Band selection using spectral and spatial information in particle swarm optimization for hyperspectral image classification
Abstract Dimensionality reduction (DR) is an effective preprocessing step in hyperspectral image (HSI) analysis. A particle swarm optimization (PSO)-based unsupervised DR method is proposed in the present paper where spectral divergence as well as spatial gradient information is used in selecting in...
Ausführliche Beschreibung
Gespeichert in:
| Autor*in: |
Paul, Arati [verfasserIn] |
|---|
| Format: |
E-Artikel |
|---|---|
| Sprache: |
Englisch |
| Erschienen: |
2022 |
|---|
| Schlagwörter: |
|---|
| Anmerkung: |
© The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022 |
|---|
| Übergeordnetes Werk: |
Enthalten in: Soft Computing - Springer-Verlag, 2003, 26(2022), 6 vom: 12. Feb., Seite 2819-2834 |
|---|---|
| Übergeordnetes Werk: |
volume:26 ; year:2022 ; number:6 ; day:12 ; month:02 ; pages:2819-2834 |
| Links: |
|---|
| DOI / URN: |
10.1007/s00500-022-06821-6 |
|---|
| Katalog-ID: |
SPR04636157X |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | SPR04636157X | ||
| 003 | DE-627 | ||
| 005 | 20230507121400.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 220302s2022 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1007/s00500-022-06821-6 |2 doi | |
| 035 | |a (DE-627)SPR04636157X | ||
| 035 | |a (SPR)s00500-022-06821-6-e | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Paul, Arati |e verfasserin |0 (orcid)0000-0003-0422-5656 |4 aut | |
| 245 | 1 | 0 | |a Band selection using spectral and spatial information in particle swarm optimization for hyperspectral image classification |
| 264 | 1 | |c 2022 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022 | ||
| 520 | |a Abstract Dimensionality reduction (DR) is an effective preprocessing step in hyperspectral image (HSI) analysis. A particle swarm optimization (PSO)-based unsupervised DR method is proposed in the present paper where spectral divergence as well as spatial gradient information is used in selecting informative bands. In general, HSI is negatively affected by low signal-to-noise ratio (SNR). Hence, in the proposed method, a noise filter is applied to minimize the effect of noise in band selection. Clustering is introduced to reduce spatial redundancy and extract distinct patterns from the data. This enables improvement in the computation performance of each iteration in PSO. The proposed method is applied on two standard datasets, and the performance is evaluated using overall classification accuracy. Finally, results are compared with other recent state-of-the-art methods where the proposed method performed reasonably better than other tested methods in terms of consistency and classification accuracy. | ||
| 650 | 4 | |a Band selection |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a Particle swarm optimization |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a Clustering |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a Hyperspectral |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a Unsupervised |7 (dpeaa)DE-He213 | |
| 700 | 1 | |a Chaki, Nabendu |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Soft Computing |d Springer-Verlag, 2003 |g 26(2022), 6 vom: 12. Feb., Seite 2819-2834 |w (DE-627)SPR006469531 |7 nnns |
| 773 | 1 | 8 | |g volume:26 |g year:2022 |g number:6 |g day:12 |g month:02 |g pages:2819-2834 |
| 856 | 4 | 0 | |u https://dx.doi.org/10.1007/s00500-022-06821-6 |z lizenzpflichtig |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a SYSFLAG_A | ||
| 912 | |a GBV_SPRINGER | ||
| 951 | |a AR | ||
| 952 | |d 26 |j 2022 |e 6 |b 12 |c 02 |h 2819-2834 | ||
| author_variant |
a p ap n c nc |
|---|---|
| matchkey_str |
paularatichakinabendu:2022----:adeetouigpcrlnsailnomtoiprilsampiiainohp |
| hierarchy_sort_str |
2022 |
| publishDate |
2022 |
| allfields |
