Cascading GA &amp;#x00026; CFS for Feature Subset selection in Medical Data Mining

Karegowda, Asha Gowda; Jayaram, M. A.

doi:10.1109/iadcc.2009.4809226

Cited by 32 publications

(9 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In second method, the authors have used GA and Correlation based feature selection (CFS) in a cascaded fashion, where GA rendered global search of attributes with fitness evaluation effected by CFS. Genetic algorithm is used as search method with Correlation based feature selection as subset evaluating mechanism [8]. GA-CFS resulted in following four relevant attributes: Intensity, Std.…”

Section: Resultsmentioning

confidence: 99%

Exudates Detection in Retinal Images using Back Propagation Neural Network

Karegowda¹,

Nasiha²,

Jayaram³

et al. 2011

IJCA

Self Cite

View full text Add to dashboard Cite

Exudates are one of the primary signs of diabetic retinopathy, which is a main cause of blindness and can be prevented with an early screening process. In this paper, authors have attempted to detect exudates using back propagation neural network. The publicly available diabetic retinopathy dataset DIARETDB1 has been used in the evaluation process. To prevent the optic disk from interfering with exudates detection, the optic disk is eliminated. Significant features are identified from the images after preprocessing by using two methods: Decision tree and GA-CFS method are used as input to the BPN model to detect the exudates and non-exudates at pixel level. The results prove that, BPN performance with features identified by Decision tree and GA_CFS approach has outperformed the performance of BPN with all inputs. The BPN classifier best performance was found with Sensitivity of 96.97 %, Specificity of 100% and classification accuracy of 98.45%.

show abstract

Section: Resultsmentioning

confidence: 99%

Exudates Detection in Retinal Images using Back Propagation Neural Network

Karegowda¹,

Nasiha²,

Jayaram³

et al. 2011

IJCA

Self Cite

View full text Add to dashboard Cite

show abstract

“…The most appropriate algorithm for feature or attribute selection is a Genetic algorithm [1] [7], where initially all the attributes are considered as individual subsets and the final combination of the attributes or features are noted as optimal best feature subset. The framework is been proposed here:…”

Section: Proposed Framework For Pre-processingmentioning

confidence: 99%

“…The focus of this work is to demonstrate a Novel Multilayer Perceptron Model to Detect Heart Disease Severity and motivated by the work of Asha Gowda et al [1].…”

Section: Introductionmentioning

confidence: 99%

A parameter based heart disease detection technique using mining technique

2016

IJLTET

View full text Add to dashboard Cite

“…Hybrid K-means and Decision tree [10] achieved the classification accuracy of 92.38% using 10 fold cross validations, cascaded learning system based on Generalized Discriminate analysis (GDA) and Least Square Support Vector Machine (LS_SVM), showed accuracy of 82.05% for diagnosis of Pima dataset [11]. Further authors have achieved classification accuracy of % 72.88 using ANN, 78.21% using DT_ANN where decision tree C4.5 is used to identify relevant features and given as input to ANN [12], 79.50% using Cascaded GA_CFS_ANN, relevant feature identified by Genetic algorithm with Correlation based feature selection is given as input to ANN [13], 77.71% using GA optimized ANN, 84.10% using GA optimized ANN with relevant features identified by decision tree and 84.71% with GA optimized ANN with relevant features identified by GA_CFS [14 ].…”

Section: Clustering Algorithms For Classifying Pima Indian Diabetic Dmentioning

confidence: 99%

An Approach for Prediction of Diabetic disease by using b-Colouring Technique in Clustering Analysis

Lakshmi¹,

Thilagavathi²

2012

International Journal of Applied Mathematical Research

View full text Add to dashboard Cite

Medical Data mining is the process of extorting hidden patterns from medical data. We propose the work which presents the development of clustering techniques for classifying Pima Indian diabetic database (PIDD). Here, clustering algorithm is used for predicting diabetic disease based on graph b-colouring technique. The proposed technique presents a real representation of clusters by dominant objects that assures the inter cluster disparity in a partitioning and used to evaluate the quality of cluster

show abstract

Cascading GA & CFS for Feature Subset selection in Medical Data Mining

Cited by 32 publications

References 5 publications

Exudates Detection in Retinal Images using Back Propagation Neural Network

Exudates Detection in Retinal Images using Back Propagation Neural Network

A parameter based heart disease detection technique using mining technique

An Approach for Prediction of Diabetic disease by using b-Colouring Technique in Clustering Analysis

Contact Info

Product

Resources

About