Traditional decision tree classifiers work with data whose values are known and precise .Here classification of data is done but for un-certain data approximate value is assumed that does not give accurate result. One of the most popular classification models is the decision tree model. Decisions trees are popular because they are practical and easy to understand. In traditional decision-tree classification, a feature of a tuple is either categorical or numerical. Multiple values are formed by Probability Distribution Function (pdf) that represents the uncertainty value. The accuracy of a decision tree classifier can be improved if the pdf is used. Existing decision tree building algorithms are improved to handle data tuples with uncertain values. Pruning techniques are used which improves the efficiency of the construction of decision trees. Proposed system classifies climate data which is uncertain due to measurement errors, to various classes using decision tree.
Cite This Article as:
[Khumesh Patil, Namrata Pagare, Pallavi Narkhede, Prashant Brahmankar (2014); Classifying Climate Data (uncertain) using Decision Tree Int. J. of Adv. Res. 2 (4). 0] (ISSN 2320-5407). www.journalijar.com
Share this article
This work is licensed under a Creative Commons Attribution 4.0 International License.