ANALYSIS AND PREDICTION OF TEMPERATURE USING STATISTICAL ARTIFICIAL NEURAL NETWORK
Journal Title: International Journal of Computer Science and Management Studies (IJCSMS) www.ijcsms.com - Year 2012, Vol 12, Issue 2
Abstract
This paper is about producing a prediction system by using artificial neural methods that will forecast temperature. This paper is based on three objectives. First, study of temperature and gathers all knowledge regarding the weather this is particularly studied in analysis part of the paper. Second, gather all knowledge about artificial neural network methods. Implement multilayer perceptron neural network with gradient descent(back propagation), BFGS, conjugate gradient training algorithm and will analyze the performance of all. Lastly, achieve an objective of developing a temperature prediction system. The general finding is that with BFGS algorithm, with multilayer perceptron model perform well with less prediction error and more accuracy than gradient descent and conjugate gradient, thus used for temperature prediction. To implement this project we make use of statistica software which provides the functionality called statistica artificial neural network(SANN) which is used here for temperature prediction and heavy weather software is used for data gathering.
Authors and Affiliations
Parag Kadu , Kishor Wagh , Prashant Chatur
Keywords
Related Articles
- EP ID EP150906
- DOI -
- Views 139
- Downloads 0
Statistical Analysis of Two Types Failure of Redundant System
In this paper we have analyzed a two unit stand by system in which the operative unit fails due to machinery defects as well as random shocks which occurs at random epochs of time.
A Comparison among Various Techniques to Prioritize the Requirements
In commercial software system development, software vendors often face the many difficulties to deal with large amount of requirements that enter the company every day. It is not possible to satisfy all the requirements...
Expansion of Chicken’s Neck Route: - A Golden Pathway for Swift and Sustainable Development of Seven Sister States of India
The landlocked Northeastern region of the India comprises seven separate states named Arunachal Pradesh, Assam, Meghalaya, Manipur, Mizoram,Nagaland and Tripura respectively.
DIGITAL SIMULATION OF MULTI LEVEL INVERTER BASED DYNAMIC VOLTAGE RESTORER
This paper deals with simulation of multilevel inverter based DVR. The DVR circuit produces high quality voltage since it uses a nine level inverter. This DVR gives better solution to the voltage sag problem by injecting...
IMPLEMENTATION OF PEAP ON MICROSOFT WINDOW’S IMPLEMENTATION OF PEAP ON MICROSOFT WINDOW’S
In today’s world most organizations are moving from wireconnected LAN’s to wireless LAN’s. WLANs are changing the landscape of computer networking. Wireless communications are inherently more open to attack than wired da...