Mineral identification based on data augmentation and ensemble learning

被引：0

作者：

Wang, Lin ^{[1
]}

Ji, Xiaohui ^{[1
]}

Yang, Mei ^{[2
]}

He, Mingyue ^{[2
]}

Zhang, Zhaochong ^{[3
]}

Zeng, Shan ^{[1
]}

Wang, Yuzhu ^{[1
]}

机构：

[1] School of Information Engineering, China University of Geosciences (Beijing), Beijing

[2] National Mineral Rock and Fossil Specimens Resource Center from MOST, China University of Geosciences (Beijing), Beijing

[3] School of Earth Sciences and Resources, China University of Geosciences (Beijing), Beijing

来源：

Earth Science Frontiers | 2024年 / 31卷 / 04期

关键词：

data augmentation; deep convolutional generative adversarial networks; ensemble learning; mineral identification;

D O I：

10.13745/j.esf.sf.2024.5.6

中图分类号：

学科分类号：

摘要：

Mineral identification as a crucial aspect of geosciences is of great importance to resource exploration, rock classification, and geological monitoring. However, traditional methods are inefficient as they often rely on human experience and subjective judgment. In recent years deep learning-based image classification has been used for accurate and rapid mineral identification. While these studies have achieved certain results, the number of identifiable mineral types are limited and the identification accuracy need to be further improved. This paper aims to address the issue of uneven distribution of mineral image samples in a mineral dataset on 36 common minerals. DCGAN is first used to generate images for data augmentation focusing on the 11 minerals with low sample counts, and the best set of images is selected, by comparison, to expand the dataset. Next, to obtain a more reliable and precise identification model, ResNet, RegNet, EfficientNet, and Vision Transformer models with better performance on ImageNet are transferred to the mineral dataset. Based on the permutations of the trained base models, 11 ensemble models are obtained, with which 24 identification results are obtained using two voting methods, average and weighted soft voting. These results are then compared to select the one with the highest accuracy. The experimental results demonstrated that data augmentation using DCGAN improved the model accuracy by 3.12% averaged over all models. Among the ensemble models, weighted soft voting performed better and achieved the highest accuracy of 87.47% on the augmented dataset. © 2024 Science Frontiers editorial department. All rights reserved.

引用

页码：87 / 94

页数：7

共 15 条

[1] LIU C Z, LI M C., ZHANG Y., Et al., An enhanced rock mineral recognition method integrating a deep learning model and clustering algorithm, Minerals, 9, 9, (2019)
[2] ZHOU W Y, WANG H, WAN Z B., Oreimage classification based on improved CNN, Computers and Electrical Engineering, 99, (2022)
[3] ZENG X, XIAO Y C, JI X H, Et al., Mineral identification based on deep learning that combines image and mohs hard-ness, Minerals, 11, 5, (2021)
[4] WU B K, JI X H, HE M Y, Et al., Mineral identification based on multi-label image classification, Minerals-2022, 12, 11
[5] ANTONIOU A, STORKEY A, EDWARDS H., Data augmentation generative adversarial networks
[6] CRESWELL A, WHITE T, DUMOULIN V, Et al., Generative adversarial networks: an overview, IEEE Signal Processing Magazine, 35, 1, pp. 53-65, (2018)
[7] BUSHRA S N, SHOBANA G., A survey on deep convolu-tional generative adversarial neural network (dcgan) for detection of Covid-19 using chest X-ray/CT-Scan, Proceedings of the 3rd international conference on intelligent sustainable systems (ICISS), Thoothukudi, pp. 702-708, (2020)
[8] DONG X B, YU Z W, CAO W M, Et al., A survey on ensemble learning, Frontiers of Computer Science, 14, 2, pp. 241-258, (2020)
[9] SAQLAIN M, JARGALSAIKHAN B, LEE J Y., A voting ensemble classifier for wafer map defect patterns identification in semiconductor manufacturing, IEEE Transactions on Semiconductor Manufacturing, 32, 2, pp. 171-182, (2019)
[10] LI J, JIA J J, XU D L., Unsupervised representation learning of image-based plant disease with deep convolutional generative adversarial networks, Proceedings of the 37th Chinese control conference (CCC), pp. 9159-9163, (2018)

← 1 2 →