10.1007/s00500-022-06821-6 doi (DE-627)SPR04636157X (SPR)s00500-022-06821-6-e DE-627 ger DE-627 rakwb eng Paul, Arati verfasserin (orcid)0000-0003-0422-5656 aut Band selection using spectral and spatial information in particle swarm optimization for hyperspectral image classification 2022 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022 Abstract Dimensionality reduction (DR) is an effective preprocessing step in hyperspectral image (HSI) analysis. A particle swarm optimization (PSO)-based unsupervised DR method is proposed in the present paper where spectral divergence as well as spatial gradient information is used in selecting informative bands. In general, HSI is negatively affected by low signal-to-noise ratio (SNR). Hence, in the proposed method, a noise filter is applied to minimize the effect of noise in band selection. Clustering is introduced to reduce spatial redundancy and extract distinct patterns from the data. This enables improvement in the computation performance of each iteration in PSO. The proposed method is applied on two standard datasets, and the performance is evaluated using overall classification accuracy. Finally, results are compared with other recent state-of-the-art methods where the proposed method performed reasonably better than other tested methods in terms of consistency and classification accuracy. Band selection (dpeaa)DE-He213 Particle swarm optimization (dpeaa)DE-He213 Clustering (dpeaa)DE-He213 Hyperspectral (dpeaa)DE-He213 Unsupervised (dpeaa)DE-He213 Chaki, Nabendu aut Enthalten in Soft Computing Springer-Verlag, 2003 26(2022), 6 vom: 12. Feb., Seite 2819-2834 (DE-627)SPR006469531 nnns volume:26 year:2022 number:6 day:12 month:02 pages:2819-2834 https://dx.doi.org/10.1007/s00500-022-06821-6 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER AR 26 2022 6 12 02 2819-2834 |
| spelling |
10.1007/s00500-022-06821-6 doi (DE-627)SPR04636157X (SPR)s00500-022-06821-6-e DE-627 ger DE-627 rakwb eng Paul, Arati verfasserin (orcid)0000-0003-0422-5656 aut Band selection using spectral and spatial information in particle swarm optimization for hyperspectral image classification 2022 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022 Abstract Dimensionality reduction (DR) is an effective preprocessing step in hyperspectral image (HSI) analysis. A particle swarm optimization (PSO)-based unsupervised DR method is proposed in the present paper where spectral divergence as well as spatial gradient information is used in selecting informative bands. In general, HSI is negatively affected by low signal-to-noise ratio (SNR). Hence, in the proposed method, a noise filter is applied to minimize the effect of noise in band selection. Clustering is introduced to reduce spatial redundancy and extract distinct patterns from the data. This enables improvement in the computation performance of each iteration in PSO. The proposed method is applied on two standard datasets, and the performance is evaluated using overall classification accuracy. Finally, results are compared with other recent state-of-the-art methods where the proposed method performed reasonably better than other tested methods in terms of consistency and classification accuracy. Band selection (dpeaa)DE-He213 Particle swarm optimization (dpeaa)DE-He213 Clustering (dpeaa)DE-He213 Hyperspectral (dpeaa)DE-He213 Unsupervised (dpeaa)DE-He213 Chaki, Nabendu aut Enthalten in Soft Computing Springer-Verlag, 2003 26(2022), 6 vom: 12. Feb., Seite 2819-2834 (DE-627)SPR006469531 nnns volume:26 year:2022 number:6 day:12 month:02 pages:2819-2834 https://dx.doi.org/10.1007/s00500-022-06821-6 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER AR 26 2022 6 12 02 2819-2834 |
| allfields_unstemmed |
10.1007/s00500-022-06821-6 doi (DE-627)SPR04636157X (SPR)s00500-022-06821-6-e DE-627 ger DE-627 rakwb eng Paul, Arati verfasserin (orcid)0000-0003-0422-5656 aut Band selection using spectral and spatial information in particle swarm optimization for hyperspectral image classification 2022 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022 Abstract Dimensionality reduction (DR) is an effective preprocessing step in hyperspectral image (HSI) analysis. A particle swarm optimization (PSO)-based unsupervised DR method is proposed in the present paper where spectral divergence as well as spatial gradient information is used in selecting informative bands. In general, HSI is negatively affected by low signal-to-noise ratio (SNR). Hence, in the proposed method, a noise filter is applied to minimize the effect of noise in band selection. Clustering is introduced to reduce spatial redundancy and extract distinct patterns from the data. This enables improvement in the computation performance of each iteration in PSO. The proposed method is applied on two standard datasets, and the performance is evaluated using overall classification accuracy. Finally, results are compared with other recent state-of-the-art methods where the proposed method performed reasonably better than other tested methods in terms of consistency and classification accuracy. Band selection (dpeaa)DE-He213 Particle swarm optimization (dpeaa)DE-He213 Clustering (dpeaa)DE-He213 Hyperspectral (dpeaa)DE-He213 Unsupervised (dpeaa)DE-He213 Chaki, Nabendu aut Enthalten in Soft Computing Springer-Verlag, 2003 26(2022), 6 vom: 12. Feb., Seite 2819-2834 (DE-627)SPR006469531 nnns volume:26 year:2022 number:6 day:12 month:02 pages:2819-2834 https://dx.doi.org/10.1007/s00500-022-06821-6 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER AR 26 2022 6 12 02 2819-2834 |
