Open AccessC3IMD : An Efficient Class-Based Clustering Classifier for Im-putation Intelligent Medical Data
Author(s) -
P. Premalatha,
S. Subasree,
N. Sakthivel
Publication year - 2018
Publication title -
international journal of engineering and technology
Language(s) - English
Resource type - Journals
ISSN - 2227-524X
DOI - 10.14419/ijet.v7i2.27.12717
Subject(s) - imputation (statistics) , cluster analysis , computer science , classifier (uml) , data mining , artificial intelligence , support vector machine , missing data , curse of dimensionality , machine learning , pattern recognition (psychology)
The fast evolution in medical application yields to abundance of huge amount of data in volume and velocity. Due to this heterogeneous medical data generation from clinical trials, its typically not free from missing values. Previously introduced imputation techniques don’t discourse the high spatiality problems and application of distance function that even have curse on high spatiality problem. Thus, there’s a necessity an Efficient and Accurate technique to overcome this problem in Medical Data Analysis. To address the above mentioned issues, this research work proposed an efficient Class-Based Clustering Classifier for Imputation Intelligent Medical Data (C3IMD). This work was implemented in Bio Weka and studied thoroughly. To improve the classification and prediction accuracy, missing data in Medical Data Sets were filled efficiently with the help of proposed Cluster-Classifier Model. The experiments are repeated with various datasets and results are evaluated and compared with existing classifiers WPT-DELM and SVM-DELM. From the results obtained, it was revealed that the proposed Class-Based Clustering Classifier for Imputation Intelligent Medical Data (C3IMD) is outperforming both the existing models in terms of Classification Accuracy, Sensitivity, Specificity and FScore.