Hybrid Multilayered Perceptron Network Trained by Modified Recursive Prediction Error-Extreme Learning Machine for Tuberculosis Bacilli Detection

2011 ◽  
pp. 667-673 ◽  
Author(s):  
M. K. Osman ◽  
M. Y. Mashor ◽  
H. Jaafar
Keyword(s):  
Extreme Learning Machine ◽  
Prediction Error ◽  
Multilayered Perceptron ◽  
Learning Machine ◽  
Recursive Prediction

scholarly journals Prediction of a composite indicators using combined method of extreme learning machine and locally weighted regression

2012 ◽  
Vol 17 (2) ◽  
pp. 238-251
Author(s):  
Jurga Rukšėnaitė ◽  
Pranas Vaitkus
Keyword(s):  
Extreme Learning Machine ◽  
Prediction Error ◽  
Composite Indicators ◽  
Weighted Regression ◽  
Combined Method ◽  
Locally Weighted Regression ◽  
Testing Sample ◽  
One Step ◽  
Learning Machine ◽  
The One

In this paper, a method of artificial neural networks (NN) is proposed as an alternative tool for the one-step-ahead prediction of composite indicators (CIs) of Lithuania’s economy. CI is composed of widely used social and economic indicators. The NN is applied for forecasting CI during the financial crisis and later periods (2008–2010) on the basis of data of earlier years (1998–2007). In this work, the Extreme Learning Machine (ELM) algorithm is combined with locally weighted regression. The analysis shows that the prediction error of a testing sample is statistically smaller compared to Levenberg–Marquardt or ELM methods.

scholarly journals Reversible Watermarking Using Prediction-Error Expansion and Extreme Learning Machine

2015 ◽  
Vol 2015 ◽  
pp. 1-12
Author(s):  
Guangyong Gao ◽  
Caixue Zhou ◽  
Zongmin Cui
Keyword(s):  
Extreme Learning Machine ◽  
Prediction Error ◽  
Image Distortion ◽  
Reversible Watermarking ◽  
Prediction Error Expansion ◽  
Improvement Method ◽  
Image Set ◽  
Error Expansion ◽  
Learning Machine ◽  
Embedding Distortion

Currently, the research for reversible watermarking focuses on the decreasing of image distortion. Aiming at this issue, this paper presents an improvement method to lower the embedding distortion based on the prediction-error expansion (PE) technique. Firstly, the extreme learning machine (ELM) with good generalization ability is utilized to enhance the prediction accuracy for image pixel value during the watermarking embedding, and the lower prediction error results in the reduction of image distortion. Moreover, an optimization operation for strengthening the performance of ELM is taken to further lessen the embedding distortion. With two popular predictors, that is, median edge detector (MED) predictor and gradient-adjusted predictor (GAP), the experimental results for the classical images and Kodak image set indicate that the proposed scheme achieves improvement for the lowering of image distortion compared with the classical PE scheme proposed by Thodi et al. and outperforms the improvement method presented by Coltuc and other existing approaches.

Sistema Híbrido Baseado Em Extreme Learning Machine E Harmony Search

2016 ◽  
Author(s):  
Edgar Wellington Marques de Almeida ◽  
Mêuser Jorge da Silva Valença
Keyword(s):  
Extreme Learning Machine ◽  
Harmony Search ◽  
Learning Machine
Sign in / Sign up

Export Citation Format

Share Document