Learning spatial decision tree for geographical classification: A summary of results

Zhe Jiang, Shashi Shekhar, Pradeep Mohan, Joe Knight, Jennifer Corcoran

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

14 Scopus citations

Abstract

Given learning samples from a spatial raster dataset, the geographical classification problem aims to learn a decision tree classifier that minimizes classification errors as well as salt-n-pepper noise. The problem is important in many applications, such as land cover classification in remote sensing and lesion classification in medical diagnosis. However, the problem is challenging due to spatial autocorrelation. Existing decision tree learning algorithms, i.e. ID3, C4.5, CART, produce a lot of salt-n-pepper noise in classification results, due to their assumption that data items are drawn independently from identical distributions. In contrast, we propose a spatial decision tree learning algorithm, which incorporates spatial autocorrelation effect by a new spatial information gain (SIG) measure. The proposed approach is evaluated in a case study on a remote sensing dataset from Chanhassen, MN. Case study results show that the proposed approach outperforms the traditional approach in not only reducing salt-n-pepper noise but also improving classification accuracy.

Original languageEnglish (US)
Title of host publication20th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2012
Pages390-393
Number of pages4
DOIs
StatePublished - Dec 1 2012
Event20th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2012 - Redondo Beach, CA, United States
Duration: Nov 6 2012Nov 9 2012

Publication series

NameGIS: Proceedings of the ACM International Symposium on Advances in Geographic Information Systems

Other

Other20th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2012
CountryUnited States
CityRedondo Beach, CA
Period11/6/1211/9/12

Keywords

  • land cover classification
  • spatial autocorrelation aware decision tree
  • spatial data mining

Fingerprint Dive into the research topics of 'Learning spatial decision tree for geographical classification: A summary of results'. Together they form a unique fingerprint.

Cite this