Matches in SemOpenAlex for { <https://semopenalex.org/work/W4380147752> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W4380147752 endingPage "577" @default.
- W4380147752 startingPage "564" @default.
- W4380147752 abstract "Hyperspectral Image (HSI) has many narrow and continuous spectral bands. There are many problems with the original HSI. For example, the classification accuracy of the test data is affected by the curse of dimensionality problem because the image bands are highly correlated in both space and time. So, dimensionality reduction is done and improved the classification result. In this paper, a deep convolutional network is suggested to reduce the dimensionality of HSI classification by considering both spectral and spatial features. When combined factor analysis and mRMR are used, spectral features are reduced, while 2D wavelet CNN reduces spatial features. A wavelet CNN is an extension of a 2D CNN that can be used to classify high-resolution images. Wavelet CNNs also use layered wavelet transformations to pull out spectral features. A wavelet CNN is easier to calculate than a 3D CNN or a 2D-3D CNN. In the next step, the spectral features are connected to the two-dimensional CNN to get the spatial features, creating a spatial-spectral feature vector. It makes a model that can accurately classify HSI data at multiple resolutions. As part of the HSI classification, we used data sets from the Pavia University and Salinas Scene dataset to see how well the two methods work together. In two datasets, the proposed Expanded 2DNET did better than the handcrafted methods, according to the experiment." @default.
- W4380147752 created "2023-06-11" @default.
- W4380147752 creator A5032219102 @default.
- W4380147752 creator A5058813589 @default.
- W4380147752 creator A5091349741 @default.
- W4380147752 date "2023-01-01" @default.
- W4380147752 modified "2023-10-17" @default.
- W4380147752 title "Spectral–Spatial Feature Reduction for Hyperspectral Image Classification" @default.
- W4380147752 cites W1986924371 @default.
- W4380147752 cites W2009673578 @default.
- W4380147752 cites W2100631457 @default.
- W4380147752 cites W2115976992 @default.
- W4380147752 cites W2118561568 @default.
- W4380147752 cites W2314785379 @default.
- W4380147752 cites W2809374289 @default.
- W4380147752 cites W2894458221 @default.
- W4380147752 cites W2914331134 @default.
- W4380147752 cites W2935967304 @default.
- W4380147752 cites W2937707715 @default.
- W4380147752 cites W2944464490 @default.
- W4380147752 cites W3014740345 @default.
- W4380147752 cites W3025392681 @default.
- W4380147752 cites W3035707407 @default.
- W4380147752 cites W3036266674 @default.
- W4380147752 cites W3038606102 @default.
- W4380147752 cites W3049323006 @default.
- W4380147752 cites W3098418201 @default.
- W4380147752 cites W3103615857 @default.
- W4380147752 cites W3114364469 @default.
- W4380147752 cites W3116252251 @default.
- W4380147752 cites W3124883010 @default.
- W4380147752 cites W3184654054 @default.
- W4380147752 cites W3202767876 @default.
- W4380147752 cites W4293198074 @default.
- W4380147752 doi "https://doi.org/10.1007/978-3-031-34622-4_45" @default.
- W4380147752 hasPublicationYear "2023" @default.
- W4380147752 type Work @default.
- W4380147752 citedByCount "0" @default.
- W4380147752 crossrefType "book-chapter" @default.
- W4380147752 hasAuthorship W4380147752A5032219102 @default.
- W4380147752 hasAuthorship W4380147752A5058813589 @default.
- W4380147752 hasAuthorship W4380147752A5091349741 @default.
- W4380147752 hasConcept C111030470 @default.
- W4380147752 hasConcept C115961682 @default.
- W4380147752 hasConcept C12267149 @default.
- W4380147752 hasConcept C138885662 @default.
- W4380147752 hasConcept C153180895 @default.
- W4380147752 hasConcept C154945302 @default.
- W4380147752 hasConcept C159078339 @default.
- W4380147752 hasConcept C196216189 @default.
- W4380147752 hasConcept C2776401178 @default.
- W4380147752 hasConcept C41008148 @default.
- W4380147752 hasConcept C41895202 @default.
- W4380147752 hasConcept C47432892 @default.
- W4380147752 hasConcept C70518039 @default.
- W4380147752 hasConcept C75294576 @default.
- W4380147752 hasConcept C81363708 @default.
- W4380147752 hasConcept C83665646 @default.
- W4380147752 hasConceptScore W4380147752C111030470 @default.
- W4380147752 hasConceptScore W4380147752C115961682 @default.
- W4380147752 hasConceptScore W4380147752C12267149 @default.
- W4380147752 hasConceptScore W4380147752C138885662 @default.
- W4380147752 hasConceptScore W4380147752C153180895 @default.
- W4380147752 hasConceptScore W4380147752C154945302 @default.
- W4380147752 hasConceptScore W4380147752C159078339 @default.
- W4380147752 hasConceptScore W4380147752C196216189 @default.
- W4380147752 hasConceptScore W4380147752C2776401178 @default.
- W4380147752 hasConceptScore W4380147752C41008148 @default.
- W4380147752 hasConceptScore W4380147752C41895202 @default.
- W4380147752 hasConceptScore W4380147752C47432892 @default.
- W4380147752 hasConceptScore W4380147752C70518039 @default.
- W4380147752 hasConceptScore W4380147752C75294576 @default.
- W4380147752 hasConceptScore W4380147752C81363708 @default.
- W4380147752 hasConceptScore W4380147752C83665646 @default.
- W4380147752 hasLocation W43801477521 @default.
- W4380147752 hasOpenAccess W4380147752 @default.
- W4380147752 hasPrimaryLocation W43801477521 @default.
- W4380147752 hasRelatedWork W1502966458 @default.
- W4380147752 hasRelatedWork W2003131921 @default.
- W4380147752 hasRelatedWork W2053724255 @default.
- W4380147752 hasRelatedWork W2153189372 @default.
- W4380147752 hasRelatedWork W2160451891 @default.
- W4380147752 hasRelatedWork W2163073107 @default.
- W4380147752 hasRelatedWork W2760085659 @default.
- W4380147752 hasRelatedWork W2781623059 @default.
- W4380147752 hasRelatedWork W3012145520 @default.
- W4380147752 hasRelatedWork W3211035526 @default.
- W4380147752 isParatext "false" @default.
- W4380147752 isRetracted "false" @default.
- W4380147752 workType "book-chapter" @default.