EDNets: Deep Feature Learning for Document Image Classification Based on Multi-view Encoder-Decoder Neural Networks

2021 ◽  
pp. 318-332
Author(s):  
Akrem Sellami ◽  
Salvatore Tabbone
Keyword(s):  
Neural Networks ◽  
Image Classification ◽  
Feature Learning ◽  
Document Image ◽  
Deep Feature ◽  
Deep Feature Learning

Day-Ahead Prediction of Wind Speed with Deep Feature Learning

2016 ◽  
Vol 30 (05) ◽  
pp. 1650011 ◽  
Author(s):  
Jie Wan ◽  
Jinfu Liu ◽  
Guorui Ren ◽  
Yufeng Guo ◽  
Daren Yu ◽  
...  
Keyword(s):  
Neural Networks ◽  
Wind Speed ◽  
Large Scale ◽  
Feature Learning ◽  
Threshold Value ◽  
Support Vector ◽  
Prediction Errors ◽  
Wind Speed Prediction ◽  
Deep Feature ◽  
Deep Feature Learning

Day-ahead prediction of wind speed is a basic and key problem of large-scale wind power penetration. Many current techniques fail to satisfy practical engineering requirements because of wind speed's strong nonlinear features, influenced by many complex factors, and the general model's inability to automatically learn features. It is well recognized that wind speed varies in different patterns. In this paper, we propose a deep feature learning (DFL) approach to wind speed forecasting because of its advantages at both multi-layer feature extraction and unsupervised learning. A deep belief network (DBN) model for regression with an architecture of 144 input and 144 output nodes was constructed using a restricted Boltzmann machine (RBM). Day-ahead prediction experiments were then carried out. By comparing the experimental results, it was found that the prediction errors with respect to both size and stability of a DBN model with only three hidden layers were less than those of the other three typical approaches including support vector regression (SVR), single hidden layer neural networks (SHL-NN), and neural networks with three hidden layers (THL-NN). In addition, the DBN model can learn and obtain complex features of wind speed through its strong nonlinear mapping ability, which effectively improves its prediction precision. In addition, prediction errors are minimized when the number of DBN model's hidden layers reaches a threshold value. Above this number, it is not possible to improve the prediction accuracy by further increasing the number of hidden layers. Thus, the DBN method has a high practical value for wind speed prediction.

scholarly journals Conditional Random Field and Deep Feature Learning for Hyperspectral Image Classification

2019 ◽  
Vol 57 (3) ◽  
pp. 1612-1628 ◽  
Author(s):  
Fahim Irfan Alam ◽  
Jun Zhou ◽  
Alan Wee-Chung Liew ◽  
Xiuping Jia ◽  
Jocelyn Chanussot ◽  
...  
Keyword(s):  
Random Field ◽  
Image Classification ◽  
Hyperspectral Image ◽  
Conditional Random Field ◽  
Feature Learning ◽  
Hyperspectral Image Classification ◽  
Deep Feature ◽  
Deep Feature Learning
Sign in / Sign up

Export Citation Format

Share Document