Predictive models for hotspots occurrence using decision tree algorithms and logistic regression.

Predictive models for hotspots (active fires) occurrence are essential to develop as one of activities in forest fires prevention in order to minimize damages because of forest fires. This work applied the decision tree algorithms i.e., ID3 and C4.5, as well as logistic regression on spatial data of...

Full description

Saved in:
Bibliographic Details
Main Authors: Sitanggang, Imas Sukaesih, Yaakob, Razali, Mustapha, Norwati, Nuruddin, Ahmad Ainuddin
Format: Article
Language:English
English
Published: Asian Network for Scientific Information 2013
Online Access:http://psasir.upm.edu.my/id/eprint/29146/1/Predictive%20models%20for%20hotspots%20occurrence%20using%20decision%20tree%20algorithms%20and%20logistic%20regression.pdf
http://psasir.upm.edu.my/id/eprint/29146/
http://scialert.net/archivedetails.php?issn=1812-5654&issueno=202
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.upm.eprints.29146
record_format eprints
spelling my.upm.eprints.291462016-02-05T02:10:01Z http://psasir.upm.edu.my/id/eprint/29146/ Predictive models for hotspots occurrence using decision tree algorithms and logistic regression. Sitanggang, Imas Sukaesih Yaakob, Razali Mustapha, Norwati Nuruddin, Ahmad Ainuddin Predictive models for hotspots (active fires) occurrence are essential to develop as one of activities in forest fires prevention in order to minimize damages because of forest fires. This work applied the decision tree algorithms i.e., ID3 and C4.5, as well as logistic regression on spatial data of forest fires for Rokan Hilir District in Riau Province in Indonesia. The data consist of ten explanatory layers (physical, weather and socio-economic data) and a target layer. Target objects in the target layer are hotspots 2008 and non-hotspot points which were randomly generated near hotspots. As many 561 target objects were prepared through several data preprocessing tasks. The results show that the C4.5 algorithm has better performance than the ID3 algorithm in terms of accuracy and the number of generated rules. The C4.5 decision tree has the accuracy of 65.24% with number of generated rules is 35 and the first test attribute of the tree is peatland type. Furthermore, the logistic regression model outperforms the decision tree algorithms with the accuracy of 68.63%. Asian Network for Scientific Information 2013 Article PeerReviewed application/pdf en http://psasir.upm.edu.my/id/eprint/29146/1/Predictive%20models%20for%20hotspots%20occurrence%20using%20decision%20tree%20algorithms%20and%20logistic%20regression.pdf Sitanggang, Imas Sukaesih and Yaakob, Razali and Mustapha, Norwati and Nuruddin, Ahmad Ainuddin (2013) Predictive models for hotspots occurrence using decision tree algorithms and logistic regression. Journal of Applied Sciences, 13 (2). pp. 252-261. ISSN 1812-5654; ESSN: 1812-5662 http://scialert.net/archivedetails.php?issn=1812-5654&issueno=202 10.3923/jas.2013.252.261 English
institution Universiti Putra Malaysia
building UPM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Putra Malaysia
content_source UPM Institutional Repository
url_provider http://psasir.upm.edu.my/
language English
English
description Predictive models for hotspots (active fires) occurrence are essential to develop as one of activities in forest fires prevention in order to minimize damages because of forest fires. This work applied the decision tree algorithms i.e., ID3 and C4.5, as well as logistic regression on spatial data of forest fires for Rokan Hilir District in Riau Province in Indonesia. The data consist of ten explanatory layers (physical, weather and socio-economic data) and a target layer. Target objects in the target layer are hotspots 2008 and non-hotspot points which were randomly generated near hotspots. As many 561 target objects were prepared through several data preprocessing tasks. The results show that the C4.5 algorithm has better performance than the ID3 algorithm in terms of accuracy and the number of generated rules. The C4.5 decision tree has the accuracy of 65.24% with number of generated rules is 35 and the first test attribute of the tree is peatland type. Furthermore, the logistic regression model outperforms the decision tree algorithms with the accuracy of 68.63%.
format Article
author Sitanggang, Imas Sukaesih
Yaakob, Razali
Mustapha, Norwati
Nuruddin, Ahmad Ainuddin
spellingShingle Sitanggang, Imas Sukaesih
Yaakob, Razali
Mustapha, Norwati
Nuruddin, Ahmad Ainuddin
Predictive models for hotspots occurrence using decision tree algorithms and logistic regression.
author_facet Sitanggang, Imas Sukaesih
Yaakob, Razali
Mustapha, Norwati
Nuruddin, Ahmad Ainuddin
author_sort Sitanggang, Imas Sukaesih
title Predictive models for hotspots occurrence using decision tree algorithms and logistic regression.
title_short Predictive models for hotspots occurrence using decision tree algorithms and logistic regression.
title_full Predictive models for hotspots occurrence using decision tree algorithms and logistic regression.
title_fullStr Predictive models for hotspots occurrence using decision tree algorithms and logistic regression.
title_full_unstemmed Predictive models for hotspots occurrence using decision tree algorithms and logistic regression.
title_sort predictive models for hotspots occurrence using decision tree algorithms and logistic regression.
publisher Asian Network for Scientific Information
publishDate 2013
url http://psasir.upm.edu.my/id/eprint/29146/1/Predictive%20models%20for%20hotspots%20occurrence%20using%20decision%20tree%20algorithms%20and%20logistic%20regression.pdf
http://psasir.upm.edu.my/id/eprint/29146/
http://scialert.net/archivedetails.php?issn=1812-5654&issueno=202
_version_ 1643829673695641600
score 13.211869