Deep Weighted Extreme Learning Machine
Deep Weighted Extreme Learning Machine
复制标题
深度加权极限学习机
DOI：
10.1007/s12559-018-9602-9
复制
发表时间：
2018-10
影响因子：
5.4
通讯作者：
Badong Chen
中科院分区：
文献类型：
--
作者：
Tianlei Wang;Jiuwen Cao;Xiaoping Lai;Badong Chen
在过去的几年里，由于生物医学工程，监控和计算机视觉等许多领域的数据不断膨胀，不平衡数据分类引起了越来越多的关注。从不平衡数据中学习是一项挑战，因为大多数标准算法都无法正确表示数据分布的固有复杂特征。作为一种新兴的技术，极端学习机（ELM）及其变体，包括加权ELM（WELM）和提升加权ELM（BWELM），最近被开发用于不平衡数据的分类。然而，WELM具有以下缺陷：（i）在学习阶段手动选择和固定样本权重矩阵;（ii）表示能力，即从原始数据中提取特征或有用信息的能力，由于其浅层结构而未得到充分探索。BWELM采用AdaBoost算法来优化样本权重。但是，浅层结构仍然制约着表征能力的提高。为了缓解这些不足，我们提出了一种新的深度加权ELM（DWELM）算法的不平衡数据分类在本文中。首先提出了一种用ELM训练的增强型堆叠多层深度表示网络（EH-DrELM）来提高表示能力，并开发了一种用于不平衡多类数据的快速AdaBoost算法（AdaBoost-ID）来优化样本权重。然后，新的DWELM的不平衡学习是通过结合上述两种算法。在9个不平衡二进制类数据集、9个不平衡多类数据集和5个大型基准数据集（3个多类数据集和2个二进制数据集）上的实验结果表明，DWELM的性能优于WELM和BWELM，以及几种最先进的基于多层网络的学习算法.
The imbalanced data classification attracts increasing attention in the past years due to the continuous expansion of data available in many areas, such as biomedical engineering, surveillance, and computer vision. Learning from imbalanced data is challenging as most standard algorithms fail to properly represent the inherent complex characteristics of the data distribution. As an emerging technology, the extreme learning machine (ELM) and its variants, including the weighted ELM (WELM) and the boosting weighted ELM (BWELM), have been recently developed for the classification of imbalanced data. However, the WELM suffers the following deficiencies: (i) the sample weight matrix is manually chosen and fixed during the learning phase; (ii) the representation capability, namely the capability to extract features or useful information from the original data, is insufficiently explored due to its shallow structure. The BWELM employs the AdaBoost algorithm to optimize the sample weights. But the representation capability is still restricted by the shallow structure. To alleviate these deficiencies, we propose a novel deep weighted ELM (DWELM) algorithm for imbalanced data classification in this paper. An enhanced stacked multilayer deep representation network trained with the ELM (EH-DrELM) is first proposed to improve the representation capability, and a fast AdaBoost algorithm for imbalanced multiclass data (AdaBoost-ID) is developed to optimize the sample weights. Then, the novel DWELM for the imbalance learning is obtained by combining the above two algorithms. Experimental results on nine imbalanced binary-class datasets, nine imbalanced multiclass datasets, and five large benchmark datasets (three for multiclass and two for binary-class) show that the proposed DWELM achieves a better performance than the WELM and BWELM, as well as several state-of-the-art multilayer network-based learning algorithms.
登录
查看更多内容
影响因子：
11.8
作者：
Chen, Tao;Yap, Kim-Hui
通讯作者：
Yap, Kim-Hui
DOI：
--
发表时间：
1997
期刊：
--
影响因子：
--
作者：
M. Kubát;S. Matwin
通讯作者：
M. Kubát;S. Matwin
DOI：
10.1016/j.jfranklin.2016.08.024
发表时间：
2016-11-01
影响因子：
4.1
作者：
Cao, Jiuwen;Hao, Jiaoping;Luo, Minxia
通讯作者：
Luo, Minxia
DOI：
--
发表时间：
1998-08
期刊：
--
影响因子：
--
作者：
Gary M. Weiss;H. Hirsh
通讯作者：
Gary M. Weiss;H. Hirsh
DOI：
--
发表时间：
--
期刊：
--
影响因子：
--
作者：
L. C. Kasun;Hongming Zhou;G. Huang;C. Vong
通讯作者：
L. C. Kasun;Hongming Zhou;G. Huang;C. Vong