A Novel Method of Multitype Hybrid Rock Lithology Classification Based on Convolutional Neural Networks
Rock lithology recognition plays a fundamental role in geological survey research, mineral resource exploration, mining engineering, etc. However, the objectivity of researchers, rock variable natures, and tedious experimental processes make it difficult to ensure the accurate and effective identifi...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-02-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/4/1574 |
| _version_ | 1797476686202142720 |
|---|---|
| author | Diyuan Li Junjie Zhao Zida Liu |
| author_facet | Diyuan Li Junjie Zhao Zida Liu |
| author_sort | Diyuan Li |
| collection | DOAJ |
| description | Rock lithology recognition plays a fundamental role in geological survey research, mineral resource exploration, mining engineering, etc. However, the objectivity of researchers, rock variable natures, and tedious experimental processes make it difficult to ensure the accurate and effective identification of rock lithology. Additionally, multitype hybrid rock lithology identification is challenging, and few studies on this issue are available. In this paper, a novel multitype hybrid rock lithology detection method was proposed based on convolutional neural network (CNN), and neural network model compression technology was adopted to guarantee the model inference efficiency. Four fundamental single class rock datasets: sandstone, shale, monzogranite, and tuff were collected. At the same time, multitype hybrid rock lithologies datasets were obtained based on data augmentation method. The proposed model was then trained on multitype hybrid rock lithologies datasets. Besides, for comparison purposes, the other three algorithms, were trained and evaluated. Experimental results revealed that our method exhibited the best performance in terms of precision, recall, and efficiency compared with the other three algorithms. Furthermore, the inference time of the proposed model is twice as fast as the other three methods. It only needs 11 milliseconds for single image detection, making it possible to be applied to the industry by transforming the algorithm to an embedded hardware device or Android platform. |
| first_indexed | 2024-03-09T21:06:08Z |
| format | Article |
| id | doaj.art-623a76ab1fd644399b0205556887a741 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T21:06:08Z |
| publishDate | 2022-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-623a76ab1fd644399b0205556887a7412023-11-23T22:01:43ZengMDPI AGSensors1424-82202022-02-01224157410.3390/s22041574A Novel Method of Multitype Hybrid Rock Lithology Classification Based on Convolutional Neural NetworksDiyuan Li0Junjie Zhao1Zida Liu2School of Resources and Safety Engineering, Central South University, Changsha 410083, ChinaSchool of Resources and Safety Engineering, Central South University, Changsha 410083, ChinaSchool of Resources and Safety Engineering, Central South University, Changsha 410083, ChinaRock lithology recognition plays a fundamental role in geological survey research, mineral resource exploration, mining engineering, etc. However, the objectivity of researchers, rock variable natures, and tedious experimental processes make it difficult to ensure the accurate and effective identification of rock lithology. Additionally, multitype hybrid rock lithology identification is challenging, and few studies on this issue are available. In this paper, a novel multitype hybrid rock lithology detection method was proposed based on convolutional neural network (CNN), and neural network model compression technology was adopted to guarantee the model inference efficiency. Four fundamental single class rock datasets: sandstone, shale, monzogranite, and tuff were collected. At the same time, multitype hybrid rock lithologies datasets were obtained based on data augmentation method. The proposed model was then trained on multitype hybrid rock lithologies datasets. Besides, for comparison purposes, the other three algorithms, were trained and evaluated. Experimental results revealed that our method exhibited the best performance in terms of precision, recall, and efficiency compared with the other three algorithms. Furthermore, the inference time of the proposed model is twice as fast as the other three methods. It only needs 11 milliseconds for single image detection, making it possible to be applied to the industry by transforming the algorithm to an embedded hardware device or Android platform.https://www.mdpi.com/1424-8220/22/4/1574rock lithologyconvolutional neural networksdata augmentationclassificationdetection |
| spellingShingle | Diyuan Li Junjie Zhao Zida Liu A Novel Method of Multitype Hybrid Rock Lithology Classification Based on Convolutional Neural Networks Sensors rock lithology convolutional neural networks data augmentation classification detection |
| title | A Novel Method of Multitype Hybrid Rock Lithology Classification Based on Convolutional Neural Networks |
| title_full | A Novel Method of Multitype Hybrid Rock Lithology Classification Based on Convolutional Neural Networks |
| title_fullStr | A Novel Method of Multitype Hybrid Rock Lithology Classification Based on Convolutional Neural Networks |
| title_full_unstemmed | A Novel Method of Multitype Hybrid Rock Lithology Classification Based on Convolutional Neural Networks |
| title_short | A Novel Method of Multitype Hybrid Rock Lithology Classification Based on Convolutional Neural Networks |
| title_sort | novel method of multitype hybrid rock lithology classification based on convolutional neural networks |
| topic | rock lithology convolutional neural networks data augmentation classification detection |
| url | https://www.mdpi.com/1424-8220/22/4/1574 |
| work_keys_str_mv | AT diyuanli anovelmethodofmultitypehybridrocklithologyclassificationbasedonconvolutionalneuralnetworks AT junjiezhao anovelmethodofmultitypehybridrocklithologyclassificationbasedonconvolutionalneuralnetworks AT zidaliu anovelmethodofmultitypehybridrocklithologyclassificationbasedonconvolutionalneuralnetworks AT diyuanli novelmethodofmultitypehybridrocklithologyclassificationbasedonconvolutionalneuralnetworks AT junjiezhao novelmethodofmultitypehybridrocklithologyclassificationbasedonconvolutionalneuralnetworks AT zidaliu novelmethodofmultitypehybridrocklithologyclassificationbasedonconvolutionalneuralnetworks |