Research Article | OPEN ACCESS
A Review on the Performance of Neural Network Classifier in Health Care Diagnostic System
1M. Nandhini, 2S.N. Sivanandam and 3M. Rajalakshmi
1Computer Science and Engineering, PSG College of Technology
2Computer Science and Engineering, Karpagam College of Engineering
3Computer Science and Engineering and Information Technology, Coimbatore Institute of
Technology, Coimbatore, India
Research Journal of Applied Sciences, Engineering and Technology 2015 9:994-1002
Received: May ‎25, ‎2015 | Accepted: June ‎22, ‎2015 | Published: November 25, 2015
Abstract
In recent times, the classification systems for diagnosing the patient’s disease have received its attention. Neural network is well known classification technique widely applied to health care systems. Health care data diagnosis is a significant task that needs to be accomplished accurately and efficiently. Disease prediction based on patient’s symptoms may lead to wrong assumptions. This study aims in implementing a neural network based Health Care Diagnostic System (HCDS) to predict the likelihood of patient getting a disease based on medical factors. In this study, Multi Layer Perceptron Neural Network (MLPNN) with Back Propagation algorithm (BP) is used to build the HCDS. To improve the accuracy of the diagnosis, MLPNN is constructed using the reduced set of significant Class Association Rules (CAR’s) as training instances instead of datasets. Genetic Algorithm (GA) is employed to generate the reduced set of CAR’s from the health care datasets. Experiments were conducted using six health care datasets from UCI machine learning repository. Based on the experiments, the combination of MLPNN with BP using significant CAR’s as training instances yields promising results in terms of classifier accuracy and training time.
Keywords:
Back Propagation (BP), classification, Class Association Rule (CAR), Genetic Algorithm (GA), Multi Layer Perceptron Neural Network (MLPNN), neural network,
Competing interests
The authors have no competing interests.
Open Access Policy
This article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.
Copyright
The authors have no competing interests.
|
|
|
ISSN (Online): 2040-7467
ISSN (Print): 2040-7459 |
|
Information |
|
|
|
Sales & Services |
|
|
|