Focal Interest
Focal Interest
AI Summary of Peer-Reviewed Research

This page presents an AI-generated summary of a published research paper. The original authors did not write or review this article. [See full disclosure ↓]

Publishing process signals: STANDARD — reflects the venue and review process. — venue and review process.

SVM and Wishart classifiers performed almost identically

Engineering research
Photo by Peter Xie on Pexels · Pexels License
Research area:EngineeringMedia TechnologyRemote Sensing in Agriculture

What the study found

Support Vector Machine (SVM) and Wishart classifiers produced almost the same classification accuracy for land-cover mapping over metropolitan Hyderabad. The reported accuracies were 91.08% for SVM and 91.07% for the Wishart classifier.

Why the authors say this matters

The authors state that quantitative assessment of land use and land cover is essential for planning and for using nearby resources properly. They also note that land-cover change is related to global change through interactions with climate, ecosystems, and human activities.

What the researchers tested

The study examined land-cover classification using L-band ALOS PALSAR-2 dual-polarization data over metropolitan Hyderabad. The data were multilooked five times in range and once in azimuth, and speckle was reduced using a refined filter with a 3×3 window kernel. The authors compared two supervised classifiers: Support Vector Machine (SVM) and Wishart classifier.

What worked and what didn't

Both classifiers worked well and gave nearly identical accuracy values. SVM was slightly higher at 91.08%, while the Wishart classifier was 91.07%.

What to keep in mind

The abstract does not describe additional limitations, uncertainty measures, or details beyond the reported comparison and accuracy values.

Key points

  • The study compared SVM and Wishart classifiers for land-cover classification.
  • The data were L-band ALOS PALSAR-2 dual-polarization observations over metropolitan Hyderabad.
  • Reported accuracies were 91.08% for SVM and 91.07% for Wishart.
  • The authors state that land-use and land-cover assessment is important for planning and resource use.
  • No additional limitations are described in the abstract.

Disclosure

Research title:
SVM and Wishart classifiers performed almost identically
Authors:
Dasari Kiran, L. Anjaneyulu
Publication date:
2026-04-20
DOI:
10.14419/ijet.v7i3.29.19195
OpenAlex record:
View
Image credit:
Photo by Peter Xie on Pexels · Pexels License
AI provenance: This post was generated by OpenAI. The original authors did not write or review this post.

More posts