2020
DOI: 10.1109/jmass.2020.3019669
|View full text |Cite
|
Sign up to set email alerts
|

Cloud Implementation of Multinomial Logistic Regression for UAV Hyperspectral Images

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
12
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
9
1

Relationship

1
9

Authors

Journals

citations
Cited by 28 publications
(12 citation statements)
references
References 70 publications
0
12
0
Order By: Relevance
“…Class RF [75] MLR [321] SVM [322] MLP [69] RNN [70] LSTM [323] GRU [324] CNN-1D [218] CNN-2D [325] CNN-3D [326] HybridSN [213] MorphCNN [196 CNN-1D, CNN-2D, CNN-3D, and MorphCNN have been considered to compare the experimental results. Some of the representative works for each above are as follows; Cloud Implementation of Logistic Regression for HSIC [321], [327], [328] 10-crossvalidation process to compute the overall, average and kappa (κ) accuracy for comparison purposes. For instance, let us assume the case of Pavia University results, for this particular case, the work [196] has the highest average, overall and kappa (κ) accuracies which are 95.51%, 93.95%, and 93.95% respectively in comparison with the average, overall and kappa (κ) accuracies for other comparative works; 92.55%, 89.94%, 89.9% for [325]…”
Section: B Experimental Results On Disjoint Train/test Samplesmentioning
confidence: 99%
“…Class RF [75] MLR [321] SVM [322] MLP [69] RNN [70] LSTM [323] GRU [324] CNN-1D [218] CNN-2D [325] CNN-3D [326] HybridSN [213] MorphCNN [196 CNN-1D, CNN-2D, CNN-3D, and MorphCNN have been considered to compare the experimental results. Some of the representative works for each above are as follows; Cloud Implementation of Logistic Regression for HSIC [321], [327], [328] 10-crossvalidation process to compute the overall, average and kappa (κ) accuracy for comparison purposes. For instance, let us assume the case of Pavia University results, for this particular case, the work [196] has the highest average, overall and kappa (κ) accuracies which are 95.51%, 93.95%, and 93.95% respectively in comparison with the average, overall and kappa (κ) accuracies for other comparative works; 92.55%, 89.94%, 89.9% for [325]…”
Section: B Experimental Results On Disjoint Train/test Samplesmentioning
confidence: 99%
“…These methods are available on [5] 2 . In particular, the methods considered include: multinomial logistic regression (MLR) [35], SVM with radial basis function [25], gated recurrent unit (GRU) [36], long short term memory (LSTM) [37], CNN-1D [38], CNN-2D [5] and CNN-3D [39], [40]. Moreover, to feed spatial-based models, a spatial neighborhood of size 11×11 has been considered to create patches for all the HSI datasets.…”
Section: B Experimental Settingsmentioning
confidence: 99%
“…Meanwhile, we list the prediction accuracy of each category in comparisons. The compared methods include classical methods, such as MLR [17], SVM [35], and LSTM [36], and recent proposed deep learning methods, such as ResNet [18], C-Net [26] M-Net [19], E-FCN [40], SSRN [49], and ASK-Net [38]. The comparisons on IndianPines, PaviaU, and KSC are shown in Table 10, 11, and 12, respectively.…”
Section: Comparisons With Existing Methods With Disjoint Deviation St...mentioning
confidence: 99%