Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal IAES International Journal of Artificial Intelligence (IJ-AI)
Supaporn Chai-Arayalert
Faculty of Science and Industrial Technology, Prince of Songkla University, Surat Thani Campus
Computer Science & IT Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
River classification and change detection from landsat images by using a river classification toolbox Supattra Puttinaovarat; Aekarat Saeliw; Siwipa Pruitikanee; Jinda Kongcharoen; Supaporn Chai-Arayalert; Kanit Khaimook; Paramate Horkaew
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 10, No 4: December 2021
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v10.i4.pp948-959

Abstract

Water bodies especially rivers are vital to existence of all lifeforms on Earth. Therefore, monitoring river areas and water bodies is essential. In the past, the monitoring relied essentially on manpower in surveying individual areas. However, there are limitations associated wih such surveys, e.g., tremendous amount of time and labour involved in expeditions. Presently, there have been accelerated development in remote sensing (RS) and artificial intelligence (AI) technology, particularly for change monitoring and detection in different areas globally. This research presents technical development of a toolbox for rivers classification and their change detection from Landsat images, by using water index analysis and four machine learning algorithms, which are K-Means, ISODATA, maximum likelihood classification (MLC), and support vector machine (SVM). Experimental findings indicated that all presented techniques were effective in detecting hydrological changes. The most accurate algorithm, nevertheless, for river classification was the SVM, with accuracy of 96.89%, precision of 98.61%, recall of 96.59%, and F-measure of 97.59%. Herein, it was demonstrated, in addition, that the developed toolbox was versatile and could be applied in rapid river change detection in other areas.
Co-Authors Aekarat Saeliw Jinda Kongcharoen Kanit Khaimook Paramate Horkaew Siwipa Pruitikanee Supattra Puttinaovarat