L1-PLS Based on Incremental Extreme Learning Machine
Zhiying Sun, Jinglin Zhou · 2020 IEEE 9th Data Driven Control and Learning Systems Conference (DDCLS) · 2020
In order to improve the accuracy of the regression model, an L1norm partial least square method (IELM-L1-PLS) based on an incremental limit learning machine is proposed. The data processing process of the incremental limit learning machine is nested into the framework based on the L1norm partial least square method, and the original data is upgraded by extracting the hidden node output matrix in the incremental limit learning machine, and then Regression analysis was performed on the upgraded data using L1-PLS. This method is used for experimental verification of actual data. The results show that the L1-PLS method based on the incremental limit learning machine can perform better regression analysis on the data.