|Effective Heart Disease Prediction Model for Feature Extraction Model using Data Mining Classification Algorithm|
|MOHANAPRIYA .D, SHANTHI . S|
|Cite This Article:|
Effective Heart Disease Prediction Model for Feature Extraction Model using Data Mining Classification Algorithm, International Journal of Innovative Research in Technology(www.ijirt.org) ,ISSN: 2349-6002 ,Volume 5 ,Issue 12 ,Page(s):554-563 ,May 2019 ,Available :IJIRT148138_PAPER.pdf
|Mobility, load balancing, MCC, cyber foraging|
|Data mining is the process of discovering interesting knowledge, such as patterns, associations, changes, anomalies and significant structures from large amounts of data stored in databases and data warehouses. The most basic definition of data mining is the analysis of large data sets to discover patterns and use those patterns to forecast or predict the likelihood of future events. Data Mining is one of the most critical aspects of automated disease diagnosis and disease prediction. It involves developing data mining algorithms and techniques to analyze medical data. In present, heart disease has excessively increased and heart diseases are becoming one of the most fatal diseases in several countries. In this paper, heart patient datasets are investigate for building classification models in order to predict heart diagnosis. This paper implements feature model construction and comparative analysis for improving prediction accuracy of heart disease in three phases. In first phase, normalization algorithms are applied on the heart patient datasets collected from UCI repository. In second phase, by the use of HCR-PSO (Highly Co-Related Attribute Practical Swarm Optimization) feature selection, using a subset (data) of heart patient from whole normalized heart patient datasets is obtained which comprises only significant attributes and then applying selected classification algorithms on obtained, significant subset of attributes. Third phase, classification algorithm KNN, Random forest, J48, SVM, Bayesian network and MLP algorithm is considered as the better performance algorithm, because it gives higher accuracy in respective to other classification analytical Model before applying HCR-PSO feature selection. But, J48 algorithm is considered as the better performance algorithm after applying HCR-PSO feature selection. In third phase, the results of classification algorithms with and MAE and RMSE validation metric are compared with each other. The results obtained from our experiments indicate that J48 algorithm outperformed all other techniques with the help of feature selection with an accuracy of 94.40%.|
|Unique Paper ID: 148138|
Publication Volume & Issue: Volume 5, Issue 12
Page(s): 554 - 563
|Article Preview & Download|
Virtual Instrumentation: An oscilloscope based on ...
Paper ID : IJIRT148798
Heat Transfer Augmentation Using Twisted Tape Inse...
Paper ID : IJIRT148786
SOFTWARE ARCHITECTURAL STYLES IN THE INTERNET OF T...
Paper ID : IJIRT148785
Comprehensive Analysis of Energy Aware Clustering ...
Paper ID : IJIRT148784
Performance Analysis of Solar Water Heater Evacuat...
Paper ID : IJIRT148783