| allfieldsGer |
10.1007/s00500-022-06821-6 doi (DE-627)SPR04636157X (SPR)s00500-022-06821-6-e DE-627 ger DE-627 rakwb eng Paul, Arati verfasserin (orcid)0000-0003-0422-5656 aut Band selection using spectral and spatial information in particle swarm optimization for hyperspectral image classification 2022 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022 Abstract Dimensionality reduction (DR) is an effective preprocessing step in hyperspectral image (HSI) analysis. A particle swarm optimization (PSO)-based unsupervised DR method is proposed in the present paper where spectral divergence as well as spatial gradient information is used in selecting informative bands. In general, HSI is negatively affected by low signal-to-noise ratio (SNR). Hence, in the proposed method, a noise filter is applied to minimize the effect of noise in band selection. Clustering is introduced to reduce spatial redundancy and extract distinct patterns from the data. This enables improvement in the computation performance of each iteration in PSO. The proposed method is applied on two standard datasets, and the performance is evaluated using overall classification accuracy. Finally, results are compared with other recent state-of-the-art methods where the proposed method performed reasonably better than other tested methods in terms of consistency and classification accuracy. Band selection (dpeaa)DE-He213 Particle swarm optimization (dpeaa)DE-He213 Clustering (dpeaa)DE-He213 Hyperspectral (dpeaa)DE-He213 Unsupervised (dpeaa)DE-He213 Chaki, Nabendu aut Enthalten in Soft Computing Springer-Verlag, 2003 26(2022), 6 vom: 12. Feb., Seite 2819-2834 (DE-627)SPR006469531 nnns volume:26 year:2022 number:6 day:12 month:02 pages:2819-2834 https://dx.doi.org/10.1007/s00500-022-06821-6 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER AR 26 2022 6 12 02 2819-2834 |
| allfieldsSound |
10.1007/s00500-022-06821-6 doi (DE-627)SPR04636157X (SPR)s00500-022-06821-6-e DE-627 ger DE-627 rakwb eng Paul, Arati verfasserin (orcid)0000-0003-0422-5656 aut Band selection using spectral and spatial information in particle swarm optimization for hyperspectral image classification 2022 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022 Abstract Dimensionality reduction (DR) is an effective preprocessing step in hyperspectral image (HSI) analysis. A particle swarm optimization (PSO)-based unsupervised DR method is proposed in the present paper where spectral divergence as well as spatial gradient information is used in selecting informative bands. In general, HSI is negatively affected by low signal-to-noise ratio (SNR). Hence, in the proposed method, a noise filter is applied to minimize the effect of noise in band selection. Clustering is introduced to reduce spatial redundancy and extract distinct patterns from the data. This enables improvement in the computation performance of each iteration in PSO. The proposed method is applied on two standard datasets, and the performance is evaluated using overall classification accuracy. Finally, results are compared with other recent state-of-the-art methods where the proposed method performed reasonably better than other tested methods in terms of consistency and classification accuracy. Band selection (dpeaa)DE-He213 Particle swarm optimization (dpeaa)DE-He213 Clustering (dpeaa)DE-He213 Hyperspectral (dpeaa)DE-He213 Unsupervised (dpeaa)DE-He213 Chaki, Nabendu aut Enthalten in Soft Computing Springer-Verlag, 2003 26(2022), 6 vom: 12. Feb., Seite 2819-2834 (DE-627)SPR006469531 nnns volume:26 year:2022 number:6 day:12 month:02 pages:2819-2834 https://dx.doi.org/10.1007/s00500-022-06821-6 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER AR 26 2022 6 12 02 2819-2834 |
| language |
English |
| source |
Enthalten in Soft Computing 26(2022), 6 vom: 12. Feb., Seite 2819-2834 volume:26 year:2022 number:6 day:12 month:02 pages:2819-2834 |
| sourceStr |
Enthalten in Soft Computing 26(2022), 6 vom: 12. Feb., Seite 2819-2834 volume:26 year:2022 number:6 day:12 month:02 pages:2819-2834 |
| format_phy_str_mv |
Article |
| institution |
findex.gbv.de |
| topic_facet |
