Bias-Boosted ELM for Knowledge Transfer in Brain Emotional Learning for Time Series Forecasting

Abstract

This paper presents the Bias-Boosted Extreme Learning Machine guided Brain Emotional Learning (B2ELM-BEL) model, a significant advancement in chaotic time series prediction that effectively incorporates knowledge transfer learning. Integrating traditional Brain Emotional Learning (BEL) with the novel Biased-ELM method, the B2ELM-BEL introduces a bias term into the output weights of Extreme Learning Machines (ELM). This addition enhances the model's predictive accuracy, proving particularly beneficial in configurations with a minimal number of hidden nodes. Our evaluation of the B2ELM-BEL model across various datasets, including complex chaotic time-series benchmarks and real-world scenarios, demonstrates its superior performance over several BEL models. It achieves lower mean RMSE, MAE, and SMAPE values, and exhibits enhanced generalizability and efficiency. The findings indicate that while the single hidden node variant of B2ELM-BEL is apt for simpler tasks, the multi-node version is more adept at handling challenging environments. This highlights the necessity of tailoring the model to the complexity of the specific dataset being analyzed.