Volume 10 Issue 3 - May 2018

  • 1. Performance analysis of support vector machine for predict rainfall and heart diseases

    Authors : Kolluru Venkata Nagendra, Dr.m.ussneiah

    Pages : 70-76

    DOI : http://dx.doi.org/10.21172/1.103.13

    Keywords : ClassificationData MiningSupport Vector MachineClassifierNeural NetworksBagging

    Abstract :

    The goal of this paper is to find the challenging pattern of Rain Fall Forecasting and Heart Diseases. The study dealt with two applications one is rainfall forecasting and another one is heart diseases prediction. SVM is good for predicting the Rain Fall Forecasting. Support vector machine (SVM) was applied for Rain Fall forecasting data using Linear kernel model. In this research by using SVM classification method to classify the rainfall datasets and shall be comparing its performance with Multi Layer Perceptron, Naïve Bayes, and Decision Tree classification methods. In this research SVM classification method is also used to build a classification model for a TIFF dataset. The dataset used herein is of Andhra Pradesh rainfall map. The map comprises of Rain fall coverage for various districts. The methodology used classifies the map based on Rain fall coverage. The performance of SVM is calculated using kappa statistics and accuracy parameters and it is established that for the given data set SVM classifies the raster image dataset with great accuracy. Finally, A hybrid classification method encompasses the advantages of the individual classification approaches that it is built upon. In this research we will be examining few popular algorithms used for classifying medical diagnosis data with a hybrid of support vector machines and neural networks. After that we will discuss the performance of these algorithms depending on different parameters and comparing their correct rate in different categories.

    Citing this Journal Article :

    Kolluru Venkata Nagendra, Dr.m.ussneiah, "Performance analysis of support vector machine for predict rainfall and heart diseases", https://www.ijltet.org/journal_details.php?id=932&j_id=4603, Volume 10 Issue 3 - May 2018, 70-76, #ijltetorg