Band selection Particle swarm optimization Clustering Hyperspectral Unsupervised |
| isfreeaccess_bool |
false |
| container_title |
Soft Computing |
| authorswithroles_txt_mv |
Paul, Arati @@aut@@ Chaki, Nabendu @@aut@@ |
| publishDateDaySort_date |
2022-02-12T00:00:00Z |
| hierarchy_top_id |
SPR006469531 |
| id |
SPR04636157X |
| language_de |
englisch |
| fullrecord |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">SPR04636157X</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230507121400.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">220302s2022 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s00500-022-06821-6</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)SPR04636157X</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(SPR)s00500-022-06821-6-e</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Paul, Arati</subfield><subfield code="e">verfasserin</subfield><subfield code="0">(orcid)0000-0003-0422-5656</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Band selection using spectral and spatial information in particle swarm optimization for hyperspectral image classification</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2022</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">© The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract Dimensionality reduction (DR) is an effective preprocessing step in hyperspectral image (HSI) analysis. A particle swarm optimization (PSO)-based unsupervised DR method is proposed in the present paper where spectral divergence as well as spatial gradient information is used in selecting informative bands. In general, HSI is negatively affected by low signal-to-noise ratio (SNR). Hence, in the proposed method, a noise filter is applied to minimize the effect of noise in band selection. Clustering is introduced to reduce spatial redundancy and extract distinct patterns from the data. This enables improvement in the computation performance of each iteration in PSO. The proposed method is applied on two standard datasets, and the performance is evaluated using overall classification accuracy. Finally, results are compared with other recent state-of-the-art methods where the proposed method performed reasonably better than other tested methods in terms of consistency and classification accuracy.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Band selection</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Particle swarm optimization</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Clustering</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Hyperspectral</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Unsupervised</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Chaki, Nabendu</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Soft Computing</subfield><subfield code="d">Springer-Verlag, 2003</subfield><subfield code="g">26(2022), 6 vom: 12. Feb., Seite 2819-2834</subfield><subfield code="w">(DE-627)SPR006469531</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:26</subfield><subfield code="g">year:2022</subfield><subfield code="g">number:6</subfield><subfield code="g">day:12</subfield><subfield code="g">month:02</subfield><subfield code="g">pages:2819-2834</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://dx.doi.org/10.1007/s00500-022-06821-6</subfield><subfield code="z">lizenzpflichtig</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_SPRINGER</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">26</subfield><subfield code="j">2022</subfield><subfield code="e">6</subfield><subfield code="b">12</subfield><subfield code="c">02</subfield><subfield code="h">2819-2834</subfield></datafield></record></collection>
|
| author |
Paul, Arati |
| spellingShingle |
Paul, Arati misc Band selection misc Particle swarm optimization misc Clustering misc Hyperspectral misc Unsupervised Band selection using spectral and spatial information in particle swarm optimization for hyperspectral image classification |
| authorStr |
Paul, Arati |
| ppnlink_with_tag_str_mv |
@@773@@(DE-627)SPR006469531 |
| format |
electronic Article |
| delete_txt_mv |
keep |
| author_role |
aut aut |
| collection |
springer |
| remote_str |
true |
| illustrated |
Not Illustrated |
| topic_title |
Band selection using spectral and spatial information in particle swarm optimization for hyperspectral image classification Band selection (dpeaa)DE-He213 Particle swarm optimization (dpeaa)DE-He213 Clustering (dpeaa)DE-He213 Hyperspectral (dpeaa)DE-He213 Unsupervised (dpeaa)DE-He213 |
| topic |
