Infrared and Laser Engineering, Volume. 51, Issue 3, 20210252(2022)
Improved data-driven compressing method for hyperspectral mineral identification models
Figures & Tables(11)
Fig. 2. Flow chart of improved sample-driven compression method for hyperspectral mineral identification model
Fig. 6. Parameters of the compressed identification models obtained in the iterative pruning process
Table 1. Information of identified minerals
View tableView in ArticleTable 1. Information of identified minerals
Class name Training samples Testing samples Diagnostic bands/nm Muscovite 100 400 2 200, 2 350 Halloysite 100 240 2 170, 2 210 Calcite 100 240 2 160, 2 340 Kaolinite 100 400 2 170, 2 210 Montmorillonite 100 400 2 230 Alunite 100 400 2 170, 2 320 Chalcedony 100 240 2 250 Total 700 2320
Table 2. Model identification accuracy corresponding to the different number of hidden units
View tableView in ArticleTable 2. Model identification accuracy corresponding to the different number of hidden units
h Overall accuracy 10 91.98% 15 92.54% 20 93.01% 25 93.36% 30 93.62% 35 93.14% 40 92.76% 45 92.50%
Table 3. Result chart of different pruning methods
View tableView in ArticleTable 3. Result chart of different pruning methods
Importance criteria Sequence number of the pruned neuron Number of pruned units Compression rate Identification accuracy after retraining Proposed C-APoZ 1, 4, 6, 12, 17, 20, 23, 27 8 1.36 94.61% APoZ 1, 4, 6, 12, 17, 20, 23 7 1.30 94.57%
Table 4. Iterative pruning results based on different importance criteria
View tableView in ArticleTable 4. Iterative pruning results based on different importance criteria
Iteration C-APoZ (Proposed method) APoZ Compression rate Threshold Identification accuracy Compression rate Threshold Identification accuracy 0 0 0.817 93.62% 0 0.814 93.62% 1 1.36 0.651 94.61% 1.30 0.643 94.57% 2 1.76 0.502 94.66% 1.76 0.597 94.40% 3 2.31 0.464 95.04% 2.14 0.469 94.00% 4 2.73 0.445 94.66% 2.50 0.426 94.00% 5 3.33 0.448 94.35% 2.73 0.444 94.22% 6 4.29 0.379 93.41% 3.00 0.435 93.84% 7 6.00 0.316 90.13% 3.33 0.412 93.32%
Tools
Get Citation
Copy Citation Text
Kewang Deng, Huijie Zhao, Na Li, Hui Cai. Improved data-driven compressing method for hyperspectral mineral identification models[J]. Infrared and Laser Engineering, 2022, 51(3): 20210252
Paper Information
Category: Image processing
Received: Dec. 10, 2021
Accepted: --
Published Online: Apr. 8, 2022
The Author Email: Li Na (lina_17@buaa.edu.cn)
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20