PERFORMANCE ANALYSIS ON DECISION TREE AND SVM CLASSIFICATION WITH REFERENCE TO FLOOD OCCURRENCES IN INDIA
Main Article Content
Abstract
Floods are pervasive catastrophic disasters which cause financial damages, lost life and environmental scarcity. Flood damage estimation is one of the important factors to the way in the depth of the flood and predicts the future damages. Data mining classification techniques to discover patterns and sequences will use to predict the zones that depiction to flood. A data of flood damages for twelve years collected from various sources. The classification models of Decision Trees and Support Vector Machine with different kernel functions are taken for the prediction models. The Matlab analytics compare the prediction models indicates the performance of the algorithm has much better accuracy. Experiments confirm that the Support Vector Machine with Quadratic kernel function is more accurate in finding the prediction pattern. The accuracy and visualization also suggest that flood prediction which the outcome will goal to better manage floods all the way through preclusion, fortification and catastrophe.
Downloads
Download data is not yet available.
Article Details
Section
Articles
COPYRIGHT
Submission of a manuscript implies: that the work described has not been published before, that it is not under consideration for publication elsewhere; that if and when the manuscript is accepted for publication, the authors agree to automatic transfer of the copyright to the publisher.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work
- The journal allows the author(s) to retain publishing rights without restrictions.
- The journal allows the author(s) to hold the copyright without restrictions.