文献类型：期刊文献

英文题名：Imbalanced classification of mental workload using a cost-sensitive majority weighted minority oversampling strategy

作者：Zhang, Jianhua[1];Cui, Xiqing[1];Li, Jianrong[1];Wang, Rubin[2]

机构：[1]East China Univ Sci & Technol, Sch Informat Sci & Engn, Shanghai 200237, Peoples R China;[2]East China Univ Sci & Technol, Sch Sci, Shanghai 200237, Peoples R China

年份：2017

卷号：19

期号：4

起止页码：633

外文期刊名：COGNITION TECHNOLOGY & WORK

收录：;EI(收录号：20174604394840);WOS:【SSCI(收录号:WOS:000417269600007)，SCI-EXPANDED(收录号:WOS:000417269600007)】；

基金：The authors would like to thank Mr. Sunan Li for his useful discussions on this work and the developers of the aCAMS software which was used in data collection experiments. The work was supported in part by the National Natural Science Foundation of China under Grant No. 61075070 and Key Grant No. 11232005.

语种：英文

外文关键词：Mental workload; Human-machine system; Imbalanced learning; Cost-sensitive classification; Dynamic resampling of data space; Neural network

摘要：Identifying the temporal variations in mental workload level (MWL) is crucial for enhancing the safety of human-machine system operations, especially when there is cognitive overload or inattention of human operator. This paper proposed a cost-sensitive majority weighted minority oversampling strategy to address the imbalanced MWL data classification problem. Both the inter-class and intra-class imbalance problems are considered. For the former, imbalance ratio is defined to determine the number of the synthetic samples in the minority class. The latter problem is addressed by assigning different weights to borderline samples in the minority class based on the distance and density meaures of the sample distribution. Furthermore, multi-label classifier is designed based on an ensemble of binary classifiers. The results of analyzing 21 imbalanced UCI multi-class datasets showed that the proposed approach can effectively cope with the imbalanced classification problem in terms of several performance metrics including geometric mean (G-mean) and average accuracy (ACC). Moreover, the proposed approach was applied to the analysis of the EEG data of eight experimental participants subject to fluctuating levels of mental workload. The comparative results showed that the proposed method provides a competing alternative to several existing imbalanced learning algorithms and significantly outperforms the basic/referential method that ignores the imbalance nature of the dataset.