College of Information Engineering, Nanjing University of Finance and Economics, Nanjing, 210023, China.
College of Information Engineering, Nanjing University of Finance and Economics, Nanjing, 210023, China.
Comput Biol Med. 2021 Jul;134:104505. doi: 10.1016/j.compbiomed.2021.104505. Epub 2021 May 23.
Embedded feature selection algorithms, such as support vector machine based recursive feature elimination (SVM-RFE), have proven to be effective for many real applications. However, due to the model selection problem, SVM-RFE naturally suffers from a heavy computational burden as well as high computational complexity. To solve these issues, this paper proposes using an optimized extreme learning machine (OELM) model instead of SVM. This model, referred to as OELM-RFE provides an efficient active set solver for training the OELM algorithm. We also present an effective alpha seeding algorithm to efficiently solve successive quadratic programming (QP) problems inherent in OELM. One of the salient characteristics of OELM-RFE is that it has only one tuning parameter: the penalty constant C. Experimental results from work on benchmark datasets show that OELM-RFE tends to have higher prediction accuracy than SVM-RFE, and requires fewer model selection efforts. In addition, the alpha seeding method works better on more datasets.
嵌入式特征选择算法，如基于支持向量机的递归特征消除 (SVM-RFE)，已被证明对许多实际应用非常有效。然而，由于模型选择问题，SVM-RFE 自然会受到计算负担重和计算复杂度高的困扰。为了解决这些问题，本文提出使用优化的极限学习机 (OELM) 模型代替 SVM。该模型称为 OELM-RFE，它为训练 OELM 算法提供了一个高效的主动集求解器。我们还提出了一种有效的 alpha 播种算法，以有效地解决 OELM 中固有的连续二次规划 (QP) 问题。OELM-RFE 的一个显著特点是它只有一个调整参数：惩罚常数 C。基准数据集上的实验结果表明，OELM-RFE 往往具有比 SVM-RFE 更高的预测精度，并且需要更少的模型选择工作。此外，alpha 播种方法在更多数据集上效果更好。
