Mixed-kernel based weighted extreme learning machine for inertial sensor based human activity recognition with imbalanced dataset

摘要

Balanced dataset has been utilized by the previous human activity recognition algorithms to train the classifier. However, imbalanced dataset are ubiquitous in human activity recognition, especially in the case of abnormal activity detection. Though the class imbalance problem exists as a universal phenomenon in human activity recognition, few researches mentioned this problem and solved it. In order to reduce the influence of the imbalance datasets problem, the mixed-kernel based weighted extreme learning machine (MK-WELM) has been proposed in this paper. Considering that the performance of extreme learning machine (ELM) is greatly influenced by the choice of kernel, the mixed kernel method is proposed for ELM. In order to deal with the imbalanced problem, the cost sensitive method is utilized. The main idea of the cost sensitive method is that the cost of minority class increases with the misclassification rate. Considering the cost sensitive function and the mixed kernel method, the MK-WELM is constructed. Comparing with ELM and weighted ELM methods, experimental results over different human activity datasets demonstrate the effectiveness of the proposed method. (C) 2016 Elsevier B.V. All rights reserved.