Comparison Of K Nearest Neighbours And Regression Tree Classifiers Used With Clonal Selection Algorithm To Diagnose Haematological Diseases
Journal Title: AJIT-e: Bilişim Teknolojileri Online Dergisi - Year 2014, Vol 5, Issue 16
Abstract
The aim of this study is to develop a method to improve the classification performance by haematological parameters. In classification problems it has been seen that kNN classifier is often used with the clonal selection algorithm. In this study unlike other studies Gini algorithm is performed instead of kNN classification algorithm and higher success rate is obtained. According to the World Health Organisation’s data nearly 10% of women in the world are anaemia. Anaemia is a disease that disrupts life quality and results in serious effects if not cured. Iron deficiency anaemia is the most common type of anaemia and women suffers this disease comparatively to men. Therefore, in this study, anaemia was preferred as a sample application. It is expected to reach successful results in diagnosis of other diseases by looking at haematological parameters with the proposed method. At the end of the study success ratios of different methods are compared by Receiver Operating Characteristics analysis method. While accuracy in memory-based classification is found as 96%, accuracy in regression tree method classification is 98.73%. Using Gini algorithm instead of kNN a higher success ratio is achieved so CSA surpassed ANN’s success ratio.
Authors and Affiliations
Burcu Yavuz, Tuba Yıldız, Nilüfer Yurtay, Ziynet Pamuk
Keywords
Related Articles
- EP ID EP95016
- DOI 10.5824/1309‐1581.2014.3.001.x
- Views 130
- Downloads 0
Tendency Of Usage Of Social Media Tools By The Public Relations Practitioners: An Evaluation On Turkeys 500 Biggest Industrial Corporations
The interactive communication in the artificial environment has widened its limits with the usage of the social media tools and has become an inevitable element of the digital era. The usage of the tools such as s...
Human Computer Interraction In RFID Technology
New Media in Terms of Human Computer Interaction
This article identifies the problem domain of human computer interactions in relation to understanding new media. It explores the existing literature in the field, and is an attempt to identify what new media is, what it...
Comparison Of K Nearest Neighbours And Regression Tree Classifiers Used With Clonal Selection Algorithm To Diagnose Haematological Diseases
The aim of this study is to develop a method to improve the classification performance by haematological parameters. In classification problems it has been seen that kNN classifier is often used with the clonal sel...
Evaluation of Accommodation Companies Recreation Activities in İstanbul
Recreation activities represent quality of company, image and attractiveness for both staying guests and day use guests. At the same time recreation can be important income source for accommodation companies. This study...