An Automatic Detection Method of Nanocomposite Film Element Based on GLCM and Adaboost M1

Guo, Hai; Yin, Jinghua; Zhao, Jun; Liu, Yuanyuan; Yao, Lei; Xu, Xia

doi:10.1155/2015/205817

Cited by 2 publications

(1 citation statement)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furmanchuk et al (2016) develop a generalised model for forecasting bulk moduli of various types of crystalline materials, based on ensemble predictive learning using a unique set of attributes. Guo et al (2017Guo et al ( , 2015aGuo et al ( , 2015b propose ensemble learning to predict the dielectrical properties of the nanocomposite film, which has obtained a good effect.…”

Section: Introductionmentioning

confidence: 99%

A predictive modelling of nanocomposite coating microhardness based on extremely randomised trees

Guo

Zhao

Xiaoniu

2019

IJMPT

Self Cite

View full text Add to dashboard Cite

Nanocomposite coating is a coating made of particles whose sizes are of nanoscale. The microhardness of the coating is an importance parameter. Currently, experimental method is mainly adopted in the coating's microhardness and performance research, with high research cost and long time period. In this paper, the content of the nano-particles in the plating liquid, current density, duty ratio, addition of additives and ultrasonic power are set as inputs; the micro hardness of the nanocomposite coating is set as output. Extremely randomised trees (ERT) are used to establish a strong prediction model. The prediction performance is the ERT model is superior to that of the single models such as linear regression, back-propagation neural network and radial basis function neural network, etc. and other ensemble learning methods. ERT model can be used for predicting the microhardness of nanocomposite coating, providing an efficient and highly reliable method for new material performance prediction.

show abstract

Section: Introductionmentioning

confidence: 99%

A predictive modelling of nanocomposite coating microhardness based on extremely randomised trees

Guo

Zhao

Xiaoniu

2019

IJMPT

Self Cite

View full text Add to dashboard Cite

show abstract

Classification of CoCr-based magnetic thin films via GLCM texture features extracted from EFTEM images and machine learning

Rumman,

Barua,

Monju

et al. 2024

AIP Advances

View full text Add to dashboard Cite

Gray-level co-occurrence matrix (GLCM) texture features offer a powerful technique for image analysis in various fields, including medical diagnostics and material classification. This research investigates their efficacy in classifying CoCr-based magnetic thin films—Co84Cr16, Co80Cr16Pt4, Co80Cr16Ta4, and Co76Cr16Ta4Pt4—using energy-filtered transmission electron microscopy (EFTEM) images. The raw EFTEM images were preprocessed to divide into variable quantities of equal segments (9, 18, or 36), leading to three distinct training and testing sets. Light Gradient Boosting Machine (LightGBM) and Artificial Neural Network (ANN) were employed, achieving accuracies exceeding 85%. Besides the accuracy metric, the ML models underwent a comprehensive evaluation using precision, recall, F1-score for each class, and 10-fold cross-validation. Furthermore, a comparative study between the LightGBM and ANN models was performed by conducting feature importance analysis using SHapley Additive exPlanations (SHAP). Notably, both ML models exhibit an accuracy of over 85%. Furthermore, the strategic segmentation of images into 18 equal pieces yielded 100% accuracy using the ANN model. The research delves into the nuanced dynamics surrounding the impact of training and testing set size on the model’s performance. Finally, the feature importance analysis via SHAP identifies pivotal contributors, accentuating the ANN model’s adeptness in leveraging a broader spectrum of features for pattern identification and underscoring the effectiveness of neural network-based models in navigating the intricate landscape of image classification tasks.

show abstract

An Automatic Detection Method of Nanocomposite Film Element Based on GLCM and Adaboost M1

Cited by 2 publications

References 15 publications

A predictive modelling of nanocomposite coating microhardness based on extremely randomised trees

A predictive modelling of nanocomposite coating microhardness based on extremely randomised trees

Classification of CoCr-based magnetic thin films via GLCM texture features extracted from EFTEM images and machine learning

Contact Info

Product

Resources

About