XRF Spectral Feature Extraction and Classification Method Based on the EO-CNN Deep Learning Model
An XRF spectral feature extraction and classification method based on an EO-CNN model is proposed to address the complexities of soil spectral data and improve classification accuracy. The proposed model is applied to soil classification, achieving an overall accuracy of 95% for five distinct soil categories. The experimental results show robustness in handling imbalanced datasets, as evidenced by a 69% classification accuracy for the category representing only 1% of the dataset.
Authors
- Fu Wang (ORCID: https://orcid.org/0000-0002-5596-4208)
- Ran Gao (ORCID: https://orcid.org/0000-0003-2666-1643)
- Yi Zhao (ORCID: https://orcid.org/0000-0002-1139-8320)
- Qinghua Tian (ORCID: https://orcid.org/0000-0002-1169-9078)
- Xiangyu Liu (ORCID: https://orcid.org/0000-0002-9728-2555)
- Qi Zhang (ORCID: https://orcid.org/0000-0001-5303-9804)
- Jiajie Li (ORCID: https://orcid.org/0000-0002-5145-2934)
- Feng Tian
- Lan Rao (ORCID: https://orcid.org/0000-0002-0517-2536)
- Yun Teng (ORCID: https://orcid.org/0000-0002-6674-5529)
- Mohai Yue (ORCID: https://orcid.org/0009-0008-1053-8783)
- Yongjun Wang (ORCID: https://orcid.org/0000-0002-1796-5576)
Institutions
- Beijing Institute of Technology (CN)
- Beijing University of Posts and Telecommunications (CN)
- Beijing Electronic Science and Technology Institute (CN)
- State Key Laboratory of Information Photonics and Optical Communications
Publication Details
- Published
- 2024-12-27
- DOI
- https://doi.org/10.1109/auteee62881.2024.10869765
- Primary Topic
- Image Processing and 3D Reconstruction
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Natural Science Foundation of China