Point Biserial Correlated Feature Selection of Weather Data
Pooja S.B1, R.V Siva Balan2
1Pooja S.B, Department of Computer Science, Noorul Islam Centre for Higher Education, Kumaracoil , Tamil Nadu, India.
2R.V Siva Balan, Department of MCA, Noorul Islam Centre for Higher Education, Kumaracoil ,Tamil Nadu, India.
Manuscript received on July 20, 2019. | Revised Manuscript received on August 10, 2019. | Manuscript published on August 30, 2019. | PP: 1854-1857 | Volume-8 Issue-6, August 2019. | Retrieval Number: F7891088619/2019©BEIESP| DOI: 10.35940/ijeat.F7891.088619
Open Access | Ethics and Policies | Cite | Mendeley
© 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: Big data is said to be huge amount of data. These data’s may be either structured or unstructured data. It is used for performing prediction in many fields and one among them is weather forecasting. Many feature selection techniques has been introduced but all these techniques failed to get accurate result. In order to improve weather prediction with less complexity, a Point Biserial Correlated Feature Selection (PBCFS) technique is introduced. The big weather dataset comprises the ‘n’ numbers of features. Initially, the PBCFS technique uses a point biserial correlation coefficient to determine relevant feature or irrelevant features among the several features. These relevant features which is selected with the help of this feature selection method can be used for clustering, classification or any other method to perform prediction. The polytomous (i.e. different classes) regression function analyzes the input data with the selected features to provide the significant results as output. Experimental evaluation of proposed PBCFS technique and existing methods are carried out using a big weather dataset. The result shows that we get the output with high feature selection accuracy.
Keywords: Big data, weather forecasting, feature selection.