Missing Value Imputation using Refined Mean Substitution
In a previous work, it was clearly shown that the performance of the very simple imputation method based on Most Common Attribute Value called MC gave performance better than that of several complex imputation algorithms. And in that work [1] it was shown that the performance of MC was almost equal to that of best performing imputation method called Event Covering (EC). So in this work, It is tried to improve the performance of the simple imputation method MC and proposed a new algorithm.
The performance of the proposed algorithm has been compared with the other simple and efficient imputation methods. The performance has been measured with respect to different rate or different percentage of missing values in the data set. To evaluate the performance, the standard WDBC data set has been used. The proposed algorithm performed very well and the arrived results were more significant and comparable.
Keywords: Datamining, Preprocessing, Missing Value
Download Full-Text
ABOUT THE AUTHORS
R. S. Somasundaram
R.S. SomaSundaram holds B.Sc(Mathematics), M.C.A., I.C.W.A(I), M.Phil. At present he is pursuing his Ph.D under the able guidance of Dr. R. Nedunchezhian. He is serving as an Associate Professor in the department of Computer Applications, Sri Ramakrishna Engineering College, Coimbatore, India. His area of interest includes Data Mining, Data Compression and Finger Print recognition. He is a member of IEEE, IAENG and ISTE. He is having 15 years of teaching experience. He has published 7 research publications in National/International Conference/Journal to his credit.
R. Nedunchezhian
Dr. Nedunchezhian. R. is working as the Professor and Head in the department of Information Technology, Sri Ramakrishna Engineering College, Coimbatore. He has more than 19 years of experience in research and teaching. Currently, he is guiding many Ph.D scholars of the Anna University, Coimbatore, and the Bharathiar University. His research interests are knowledge discovery and data mining, distributed computing, and database security. He has published many research papers in national/international conferences and journals. He has edited a book entitled “Handbook of Research on Soft Computing Applications for Database Technologies: Techniques and Issues” which was published by IGI publications, USA in April, 2010. He is a Life member of Advanced Computing and Communication Society and ISTE.
R. S. Somasundaram
R.S. SomaSundaram holds B.Sc(Mathematics), M.C.A., I.C.W.A(I), M.Phil. At present he is pursuing his Ph.D under the able guidance of Dr. R. Nedunchezhian. He is serving as an Associate Professor in the department of Computer Applications, Sri Ramakrishna Engineering College, Coimbatore, India. His area of interest includes Data Mining, Data Compression and Finger Print recognition. He is a member of IEEE, IAENG and ISTE. He is having 15 years of teaching experience. He has published 7 research publications in National/International Conference/Journal to his credit.
R. Nedunchezhian
Dr. Nedunchezhian. R. is working as the Professor and Head in the department of Information Technology, Sri Ramakrishna Engineering College, Coimbatore. He has more than 19 years of experience in research and teaching. Currently, he is guiding many Ph.D scholars of the Anna University, Coimbatore, and the Bharathiar University. His research interests are knowledge discovery and data mining, distributed computing, and database security. He has published many research papers in national/international conferences and journals. He has edited a book entitled “Handbook of Research on Soft Computing Applications for Database Technologies: Techniques and Issues” which was published by IGI publications, USA in April, 2010. He is a Life member of Advanced Computing and Communication Society and ISTE.
