Feature Selection with Enhanced Bat Algorithm and Modified Recursive Bayesian Deep Neural Network (MRBDNN) for Temperature Prediction
R. Rajkumar1, A. James Albert2, S.P. Siddique Ibrahim3
1R. Rajkumar, Department of Mathematics, Kumaraguru College of Technology, Coimbatore (Tamil Nadu), India.
2A. James Albert, Department of Mathematics, Kumaraguru College of Technology, Coimbatore (Tamil Nadu), India.
3S.P. Siddique Ibrahim, Assistant Professor, Department of Computer Science and Engineering, Kumaraguru College of Technology, Coimbatore (Tamil Nadu), India.
Manuscript received on 11 December 2018 | Revised Manuscript received on 22 December 2018 | Manuscript Published on 09 January 2019 | PP: 96-99 | Volume-7 Issue-4S November 2018 | Retrieval Number: E1878017519/19©BEIESP
Open Access | Editorial and Publishing 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: Weather forecasting is major problemin ecological science. Existing statistical and Climate models are ineffective prediction tools of the long run temperature. Exact weather forecasting is tedious tasks that deal with huge amount of data. In this paper, an Enhanced Bat Algorithm (EBA) is proposed for selection of features from the temperature dataset. High dimensionality of data based on DNN with RMBLR are attempted in this work. Based on analysis of monthly high, average and low temperatures data sets, a novel Recursive Modified Bayesian Linear Regression (RMBLR) algorithm based on Deep Neural Network (DNN) is presented in this study.
Keywords: Feature Selection, BAT Algorithm, Recursive Bayesian, Temperature Prediction, Deep Neural Network.
Scope of the Article: Algorithm Engineering