Please use this identifier to cite or link to this item: http://nopr.niscair.res.in/handle/123456789/42546
Title: A Model for Accurate Prediction in GeoRSS Data Using Naive Bayes Classifier
Authors: Netti, K
Radhika, Y
Keywords: Data Mining;Classification;Knowledge;Prediction;Accuracy;Naïve Bayes Classifier;GeoRSS;XML;Earthquake
Issue Date: Aug-2017
Publisher: NISCAIR-CSIR, India
Abstract: With new technologies emerging in collecting real-time data especially in earth sciences, the amount of data in terms of capacity and volume is growing rapidly. However, extracting relevant and useful knowledge from that data is vital. In addition, predicting an event depending on the set of features is equally important. One such method for predicting outcome from data is Naïve Bayes Classifier. In this paper, Naïve Bayes Classifier is applied on earthquake data which is available as RSS feed otherwise called as GeoRSS data. The GeoRSS can be mapped onto any GIS software for determining the area of interest. However, if the data is dense identifying a particular area of interest could be very cumbersome. Hence, there is a need for an efficient classifier to identify specific areas of interest from GeoRSS data. This paper proposes an efficient model using Naive Bayes Classifier to predict the outcome in GeoRSS data. It is proved that applying Naïve Bayes Classifier on a data set like GeoRSS, gave better accuracy for identifying an exact location of the earthquake with specific magnitude.
Page(s): 473-476
URI: http://nopr.niscair.res.in/handle/123456789/42546
ISSN: 0975-1084 (Online); 0022-4456 (Print)
Appears in Collections:JSIR Vol.76(08) [August 2017]

Files in This Item:
File Description SizeFormat 
JSIR 76(8) 473-476.pdf92.88 kBAdobe PDFView/Open


Items in NOPR are protected by copyright, with all rights reserved, unless otherwise indicated.