misc Band selection misc Particle swarm optimization misc Clustering misc Hyperspectral misc Unsupervised |
| topic_unstemmed |
misc Band selection misc Particle swarm optimization misc Clustering misc Hyperspectral misc Unsupervised |
| topic_browse |
misc Band selection misc Particle swarm optimization misc Clustering misc Hyperspectral misc Unsupervised |
| format_facet |
Elektronische Aufsätze Aufsätze Elektronische Ressource |
| format_main_str_mv |
Text Zeitschrift/Artikel |
| carriertype_str_mv |
cr |
| hierarchy_parent_title |
Soft Computing |
| hierarchy_parent_id |
SPR006469531 |
| hierarchy_top_title |
Soft Computing |
| isfreeaccess_txt |
false |
| familylinks_str_mv |
(DE-627)SPR006469531 |
| title |
Band selection using spectral and spatial information in particle swarm optimization for hyperspectral image classification |
| ctrlnum |
(DE-627)SPR04636157X (SPR)s00500-022-06821-6-e |
| title_full |
Band selection using spectral and spatial information in particle swarm optimization for hyperspectral image classification |
| author_sort |
Paul, Arati |
| journal |
Soft Computing |
| journalStr |
Soft Computing |
| lang_code |
eng |
| isOA_bool |
false |
| recordtype |
marc |
| publishDateSort |
2022 |
| contenttype_str_mv |
txt |
| container_start_page |
2819 |
| author_browse |
Paul, Arati Chaki, Nabendu |
| container_volume |
26 |
| format_se |
Elektronische Aufsätze |
| author-letter |
Paul, Arati |
| doi_str_mv |
10.1007/s00500-022-06821-6 |
| normlink |
(ORCID)0000-0003-0422-5656 |
| normlink_prefix_str_mv |
(orcid)0000-0003-0422-5656 |
| title_sort |
band selection using spectral and spatial information in particle swarm optimization for hyperspectral image classification |
| title_auth |
Band selection using spectral and spatial information in particle swarm optimization for hyperspectral image classification |
| abstract |
Abstract Dimensionality reduction (DR) is an effective preprocessing step in hyperspectral image (HSI) analysis. A particle swarm optimization (PSO)-based unsupervised DR method is proposed in the present paper where spectral divergence as well as spatial gradient information is used in selecting informative bands. In general, HSI is negatively affected by low signal-to-noise ratio (SNR). Hence, in the proposed method, a noise filter is applied to minimize the effect of noise in band selection. Clustering is introduced to reduce spatial redundancy and extract distinct patterns from the data. This enables improvement in the computation performance of each iteration in PSO. The proposed method is applied on two standard datasets, and the performance is evaluated using overall classification accuracy. Finally, results are compared with other recent state-of-the-art methods where the proposed method performed reasonably better than other tested methods in terms of consistency and classification accuracy. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022 |
| abstractGer |
Abstract Dimensionality reduction (DR) is an effective preprocessing step in hyperspectral image (HSI) analysis. A particle swarm optimization (PSO)-based unsupervised DR method is proposed in the present paper where spectral divergence as well as spatial gradient information is used in selecting informative bands. In general, HSI is negatively affected by low signal-to-noise ratio (SNR). Hence, in the proposed method, a noise filter is applied to minimize the effect of noise in band selection. Clustering is introduced to reduce spatial redundancy and extract distinct patterns from the data. This enables improvement in the computation performance of each iteration in PSO. The proposed method is applied on two standard datasets, and the performance is evaluated using overall classification accuracy. Finally, results are compared with other recent state-of-the-art methods where the proposed method performed reasonably better than other tested methods in terms of consistency and classification accuracy. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022 |
| abstract_unstemmed |
