• Dr S Subasree
• P Premalatha
• Dr N K Sakthivel

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 C3IMD) is outperforming both the existing models in terms of Classification Accuracy, Sensitivity, Speci-ficity and FScore. The Error Rate was analyzed and measured and observed that Error Rate observed in C3IMD Classifier. Thus to improve the FScore value, some modifications are made in our Classifier C3IMD to reduce Error Rate. The proposed Classifier is called as Improved Class-Based Clustering Classifier (ICBCC). From the results, it was noticed that the proposed ICBCC is outperforming C3IMD in term of FScore.

Classification; Clustering; Hybrid classifier; Imputation; Medical Data; SVM; DELM.

"Improved Class-Based Clustering Classifier for Imputation Intelligent Medical Data", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 6, page no.907-912, June 2019, Available :http://www.jetir.org/papers/JETIR1907887.pdf

"Improved Class-Based Clustering Classifier for Imputation Intelligent Medical Data", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 6, page no. pp907-912, June 2019, Available at : http://www.jetir.org/papers/JETIR1907887.pdf