Rolling Prediction Model of Closing Price Based on EEMD Data Noise Reduction and HGS-DELM

Gao, Yuansheng; Li, Lei; Yu, Jiguang

doi:10.1109/icdacai57211.2022.00059

Cited by 1 publication

(1 citation statement)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Meanwhile, ELM does not have more learning parameters. Over the course of several years, ELM has been applied to practical issues such as forecasting stock prices, diagnosing faults, and predicting remaining useful life [4,5]. In addition, the Kernel Extreme Learning Machine (KELM) introduces kernel functions in the hidden layer [6].…”

Section: Introductionmentioning

confidence: 99%

Kernel extreme learning machine optimized by arithmetic optimization algorithm

Li,

Wang,

Peng

et al. 2024

Fourth International Conference on Applied Mathematics, Modelling, and Intelligent Computing (CAMMIC 2024)

View full text Add to dashboard Cite

The kernel function is introduced by the Kernel Extreme Learning Machine on the basis of the original Extreme Learning Machine, which effectively improves the capability of prediction of the Extreme Learning Machine, but the hyperparameters of it still affect the model performance to a large extent. As an effective metaheuristic algorithm, the Arithmetic Optimization Algorithm is frequently utilized to address optimization problems. This work introduces the Kernel Extreme Learning Machine optimized by the Arithmetic Optimization Algorithm (AOA-KELM) in an effort to significantly improve the efficiency of the Kernel Extreme Learning Machine. Regularization coefficients and Kernel parameters are the hyperparameters under optimization. On the UCI dataset, the performance of the proposed algorithm is verified through comparison with the Extreme Learning Machine-Grey Wolf Optimizer, Deep Extreme Learning Machine, Backpropagation Algorithm, and Support Vector Machine. The results obtained from the numerical analysis validate the superiority of the proposed method, since the proposed algorithm significantly outperforms its competitors.

show abstract

Section: Introductionmentioning

confidence: 99%