO_3-δ Perovskites with High Oxide Ionic Conductivity

Machine Learning Combined with Weighted Voting Regression and Proactive Searching Progress to Discover ABO_3-δ Perovskites with High Oxide Ionic Conductivity

Method of raw materials selection for production of the MgO‐C bricks of comparable properties using PCA and K‐medoids

DFT Investigation of Electronic and Mechanical Properties of Binary Magnesium-Rare Earth Alloys Examined with Data Mining Approach

Contact Info

Product

Resources

About

The use of principal component analysis (PCA) and partial least square (PLS) for designing new hard inverse perovskites materials

Cited by 10 publications

References 149 publications

Machine Learning Combined with Weighted Voting Regression and Proactive Searching Progress to Discover ABO3-δ Perovskites with High Oxide Ionic Conductivity

Machine Learning Combined with Weighted Voting Regression and Proactive Searching Progress to Discover ABO3-δ Perovskites with High Oxide Ionic Conductivity

Method of raw materials selection for production of the MgO‐C bricks of comparable properties using PCA and K‐medoids

DFT Investigation of Electronic and Mechanical Properties of Binary Magnesium-Rare Earth Alloys Examined with Data Mining Approach

Contact Info

Product

Resources

About

Machine Learning Combined with Weighted Voting Regression and Proactive Searching Progress to Discover ABO_3-δ Perovskites with High Oxide Ionic Conductivity

Machine Learning Combined with Weighted Voting Regression and Proactive Searching Progress to Discover ABO_3-δ Perovskites with High Oxide Ionic Conductivity