New Weather Forecasting Technique using ANFIS with Modified Levenberg-Marquardt Algorithm for Learning

• Published in: International journal of computer science and information security Vol. 10; no. 3; p. 140
• Main Authors: Shereef, I Kadar, Baboo, S Santhosh
• Format: Journal Article
• Language: English
• Published: Pittsburgh L J S Publishing 01.03.2012
• Subjects: Algorithms; Neural networks; Studies; Wind
• ISSN: 1947-5500

Temperature warnings are essential forecasts since they are utilized to guard life and property. Temperature forecasting is the kind of science and technology to approximate the temperature for a future time and for a given place. Temperature forecasts are performed by means of gathering quantitative data regarding the in progress state of the atmosphere. The author in this paper utilized a neural network-based technique for determining the temperature in future. The Neural Networks package consists of various kinds of training or learning techniques. One such technique is Adaptive Neuro Fuzzy Inference System (ANFIS) technique. The main advantage of the ANFIS technique is that it can reasonably estimated a large class of functions. This technique is more efficient than numerical differentiation. The simple meaning of this term is that the proposed technique has ability to confine the complex relationships among several factors that contribute to assured temperature. The proposed idea is tested using the real time dataset. In order to further improve the prediction accuracy, this paper uses Modified Levenberg-Marquardt (LM) Algorithm for Neural Network learning. In modified LM, the learning parameters are modified. The proposed algorithm has good convergence and also it reduces the amount of oscillation in learning procedure. The proposed technique is compare with the usage of ANFIS and the practical working of meteorological department. The experimental result shows that the proposed technique results in better accuracy of prediction when compared to the conventional technique of weather prediction. [PUBLICATION ABSTRACT]