Big Data Analysis for Diabetes Recognition using Classification Algorithms
S. Kamalakkannan1, R. Thiagarajan2, S. Mathivilasini3, R. Thayammal4
1Dr.S.Kamalakkannan, Associate Professor, Department of, Information Technology, Vels Institute of Science, Technology & Advanced Studies, Chennai.
2R.Thiagarajan, Assistant Professor, Department of, Computer Science, St. Joseph’s College (Arts & Science), Chennai.
3Dr.S.Mathivilasini, Department of, Computer Science, Ethiraj College for Women, Chennai.
4R.Thayammal, Department of, Computer Science, Chennai.
Manuscript received on 1 March 2019 | Revised Manuscript received on 6 March 2019 | Manuscript published on 30 July 2019 | PP: 62-65 | Volume-8 Issue-2, July 2019 | Retrieval Number: A1333058119/19©BEIESP | DOI: 10.35940/ijrte.A1333.078219
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 that paper, we’ve an inclination to project as checking the whole patient ill health victimization Naive Bayes classification and J48 decision tree. As a result of the information, enormous process comes from multiple, heterogeneous, autonomous sources with sophisticated and evolving relationships and continues to grow. So in that, we’ll take results of what proportion share patients get ill health as a positive knowledge and negative knowledge. Huge info is difficult to work with victimization most database management systems and desktop statistics and internal representation packages. The projected shows a huge process model, from the data mining perspective. Victimization classifiers, we’ve an inclination to unit method congenital disease share and values unit showing as a confusion matrix. We’ve an inclination to projected a replacement classification theme which could effectively improve the classification performance inside the situation that employment dataset is out there. During this dataset, we have nearly 1000 patient details. We’ll get all that details from there. Then we have a tendency to unit attending to sensible and unhealthy values square measure victimization naive Bayes classifier and J48 tree.
Index Terms: Big Data, Diabetes, J48 Tree, Naïve Bayes Classification.
Scope of the Article: Classification