Research on Coal and Gangue Recognition Model Based on CAM-Hardswish with EfficientNetV2
Source abstract
Abstract
In response to the multiscale shape of coal and gangue in actual production conditions, existing coal separation methods are inefficient in recognizing coal and gangue, causing environmental pollution and other problems. Combining image data preprocessing and deep learning techniques, this paper presents an improved EfficientNetV2 network for coal and gangue recognition. To expand the dataset and prevent network overfitting, a pipeline-based data enhancement method is used on small sample datasets to simulate coal and gangue production conditions under actual working conditions. This method involves modifying the attention mechanism module in the model, employing the CAM attention mechanism module, selecting the Hardswish activation function, and updating the block structure in the network. The parallel pooling layer introduced in the CAM module can minimize information loss and extract rich feature information compared with the single pooling layer of the SE module. The Hardswish activation function is characterized by excellent numerical stability and fast computation speed. It can effectively be deployed to solve complex computation and derivation problems, compensate for the limitations of the ReLu activation function, and improve the efficiency of neural network training. We increased the training speed of the network while maintaining the accuracy of the model by selecting optimized hyperparameters for the network structure. Finally, we applied the improved model to the problem of coal and gangue recognition. The experimental results showed that the improved EfficientNetV2 coal and gangue recognition method is easy to train, has fast convergence and training speeds, and thus achieves high recognition accuracy under insufficient dataset conditions. The accuracy of coal and gangue recognition increased by 3.98% compared with the original model, reaching 98.24%. Moreover, the training speed improved, and the inference time of the improved model decreased by 6.6 ms. The effectiveness of our proposed model improvements is confirmed by these observations.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Mineral Processing and Grinding · Metal Extraction and Bioleaching · Iron and Steelmaking Processes
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Computer Science and Technology, Xi’an University of Science and Technology, Xi’an 710054, China
Funding
National Natural Science Foundation of China
References (27)
Show source-provided references
1. Analysis on composition characteristics and resource utilization status of coal gangue
2. Wang, X., and Niu, Y. (2023, June 07). Review of research on coal gangue: Classification, hazard and comprehensive utilization. Available online: https://kns.cnki.net/kcms/detail/32.1492.TQ.20230228.1822.002.html.
3. Coal and gangue recognition method research status and prospect
4. Coal and gangue recognition method based on density difference study
5. Research on coal gangue density recognition system based on image processing
6. Research on Recognition of coal gangue in X-ray Detection Based on MATLAB and Image Gray Value
7. Coal gangue dual-energy X-ray image dimensional analysis recognition method
8. Kiljan, P., Moczulski, W., and Kalinowski, K. (2021). Initial Study into the Possible Use of Digital Sound Processing for the Development of Automatic Longwall Shearer Operation. Energies, 14.10.3390/en14102877 ↗
9. Detection and counting of banana bunches by integrating deep learning and classic image-processing algorithms10.1016/j.compag.2023.107827 ↗
10. Novel visual crack width measurement based on backbone double-scale features for improved detection automation10.1016/j.engstruct.2022.115158 ↗
11. Segmentation method for low quality images of coal and gangue based on Retinex and local texture features with multifractal10.1117/1.JEI.31.6.061820 ↗
12. An Image Preprocessing Model of Coal and Gangue in High Dust and Low Light Conditions Based on the Joint Enhancement Algorithm10.1155/2021/2436486 ↗
13. Bloice, M., Stocker, C., and Holzinger, A. (2017). Augmentor: An image augmentation library for machine learning. arXiv.10.21105/joss.00432 ↗
14. Coal gangue recognition method based on image processing and convolutional Neural Network
15. He, K., Zhang, X., and Ren, S. (2016, January 27–30). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
16. Woo, S., Park, J., and Lee, J. (2018, January 8–14). Cbam: Convolutional block attention module. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.10.1007/978-3-030-01234-2_1 ↗
17. Hu, J., Shen, L., and Sun, G. (2018, January 18–23). Squeeze-and-excitation networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.10.1109/CVPR.2018.00745 ↗
18. Based on in-depth study of coal gangue identification technology and implementation
19. Howard, A., Sandler, M., and Chu, G. (November, January 27). Searching for mobilenetv3. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Republic of Korea.
20. Ramachandran, P., Zoph, B., and Le, Q. (2017). Searching for activation functions. arXiv.
21. Neural network architecture search development review
22. Hong, H., Zheng, L., and Zhu, J. (2017). Automatic recognition of coal and gangue based on convolution neural network. arXiv.
23. An image-based hierarchical deep learning framework for coal and gangue detection10.1109/ACCESS.2019.2961075 ↗
24. Dosovitskiy, A., Beyer, L., and Kolesnikov, A. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv.
25. Liu, Z., Mao, H., and Wu, C. (2022, January 18–24). A convnet for the 2020s. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (IEEE/CVF), New Orleans, LA, USA.10.1109/CVPR52688.2022.01167 ↗
26. Tan, M., and Le, Q. (2019, January 9–15). Efficientnet: Rethinking model scaling for convolutional neural networks. Proceedings of the International Conference on Machine Learning (ICML), Long Beach, CA, USA.
27. Tan, M., and Le, Q. (2021, January 18–24). Efficientnetv2: Smaller models and faster training. Proceedings of the International Conference on Machine Learning (ICML), Virtual Event.