Heart Disease Prediction with PCA and SRP
Bandari Sai Santosh1, Dharma Sahith Reddy2, M Sai Vardhan3, Dr. Shaik Subhani4
1Bandari Sai Santosh, Student, Department of Information Technology, Sreenidhi Institute of Science and Technology (Autonomous), Hyderabad (Telangana), India.
2Dharma Sahith Reddy, Student, Department of Information Technology, Sreenidhi Institute of Science and Technology (Autonomous), Hyderabad (Telangana), India.
3M Sai Vardhan, Student, Department of Information Technology, Sreenidhi Institute of Science and Technology (Autonomous), Hyderabad (Telangana), India.
4Dr. Shaik Subhani, Associate Professor, Department of Information Technology, Sreenidhi Institute of Science and Technology (Autonomous), Hyderabad (Telangana), India.
Manuscript received on 18 April 2019 | Revised Manuscript received on 25 April 2019 | Manuscript published on 30 April 2019 | PP: 1279-1282 | Volume-8 Issue-4, April 2019 | Retrieval Number: D6603048419/19©BEIESP
Open Access | Ethics and 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: In this expeditiously modern world, it all depends on how effectively the data can be maintained and utilized for a suitable purpose. Handling such a large quantity of dynamic data is not at all an easy task. On the contrary, we can use classification techniques, which is purely for building the relationships among huge databases by easily predicting the outcomes by considering the type of relationship. This kind of techniques plays an essential role in every aspect of science and engineering, for example, human services, education, web-based businesses. In the Health maintenance industry, all the data mining techniques are most part utilized for malady prediction. The main goal in this work attempts deeply to anticipate the occurrence of coronary disease with reduced attributes in the dataset. In this case, 14 characteristics are associated with anticipating coronary illness. Following the process, Five classifiers like Classification by clustering, Support Vector Machine, Naive Bayes, Random Forest, Decision Tree are utilized to anticipate the diagnostic influence of heart disease once after reducing the range of characteristics.
Keywords: Clustering, Decision Tree, Naive Bayes, Principal Component Analysis, Random Forest, Sparse Random Projection, Support Vector Machine.
Scope of the Article: Clustering