TY - JOUR
T1 - Intelligent identification for rock-mineral microscopic images using ensemble machine learning algorithms
AU - Zhang, Ye
AU - Li, Mingchao
AU - Han, Shuai
AU - Ren, Qiubing
AU - Shi, Jonathan
N1 - Funding Information:
This research was funded by the National Natural Science Foundation for Excellent Young Scientists of China (Grant no. 51622904), the Tianjin Science Foundation for Distinguished Young Scientists of China (Grant no. 17JCJQJC44000) and the National Natural Science Foundation for Innovative Research Groups of China (Grant no. 51621092).
Funding Information:
Funding: This research was funded by the National Natural Science Foundation for Excellent Young Scientists of China (Grant no. 51622904), the Tianjin Science Foundation for Distinguished Young Scientists of China (Grant no. 17JCJQJC44000) and the National Natural Science Foundation for Innovative Research Groups of China (Grant no. 51621092).
Publisher Copyright:
© 2019 by the authors. Licensee MDPI, Basel, Switzerland.
PY - 2019/9/2
Y1 - 2019/9/2
N2 - It is significant to identify rock-mineral microscopic images in geological engineering. The task of microscopic mineral image identification, which is often conducted in the lab, is tedious and time-consuming. Deep learning and convolutional neural networks (CNNs) provide a method to analyze mineral microscopic images efficiently and smartly. In this research, the transfer learning model of mineral microscopic images is established based on Inception-v3 architecture. The four mineral image features, including K-feldspar (Kf), perthite (Pe), plagioclase (Pl), and quartz (Qz or Q), are extracted using Inception-v3. Based on the features, the machine learning methods, logistic regression (LR), support vector machine (SVM), random forest (RF), k-nearest neighbors (KNN), multilayer perceptron (MLP), and gaussian naive Bayes (GNB), are adopted to establish the identification models. The results are evaluated using 10-fold cross-validation. LR, SVM, and MLP have a significant performance among all the models, with accuracy of about 90.0%. The evaluation result shows LR, SVM, and MLP are the outstanding single models in high-dimensional feature analysis. The three models are also selected as the base models in model stacking. The LR model is also set as the meta classifier in the final prediction. The stacking model can achieve 90.9% accuracy, which is higher than all the single models. The result also shows that model stacking effectively improves model performance.
AB - It is significant to identify rock-mineral microscopic images in geological engineering. The task of microscopic mineral image identification, which is often conducted in the lab, is tedious and time-consuming. Deep learning and convolutional neural networks (CNNs) provide a method to analyze mineral microscopic images efficiently and smartly. In this research, the transfer learning model of mineral microscopic images is established based on Inception-v3 architecture. The four mineral image features, including K-feldspar (Kf), perthite (Pe), plagioclase (Pl), and quartz (Qz or Q), are extracted using Inception-v3. Based on the features, the machine learning methods, logistic regression (LR), support vector machine (SVM), random forest (RF), k-nearest neighbors (KNN), multilayer perceptron (MLP), and gaussian naive Bayes (GNB), are adopted to establish the identification models. The results are evaluated using 10-fold cross-validation. LR, SVM, and MLP have a significant performance among all the models, with accuracy of about 90.0%. The evaluation result shows LR, SVM, and MLP are the outstanding single models in high-dimensional feature analysis. The three models are also selected as the base models in model stacking. The LR model is also set as the meta classifier in the final prediction. The stacking model can achieve 90.9% accuracy, which is higher than all the single models. The result also shows that model stacking effectively improves model performance.
KW - CNN
KW - Deep learning
KW - Machine learning
KW - Model stacking
KW - Rock-mineral microscopic images
KW - Transfer learning
UR - http://www.scopus.com/inward/record.url?scp=85072151148&partnerID=8YFLogxK
U2 - 10.3390/s19183914
DO - 10.3390/s19183914
M3 - Journal article
C2 - 31514321
AN - SCOPUS:85072151148
SN - 1424-8220
VL - 19
JO - Sensors (Switzerland)
JF - Sensors (Switzerland)
IS - 18
M1 - 3914
ER -