A robust double-parallel extreme learning machine based on an improved M-estimation algorithm. (April 2022)

• Record Type: Journal Article
• Authors: Zha, Linlin; Ma, Kai; Li, Guoqiang; Fang, Qi; Hu, Xiaobin
• Is Part Of: Advanced engineering informatics. Volume 52(2022)
• Publication Date: 2022-04
• Subjects: 00-01 -- 99-00; Outlier-robust regression -- Extreme learning machine (ELM) -- Double-parallel -- M-estimation -- Coal-fired boiler; Computer-aided engineering -- Periodicals; Engineering -- Data processing -- Periodicals; 620.00285
• DOI: 10.1016/j.aei.2022.101606
• Languages: English
• ISSNs: 1474-0346

Abstract

Abstract: To solve the problem of improving the regression accuracy and model stability of the extreme learning machine(ELM), a new approach based on an improved M-estimation optimized double-parallel extreme learning machine is proposed in this study, namely robust double-parallel extreme learning machine(RD-ELM). Firstly, RD-ELM is constructed with a double parallel forward structure, thus the information can be received from both hidden layer neurons and input layer neurons. Secondly, we use an improved M-estimation to calculate output weights of neural network by iteratively reweighted Least-Squares Estimation(LSE), with weights assigned by the least absolute residual estimation of the samples. Finally, we establish a regression prediction model utilized to test the goodness of fit in a SinC function and verify the regression ability in eight benchmark regression problems. Then the proposed method is applied to an actual operational condition of a power plant. Experimental results show that the proposed method can efficiently process the influence of outliers and noise with strong anti-jamming ability. Compared with other methods, RD-ELM has superior performance that is stronger robustness and better generalization performance in many benchmark data and practical experiments.