Total views : 164

Predicting Lung Disease Severity Evaluation and Comparison of Hybird Decision Tree Algorithm


  • Department of Information Technology, School of Computing Sciences, Vels University, Chennai, India


Objective: To focus on classification algorithms to arrive better prediction model for Lung Disease Severity.

Methods/Statistical analysis: In therapeutic analyses, the part of information mining methodologies is being expanded. Especially Classification calculations are exceptionally useful in arranging the information, which is critical for basic leadership prepare for therapeutic experts. In this paper the analysis is done in the WEKA apparatus on the spiro informational index.

Findings: The paper embarks to make relative assessment of classifiers, for example, J48, Random forest and proposed Hybird Decision Tree(HDT) Algorithm with regards to Spiro dataset to amplify genuine positive rate and limit false positive rate of defaulters as opposed to accomplishing just higher grouping exactness utilizing WEKA instrument. The tests comes about appeared in this paper are about grouping exactness, affectability and specificity.

Application/Improvements: The outcomes created on this dataset likewise demonstrate that the productivity and exactness of J48 is superior to anything other choice tree classifiers. J48 develops purge branches, it is the most urgent stride for govern era in J48. In more often than not this approach over fits the preparation cases with boisterous information. The proposed Hybird Decision Tree (HDT) Algorithm demonstrates great exactness in less time.


Decision Tree, Pulmonary Function Test Means, Spirometry Data, Hybird Decision Tree Algorithm, J48 Algorithm.

Full Text:

 |  (PDF views: 0)


  • K.Rohini, G. Suseendran. Aggregated k means clustering and decision tree. Indian Journal of Science and Technology.2016; 9(44), 1-6.
  • Gareth James, Witten Daniela, Hastie Trevor, Tibshirani Robert. An Introduction to Statistical Learning. New York: Springer. 2015, 315.
  • J. Quinlan. Induction of decision trees. Machine Learning. 1986; 1, 81—106.
  • J. Quinlan. C4.5: programs for machine learning. San Mateo, CA: Morgan Kaufmann; 1993.
  • L. Breiman, J. H. Friedman, R.A. Olshen, C.J. Stone. Classification and regression trees. Monterey, CA: Wadsworth & Brooks/Cole Advanced Books & Software. 1984.
  • M.D. Eisner, Nicholas Anthonisen, David Coultas, Nino Kuenzli, Rogelio Perez-Padilla, Dirkje Postma, Isabelle Romieu, E.K. Silverman, J.R. Balmes. Novel risk factors and the global burden of chronic obstructive pulmonary disease(on behalf of the environmental and occupational health assembly committee on nonsmoking COPD) .American Journal Of Respiratory And Critical Care Medicine. 2010; 182, 1-26.
  • M.H. Danham, S. Sridhar. Data mining, Introductory and Advanced Topics. Pearson education. 1st edition. 2006.
  • WHO - PHE health topics-2016. http:// Date Accessed: 27/09/2016.
  • Wenke Lee, S.J. Stolfo, K.W. Mok. A data mining framework for building intrusion detection models. Security and Privacy.1999, Proceedings of the 1999 IEEE Symposium on. 1999.
  • Aman Kumar Sharma, Suruchi Sahni. A comparative study of classification algorithms for spam email data analysis. IJCSE. 2011; 3(5), 1890-1895.
  • J.R. QUINLAN (munnari! nswitgould.oz! quinlan@ on induction of decision trees, centre for advanced computing sciences. New South Wales Institute of Technology, Sydney. 2007.
  • Nishkam Ravi, Nikhil Dadekar, Preetham Mysore, M.L. Littman. Activity recognition from accelerometer data. American Association for Artificial Intelligence, 2005.
  • Clemens Lombriser, N.B. Bharatula, Daniel Roggen, Gerhard Tr¨oster. On-body activity recognition in a dynamic sensor network. In BodyNets ’07: Proceedings of the ICST 2nd international conference on Body area networks. ICST, Brussels, Belgium. 2007, 1-6.


  • There are currently no refbacks.