Spectral quantitative analysis of complex samples based on the extreme learning machine

2016 ◽  
Vol 8 (23) ◽  
pp. 4674-4679 ◽  
Author(s):  
Xi-Hui Bian ◽  
Shu-Juan Li ◽  
Meng-Ran Fan ◽  
Yu-Gao Guo ◽  
Na Chang ◽  
...  
Keyword(s):  
Quantitative Analysis ◽  
Extreme Learning Machine ◽  
Predictive Performance ◽  
Complex Samples ◽  
Learning Machine ◽  
Novel Algorithm

A novel algorithm called the extreme learning machine is introduced for the spectral quantitative analysis of complex samples, which enhances predictive performance.

A boosting extreme learning machine for near-infrared spectral quantitative analysis of diesel fuel and edible blend oil samples

2017 ◽  
Vol 9 (20) ◽  
pp. 2983-2989 ◽  
Author(s):  
Xihui Bian ◽  
Caixia Zhang ◽  
Xiaoyao Tan ◽  
Michal Dymek ◽  
Yugao Guo ◽  
...  
Keyword(s):  
Quantitative Analysis ◽  
Extreme Learning Machine ◽  
Diesel Fuel ◽  
Near Infrared ◽  
Predictive Accuracy ◽  
Infrared Spectral ◽  
Learning Machine ◽  
Accuracy And Stability

A novel boosting extreme learning machine is proposed for near-infrared spectral quantitative analysis which greatly enhances predictive accuracy and stability.

scholarly journals A parallel inertial S-iteration forward-backward algorithm for regression and classification problems

2020 ◽  
Vol 36 (1) ◽  
pp. 35-44 ◽  
Author(s):  
LIMPAPAT BUSSABAN ◽  
ATTAPOL KAEWKHAO ◽  
SUTHEP SUANTAI
Keyword(s):  
Fixed Point ◽  
Common Fixed Point ◽  
Extreme Learning Machine ◽  
Nonexpansive Mappings ◽  
Countable Family ◽  
Classification Problems ◽  
Output Layer ◽  
Learning Machine ◽  
Hidden Layer ◽  
Novel Algorithm

In this paper, a novel algorithm, called parallel inertial S-iteration forward-backward algorithm (PISFBA) isproposed for finding a common fixed point of a countable family of nonexpansive mappings and convergencebehavior of PISFBA is analyzed and discussed. As applications, we apply PISFBA to estimate the weight con-necting the hidden layer and output layer in a regularized extreme learning machine. Finally, the proposedlearning algorithm is applied to solve regression and data classification problems

scholarly journals Smoothing L0 Regularization for Extreme Learning Machine

2020 ◽  
Vol 2020 ◽  
pp. 1-10 ◽  
Author(s):  
Qinwei Fan ◽  
Ting Liu
Keyword(s):  
Extreme Learning Machine ◽  
Numerical Experiments ◽  
Learning Algorithm ◽  
Human Intervention ◽  
Feedforward Networks ◽  
Learning Machine ◽  
Hidden Layer ◽  
Efficient Learning ◽  
Hidden Nodes ◽  
Novel Algorithm

Extreme learning machine (ELM) has been put forward for single hidden layer feedforward networks. Because of its powerful modeling ability and it needs less human intervention, the ELM algorithm has been used widely in both regression and classification experiments. However, in order to achieve required accuracy, it needs many more hidden nodes than is typically needed by the conventional neural networks. This paper considers a new efficient learning algorithm for ELM with smoothing L0 regularization. A novel algorithm updates weights in the direction along which the overall square error is reduced the most and then this new algorithm can sparse network structure very efficiently. The numerical experiments show that the ELM algorithm with smoothing L0 regularization has less hidden nodes but better generalization performance than original ELM and ELM with L1 regularization algorithms.

Quantitative analysis of sinters using laser-induced breakdown spectroscopy (LIBS) coupled with kernel-based extreme learning machine (K-ELM)

2018 ◽  
Vol 10 (9) ◽  
pp. 1074-1079 ◽  
Author(s):  
Yu Ding ◽  
Fei Yan ◽  
Guang Yang ◽  
Haixiu Chen ◽  
Zhensheng Song
Keyword(s):  
Quantitative Analysis ◽  
Extreme Learning Machine ◽  
Total Iron ◽  
Laser Induced Breakdown Spectroscopy ◽  
Breakdown Spectroscopy ◽  
Laser Induced Breakdown ◽  
Learning Machine

This work explores the combination of LIBS technology and K-ELM algorithm for the quantitative analysis of total iron (TFe) content and alkalinity of sinter.

Spectrum Prediction for Cognitive Radio System Based on Optimally Pruned Extreme Learning Machine

2014 ◽  
Vol 536-537 ◽  
pp. 430-436 ◽  
Author(s):  
Ling Yang ◽  
Na Lv ◽  
Zhen Xing Xu
Keyword(s):  
Cognitive Radio ◽  
Extreme Learning Machine ◽  
Predictive Performance ◽  
Prediction Algorithm ◽  
Good Precision ◽  
Secondary Users ◽  
Spectrum Prediction ◽  
Radio System ◽  
Novel Approach ◽  
Learning Machine

The Cognitive Radio (CR) technology is an efficient solution to spectrum scarcity by share the spectrum with the secondary users on a non-interfering basis. The spectrum prediction can rationalize the spectrum allocation based on previous information about the spectrum evolution in time. Against previous spectrum prediction algorithm lack of timeliness and accuracy, this paper proposes a novel approach for spectrum prediction based on Optimally Pruned Extreme Learning Machine (OP-ELM) which improved the original Extreme Learning Machine (ELM) algorithm. This method not only takes the advantage of the ELM extremely fast speed and good precision, but also more robust and generic with additional steps compared with ELM. In order to compare its comprehensive properties to other algorithms, some experiments were designed. The results show that the predictive performance of this new algorithm is more satisfaction than others in spectrum prediction problem.

Sign in / Sign up

Export Citation Format

Share Document