Optimizing land use classification using decision tree approaches

Tribikram Pradhan, Vaibhav Walia, Rohini Kapoor, Sameer Saran

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Supervised classification is one of the important tasks in remote sensing image interpretation, in which the image pixels are classified to various predefined land use/land cover classes based on the spectral reflectance values in different bands. In reality some classes may have very close spectral reflectance values that overlap in feature space. This produces spectral confusion among the classes and results in inaccurate classified images. To remove such spectral confusion one requires extra spectral and spatial knowledge. This report presents a decision tree classifier approach to extract knowledge from spatial data in form of classification rules using Gini Index and Shannon Entropy (Shannon and Weaver, 1949) to evaluate splits. This report also features calculation of optimal dataset size required for rule generation, in order to avoid redundant Input/output and processing.

Original languageEnglish
Title of host publication2014 International Conference on Data Mining and Intelligent Computing, ICDMIC 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781479946754
DOIs
Publication statusPublished - 12-11-2014
Event2014 International Conference on Data Mining and Intelligent Computing, ICDMIC 2014 - Delhi, India
Duration: 05-09-201406-09-2014

Conference

Conference2014 International Conference on Data Mining and Intelligent Computing, ICDMIC 2014
CountryIndia
CityDelhi
Period05-09-1406-09-14

Fingerprint

Land Use
Decision trees
Decision tree
Land use
Remote sensing
Classifiers
Entropy
Reflectance
Pixels
Gini Index
Rule Generation
Processing
Land Cover
Supervised Classification
Classification Rules
Shannon Entropy
Remote Sensing Image
Spatial Data
Inaccurate
Feature Space

All Science Journal Classification (ASJC) codes

  • Theoretical Computer Science
  • Information Systems
  • Software

Cite this

Pradhan, T., Walia, V., Kapoor, R., & Saran, S. (2014). Optimizing land use classification using decision tree approaches. In 2014 International Conference on Data Mining and Intelligent Computing, ICDMIC 2014 [6954256] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICDMIC.2014.6954256
Pradhan, Tribikram ; Walia, Vaibhav ; Kapoor, Rohini ; Saran, Sameer. / Optimizing land use classification using decision tree approaches. 2014 International Conference on Data Mining and Intelligent Computing, ICDMIC 2014. Institute of Electrical and Electronics Engineers Inc., 2014.
@inproceedings{de9831eec33e4d37b516298fd32e1e93,
title = "Optimizing land use classification using decision tree approaches",
abstract = "Supervised classification is one of the important tasks in remote sensing image interpretation, in which the image pixels are classified to various predefined land use/land cover classes based on the spectral reflectance values in different bands. In reality some classes may have very close spectral reflectance values that overlap in feature space. This produces spectral confusion among the classes and results in inaccurate classified images. To remove such spectral confusion one requires extra spectral and spatial knowledge. This report presents a decision tree classifier approach to extract knowledge from spatial data in form of classification rules using Gini Index and Shannon Entropy (Shannon and Weaver, 1949) to evaluate splits. This report also features calculation of optimal dataset size required for rule generation, in order to avoid redundant Input/output and processing.",
author = "Tribikram Pradhan and Vaibhav Walia and Rohini Kapoor and Sameer Saran",
year = "2014",
month = "11",
day = "12",
doi = "10.1109/ICDMIC.2014.6954256",
language = "English",
booktitle = "2014 International Conference on Data Mining and Intelligent Computing, ICDMIC 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

Pradhan, T, Walia, V, Kapoor, R & Saran, S 2014, Optimizing land use classification using decision tree approaches. in 2014 International Conference on Data Mining and Intelligent Computing, ICDMIC 2014., 6954256, Institute of Electrical and Electronics Engineers Inc., 2014 International Conference on Data Mining and Intelligent Computing, ICDMIC 2014, Delhi, India, 05-09-14. https://doi.org/10.1109/ICDMIC.2014.6954256

Optimizing land use classification using decision tree approaches. / Pradhan, Tribikram; Walia, Vaibhav; Kapoor, Rohini; Saran, Sameer.

2014 International Conference on Data Mining and Intelligent Computing, ICDMIC 2014. Institute of Electrical and Electronics Engineers Inc., 2014. 6954256.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Optimizing land use classification using decision tree approaches

AU - Pradhan, Tribikram

AU - Walia, Vaibhav

AU - Kapoor, Rohini

AU - Saran, Sameer

PY - 2014/11/12

Y1 - 2014/11/12

N2 - Supervised classification is one of the important tasks in remote sensing image interpretation, in which the image pixels are classified to various predefined land use/land cover classes based on the spectral reflectance values in different bands. In reality some classes may have very close spectral reflectance values that overlap in feature space. This produces spectral confusion among the classes and results in inaccurate classified images. To remove such spectral confusion one requires extra spectral and spatial knowledge. This report presents a decision tree classifier approach to extract knowledge from spatial data in form of classification rules using Gini Index and Shannon Entropy (Shannon and Weaver, 1949) to evaluate splits. This report also features calculation of optimal dataset size required for rule generation, in order to avoid redundant Input/output and processing.

AB - Supervised classification is one of the important tasks in remote sensing image interpretation, in which the image pixels are classified to various predefined land use/land cover classes based on the spectral reflectance values in different bands. In reality some classes may have very close spectral reflectance values that overlap in feature space. This produces spectral confusion among the classes and results in inaccurate classified images. To remove such spectral confusion one requires extra spectral and spatial knowledge. This report presents a decision tree classifier approach to extract knowledge from spatial data in form of classification rules using Gini Index and Shannon Entropy (Shannon and Weaver, 1949) to evaluate splits. This report also features calculation of optimal dataset size required for rule generation, in order to avoid redundant Input/output and processing.

UR - http://www.scopus.com/inward/record.url?scp=84919344182&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84919344182&partnerID=8YFLogxK

U2 - 10.1109/ICDMIC.2014.6954256

DO - 10.1109/ICDMIC.2014.6954256

M3 - Conference contribution

AN - SCOPUS:84919344182

BT - 2014 International Conference on Data Mining and Intelligent Computing, ICDMIC 2014

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Pradhan T, Walia V, Kapoor R, Saran S. Optimizing land use classification using decision tree approaches. In 2014 International Conference on Data Mining and Intelligent Computing, ICDMIC 2014. Institute of Electrical and Electronics Engineers Inc. 2014. 6954256 https://doi.org/10.1109/ICDMIC.2014.6954256