Volume 32 Issue 1
Jan.  2023
Turn off MathJax
Article Contents
GU Jun, ZOU Quanyi, DENG Changhui, WANG Xiaojun. A Novel Robust Online Extreme Learning Machine for the Non-Gaussian Noise[J]. Chinese Journal of Electronics, 2023, 32(1): 130-139. doi: 10.23919/cje.2021.00.122
 Citation: GU Jun, ZOU Quanyi, DENG Changhui, WANG Xiaojun. A Novel Robust Online Extreme Learning Machine for the Non-Gaussian Noise[J]. Chinese Journal of Electronics, 2023, 32(1): 130-139.

# A Novel Robust Online Extreme Learning Machine for the Non-Gaussian Noise

##### doi: 10.23919/cje.2021.00.122
Funds:  This work was supported by Scientific Research Funding Project of the Education Department of Liaoning Province (LN2019Q44)
• Author Bio:

Jun GU is a Senior Experimenter in Telecommunications Experiment Center, School of Information Engineering, Dalian Ocean University. Her research interests include electrical and electronic technology and electrical automation

Quanyi ZOU is pursuing the Ph.D. degree in the School of Software Engineering, South China University of Technology, Guangzhou, China. His current research interests include machine learning, transfer learning, and software defect prediction

Changhui DENG is a Professor at Dalian Ocean University, Dalian, China. His research interests include complex process modeling and control, artificial intelligence technology, and intelligent detection

Xiaojun WANG (corresponding author) received the B.S. degree in automation from Dalian Ocean University, Dalian, China, in 2009. She received the M.S. and Ph.D. degrees in control theory and control engineering from Northeastern University, Shenyang, China, in 2011 and 2016, respectively. She is a Lecturer of School of Management Science and Engineering, Dongbei University of Finance and Economics, Dalian, China. Her research interests include recommender system, deep learning, machine learning, modeling of industrial processes and soft sensors. She is the first or the corresponding author of about 20 papers. (Email: wxjjessicaxj0903@126.com)

• Accepted Date: 2021-12-08
• Available Online: 2021-12-29
• Publish Date: 2023-01-05
• Samples collected from most industrial processes have two challenges: one is contaminated by the non-Gaussian noise, and the other is gradually obsolesced. This feature can obviously reduce the accuracy and generalization of models. To handle these challenges, a novel method, named the robust online extreme learning machine (RO-ELM), is proposed in this paper, in which the least mean $\boldsymbol{p}$-power criterion is employed as the cost function which is to boost the robustness of the ELM, and the forgetting mechanism is introduced to discard the obsolescence samples. To investigate the performance of the RO-ELM, experiments on artificial and real-world datasets with the non-Gaussian noise are performed, and the datasets are from regression or classification problems. Results show that the RO-ELM is more robust than the ELM, the online sequential ELM (OS-ELM) and the OS-ELM with forgetting mechanism (FOS-ELM). The accuracy and generalization of the RO-ELM models are better than those of other models for online learning.
• https://archive.ics.uci.edu/ml/index.php

### Catalog

###### 通讯作者: 陈斌, bchen63@163.com
• 1.

沈阳化工大学材料科学与工程学院 沈阳 110142

Figures(2)  / Tables(7)