Title: A new approach for prediction by using integrated neural networks
Abstract:In this paper, a new neural model is presented. Fast Feedforwared Neural Networks (FFNNs) is integrated with modified recurrent neural networks for powerful estimation. The proposed new model is appli...In this paper, a new neural model is presented. Fast Feedforwared Neural Networks (FFNNs) is integrated with modified recurrent neural networks for powerful estimation. The proposed new model is applied for prediction of power consumption. First, Modified Kohonen's Neural Networks (MKNNs) are used to facilitate the prediction process because they have the ability for clustering the input space into a number of classes. Therefore it is used for data classification to identify the categories which are essential for the prediction process. The unsupervised process performs the role of front-end data compression. For each category, the supervised learning algorithm LVQ is used for training FFNNs. The operation of FFNNs relies on performing cross correlation in the frequency domain between the input data and the weights of neural networks. Simulation results have shown that the presented integrated neural model is very powerful prediction.Read More
Publication Year: 2011
Publication Date: 2011-01-29
Language: en
Type: article
Access and Citation
Cited By Count: 5
AI Researcher Chatbot
Get quick answers to your questions about the article from our AI researcher chatbot