|
Abstract
|
Article Information:
Machine Learning in Parliament Elections
Ahmad Esfandiari, Hamid Khaloozadeh, Mojtaba Esfandiari and Zahra Jafari Fard
Corresponding Author: Hamid Alinejad-Rokny
Submitted: March 03, 2012
Accepted: March 24, 2012
Published: October 01, 2012 |
Abstract:
|
Parliament is considered as one of the most important pillars of the country governance. The
parliamentary elections and prediction it, had been considered by scholars of from various field like political
science long ago. Some important features are used to model the results of consultative parliament elections.
These features are as follows: reputation and popularity, political orientation, tradesmen's support, clergymen's
support, support from political wings and the type of supportive wing. Two parameters of reputation and
popularity and the support of clergymen and religious scholars that have more impact in reducing of prediction
error in election results, have been used as input parameters in implementation. In this study, the Iranian
parliamentary elections, modeled and predicted using learnable machines of neural network and neuro-fuzzy.
Neuro-fuzzy machine combines the ability of knowledge representation of fuzzy sets and the learning power
of neural networks simultaneously. In predicting the social and political behavior, the neural network is first
trained by two learning algorithms using the training data set and then this machine predict the result on test
data. Next, the learning of neuro-fuzzy inference machine is performed. Then, be compared the results of two
machines.
Key words: ANFIS, machine learning, back-propagation learning algorithm, hybrid learning algorithm, neural networks, , parliamentary elections,
|
|
Abstract
|
PDF
|
HTML |
|
Cite this Reference:
Ahmad Esfandiari, Hamid Khaloozadeh, Mojtaba Esfandiari and Zahra Jafari Fard, . Machine Learning in Parliament Elections. Research Journal of Applied Sciences, Engineering and Technology, (19): 3732-3739.
|
|
|
|
 |
ISSN (Online): 2040-7467
ISSN (Print): 2040-7459 |
 |
| Information |
|
|
|
|
| Sales & Services |
|
|
|
|
