Resemblance of Rain Fall in Bangladesh with Correlation Dimension and Neural Network Learning
- 1 Department of Electrical and Electronic Engineering, Faculty of Electrical and Electronic Engineering, Khulna University of Engineering and Technology, Khulna-9203, Bangladesh
- 2 School of Electrical Systems Engineering, University Malaysia Perlis, Pauh Putra Campus, 02000 Arau, Perlis, Malaysia
Abstract
Rain fall and Temperature are undoubtedly two important factors that balance water in the environment. Adequate study of the rain behavior helps to forecast it. The time series obtained from different stations of the country throughout the several years are collected and analyzed. The dynamics of rain fall time series is analyzed with Correlation Dimension (CD) to characterize the several zones of Bangladesh. In addition a Neural Network (NN) predictor model was designed to realize complexity of rain fall. We found the interesting similarity between CD and NN predictor. The findings are useful in explaining why several zones show behavioral regularity and change.
DOI: https://doi.org/10.3844/ajassp.2013.1172.1180
Copyright: © 2013 Abu Nasir Mohammad Enamul Kabir, Hussain Muhammad Imran Hasan, Mohd Abdur Rashid, Azralmukmin Azmi, Md. Zakir Hossain and Md. Shahjahan. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
- 3,500 Views
- 2,536 Downloads
- 10 Citations
Download
Keywords
- Rain Fall
- Time Series Analysis
- Complexity
- Neural Network
- Learning and Prediction