Data Mining using Meta Heuristic Approaches for Detecting Hepatitis
Neenu R S1, Greeshma G Vijayan2
1Neenu R S, M.Tech Scholar ,Department of Computer Science and Engineering, LBS Institute of Technology for Women, Thiruvananthapuram (Kerala), India.
2Greeshma G Vijayan, Assistant Professor, Department of Computer Science and Engineering, LBS institute of Technology for Women, Thiruvananthapuram (Kerala), India.
Manuscript received on 13 August 2016 | Revised Manuscript received on 20 August 2016 | Manuscript Published on 30 August 2016 | PP: 163-167 | Volume-5 Issue-6, August 2016 | Retrieval Number: F4711085616/16©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Clinical Data Mining involves the process of extracting, analyzing and finding the available data for clinical decision making. Mining data from clinical data set is not an easy task as they are inserted manually. In this paper, a solution for accurately predicting the presence or absence of hepatitis is proposed. The proposed technique is applied on clinical data sets taken from University of California at Irvine (UCI) machine learning repository. The proposed system contains two main subsystems for preprocessing and classifying. In the preprocessing subsystem the missing values in the data set is handled using missing data imputation methods like litwise deletion or mean/mode imputation method. If the percentage of missing values in a tuple is greater than 25%, then the tuple is rejected from the dataset else it was imputed by the most frequently used value. After handling the missing value, the relevant attributes are selected using meta-heuristic approaches like Particle Swarm Optimization (PSO) is used for feature selection. The reducts obtained after preprocessing are fed into the classification. In the classification subsystem the selected reducts are trained and tested using back propagation neural network. This paper aims at accurate prediction of diseases by analyzing clinical data sets.
Keywords: Back Propagation Neural Network, Clinical Data Mining, Particle Swarm Optimization (PSO), University Of California At Irvine (UCI).
Scope of the Article: Neural Network