EVALUATION OF NEURAL NETWORK AND DECISION TREE MODELS FOR DETERMINATION OF CLOUDY REGIONS OF NOAA IMAGES OVER IRAN

Q: How can I download an article?

To download an article from SID, first log in to the site, search for the article title, and click on the 'Download Article' option.

Q: How can I download an ISI article?

To download an ISI article on SID, enter the keyword or article title in the search bar, view the relevant results, click on the desired article, and select the 'Download Article' option.

Q: How can I access the SID database?

To access the SID database, visit SID.ir, create an account, and log in to access scientific resources.

Q: Is downloading articles from SID free?

Some articles on SID are available for free, while others require payment. Details are specified on the article's page.

GHORBANI KH.; KHALILI A.; ALVAIPANAH S.K.; NAKHAEZADEH GH.R.

مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resources

Journal Paper

Paper Information

Journal: Iranian Journal of Remote Sensing & GIS Year:2010 | Volume:1 | Issue:4 Page(s): 87-98

Download Full-Text

Persian Verion

View:

810

Download:

Cites:

Information Journal Paper

Title

EVALUATION OF NEURAL NETWORK AND DECISION TREE MODELS FOR DETERMINATION OF CLOUDY REGIONS OF NOAA IMAGES OVER IRAN

Author(s)

GHORBANI KH. | KHALILI A. | ALVAIPANAH S.K. | NAKHAEZADEH GH.R. | Issue Writer Certificate

Keywords

CLASSIFICATIONQ2

CLOUDY PIXELQ3

DECISION TREEQ1

NEURAL NETWORKQ2

NOAA SATELLITEQ3

Abstract

Precise CLASSIFICATION and recognition of CLOUDY PIXELs are essential to study the earth surface by means of satellite imagery. Among the existing CLASSIFICATION methods, NEURAL NETWORK and DECISION TREE models in Data Mining can be exampled from which several algorithms have been developed. In order to evaluate CLASSIFICATION accuracy of NEURAL NETWORK and DECISION TREE models, eleven algorithms from them were considered. To do this, 40,000 pixels from cloudy, clear, snowy and water bodies in four classes on the calibrated NOAA SATELLITE images were chosen, spectral information of five-band were extracted and NDVI spectral ratio, first band to second band ratio and difference temperature of fifth band from fourth band were calculated and by putting them as input variables, accuracy of each algorithm in CLASSIFICATION of the pixels were compared. Elapsed times to running DECISION TREE models were quicker than NEURAL NETWORKs algorithms and Decisions had been obtained in DECISION TREE models were clear so that these are advantages of the mentioned category models. Finally, after forming of coincidence matrix that showing number of right and wrong in pixel CLASSIFICATION, the results indicated among 11 compared algorithms; C5 algorithm is superior to diagnosis of CLOUDY PIXEL with 43 errors and roughly accuracy of 99.56%. By considering the mentioned advantage, C5 algorithm was introduced as the best algorithm for image CLASSIFICATION and diagnosis of CLOUDY PIXELs.

Cites

No record.

References

No record.

Cite

APA: Copy

GHORBANI, KH., KHALILI, A., ALVAIPANAH, S.K., & NAKHAEZADEH, GH.R.. (2010). EVALUATION OF NEURAL NETWORK AND DECISION TREE MODELS FOR DETERMINATION OF CLOUDY REGIONS OF NOAA IMAGES OVER IRAN. REMOTE SENSING & GIS, 1(4), 87-98. SID. https://sid.ir/paper/184199/en

Vancouver: Copy

GHORBANI KH., KHALILI A., ALVAIPANAH S.K., NAKHAEZADEH GH.R.. EVALUATION OF NEURAL NETWORK AND DECISION TREE MODELS FOR DETERMINATION OF CLOUDY REGIONS OF NOAA IMAGES OVER IRAN. REMOTE SENSING & GIS[Internet]. 2010;1(4):87-98. Available from: https://sid.ir/paper/184199/en

IEEE: Copy

KH. GHORBANI, A. KHALILI, S.K. ALVAIPANAH, and GH.R. NAKHAEZADEH, “EVALUATION OF NEURAL NETWORK AND DECISION TREE MODELS FOR DETERMINATION OF CLOUDY REGIONS OF NOAA IMAGES OVER IRAN,” REMOTE SENSING & GIS, vol. 1, no. 4, pp. 87–98, 2010, [Online]. Available: https://sid.ir/paper/184199/en

Related Journal Papers