研究目的
Investigating the performance of a regularized weighted circular complex-valued extreme learning machine (RWCC-ELM) for imbalanced learning.
研究成果
RWCC-ELM outperforms CC-ELM and WELM for most evaluated datasets, demonstrating its effectiveness in handling imbalanced learning problems. The study suggests future work could explore RWCC-ELM's application on real-world complex-valued input problems.
研究不足
The study is limited to imbalanced datasets from the Keel repository and does not explore the application of RWCC-ELM on real-world complex-valued input problems with large class distribution variations.
1：Experimental Design and Method Selection:
The study proposes RWCC-ELM, a variant of ELM, combining the strengths of CC-ELM and WELM. It uses a circular transformation function to map real-valued data to complex domain and a fully complex sech activation function in the hidden layer.
2：Sample Selection and Data Sources:
The performance of RWCC-ELM is evaluated using imbalanced datasets from the Keel repository.
3：List of Experimental Equipment and Materials:
The experiments are conducted using Matlab
4：1 on a PC with Intel core i5 processor, 20 GHz CPU, and 2 GB RAM. Experimental Procedures and Operational Workflow:
The study involves training RWCC-ELM on various datasets, comparing its performance with CC-ELM and WELM in terms of G-mean and overall accuracy, and conducting a Wilcoxon signed-rank test for statistical significance.
5：Data Analysis Methods:
The performance metrics include G-mean for imbalanced datasets and overall accuracy. The study also uses a grid search for optimal parameter settings.
独家科研数据包，助您复现前沿成果，加速创新突破
获取完整内容