Abstract Dimensionality reduction (DR) is an effective preprocessing step in hyperspectral image (HSI) analysis. A particle swarm optimization (PSO)-based unsupervised DR method is proposed in the present paper where spectral divergence as well as spatial gradient information is used in selecting informative bands. In general, HSI is negatively affected by low signal-to-noise ratio (SNR). Hence, in the proposed method, a noise filter is applied to minimize the effect of noise in band selection. Clustering is introduced to reduce spatial redundancy and extract distinct patterns from the data. This enables improvement in the computation performance of each iteration in PSO. The proposed method is applied on two standard datasets, and the performance is evaluated using overall classification accuracy. Finally, results are compared with other recent state-of-the-art methods where the proposed method performed reasonably better than other tested methods in terms of consistency and classification accuracy. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022 |
| collection_details |
GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER |
| container_issue |
6 |
| title_short |
Band selection using spectral and spatial information in particle swarm optimization for hyperspectral image classification |
| url |
https://dx.doi.org/10.1007/s00500-022-06821-6 |
| remote_bool |
true |
| author2 |
Chaki, Nabendu |
| author2Str |
Chaki, Nabendu |
| ppnlink |
SPR006469531 |
| mediatype_str_mv |
c |
| isOA_txt |
false |
| hochschulschrift_bool |
false |
| doi_str |
10.1007/s00500-022-06821-6 |
| up_date |
2024-07-03T22:04:08.807Z |
| _version_ |
1803597118240194560 |
| fullrecord_marcxml |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">SPR04636157X</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230507121400.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">220302s2022 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s00500-022-06821-6</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)SPR04636157X</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(SPR)s00500-022-06821-6-e</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Paul, Arati</subfield><subfield code="e">verfasserin</subfield><subfield code="0">(orcid)0000-0003-0422-5656</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Band selection using spectral and spatial information in particle swarm optimization for hyperspectral image classification</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2022</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">© The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract Dimensionality reduction (DR) is an effective preprocessing step in hyperspectral image (HSI) analysis. A particle swarm optimization (PSO)-based unsupervised DR method is proposed in the present paper where spectral divergence as well as spatial gradient information is used in selecting informative bands. In general, HSI is negatively affected by low signal-to-noise ratio (SNR). Hence, in the proposed method, a noise filter is applied to minimize the effect of noise in band selection. Clustering is introduced to reduce spatial redundancy and extract distinct patterns from the data. This enables improvement in the computation performance of each iteration in PSO. The proposed method is applied on two standard datasets, and the performance is evaluated using overall classification accuracy. Finally, results are compared with other recent state-of-the-art methods where the proposed method performed reasonably better than other tested methods in terms of consistency and classification accuracy.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Band selection</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Particle swarm optimization</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Clustering</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Hyperspectral</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Unsupervised</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Chaki, Nabendu</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Soft Computing</subfield><subfield code="d">Springer-Verlag, 2003</subfield><subfield code="g">26(2022), 6 vom: 12. Feb., Seite 2819-2834</subfield><subfield code="w">(DE-627)SPR006469531</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:26</subfield><subfield code="g">year:2022</subfield><subfield code="g">number:6</subfield><subfield code="g">day:12</subfield><subfield code="g">month:02</subfield><subfield code="g">pages:2819-2834</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://dx.doi.org/10.1007/s00500-022-06821-6</subfield><subfield code="z">lizenzpflichtig</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_SPRINGER</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">26</subfield><subfield code="j">2022</subfield><subfield code="e">6</subfield><subfield code="b">12</subfield><subfield code="c">02</subfield><subfield code="h">2819-2834</subfield></datafield></record></collection>
|
| score |
7.3994265 |