Improved Medical Diagnosis using Wrapper and Filter Techniques of Feature Selection


Authors : Sonu Rani, Dharminder kumar, Sunita Beniwal.

Volume/Issue : Volume 3 - 2018, Issue 9 - September

Google Scholar : https://goo.gl/DF9R4u

Scribd : https://goo.gl/Qz7JQd

Thomson Reuters ResearcherID : https://goo.gl/3bkzwv

Abstract : Data mining field deals with the discovery of knowledge from enormous amount of data. To solve any problem there should be appropriate knowledge about the problem and technique that we are going to use to solve that problem. But there are many areas where problem identification itself takes a lot of time; medical area is one of them in which diagnosis of diseases takes a lot of time. Till then problem (diseases) flourishes to the extent that it cannot be controlled. So there should be some technique that could help in proper and early diagnosis of diseases. Data mining techniques helps here a lot to improve medical diagnosis. The most prevalent technique for this is feature selection. Although there are many feature selection techniques. In our research work we have used feature selection technique on medical data set where each attribute represent a test that is performed for the diagnosis of diseases. For filtering of attributes we have used Relief f attribute Evaluator to check the worthiness of an attribute, to compare the performance we have used multilayer perceptron classifier where comparison has been made on the basis of accuracy and efficacy of classifier.

Keywords : Relief f Attribute valuator, Multilayer perceptron classifier.

Data mining field deals with the discovery of knowledge from enormous amount of data. To solve any problem there should be appropriate knowledge about the problem and technique that we are going to use to solve that problem. But there are many areas where problem identification itself takes a lot of time; medical area is one of them in which diagnosis of diseases takes a lot of time. Till then problem (diseases) flourishes to the extent that it cannot be controlled. So there should be some technique that could help in proper and early diagnosis of diseases. Data mining techniques helps here a lot to improve medical diagnosis. The most prevalent technique for this is feature selection. Although there are many feature selection techniques. In our research work we have used feature selection technique on medical data set where each attribute represent a test that is performed for the diagnosis of diseases. For filtering of attributes we have used Relief f attribute Evaluator to check the worthiness of an attribute, to compare the performance we have used multilayer perceptron classifier where comparison has been made on the basis of accuracy and efficacy of classifier.

Keywords : Relief f Attribute valuator, Multilayer perceptron classifier.

Never miss an update from Papermashup

Get notified about the latest tutorials and downloads.

Subscribe by Email

Get alerts directly into your inbox after each post and stay updated.
Subscribe
OR

Subscribe by RSS

Add our RSS to your feedreader to get regular updates from us.
Subscribe