Cross-person activity recognition using reduced kernel extreme learning machine

By W. Deng, Qinghua Zheng, Zhong-Min Wang. 2014

174 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Toward an optimal kernel extreme learning machine using a chaotic moth-flame optimization strategy with applications in medical diagnoses (2017, background): “KELM can perform comparatively, or better, than popular machine learning paradigms like the support vector machine (SVM), in many scenarios like hyperspectral remote-sensing image classification [12, 13], disease diagnosis [14-17], bankruptcy prediction [18], activity recognition [19], 2-D profiles ”
Elderly Fall Detection Systems: A Literature Survey (2020, methodology): “Another solution, which can potentially address the scarcity of data, is to develop algorithms that can be adapted to subjects that were not part of the original training set (Deng et al., 2014; Namba and Yamada, 2018a,b) as we described in section 4.1.4.”
Activity recognition with smartphone sensors (2014, background): “Deng et al.[60] proposed a cross-person activity recognition model to eliminate the effect of user sensitivity.”
A Decade Survey of Transfer Learning (2010–2020) (2020, methodology): “Similar to TransEMDT, [51] proposed another framework, Tran-sRKELM (Transfer learning Reduced Kernel Extreme Learning Machine), which uses RKELM to build an initial activity recognition model.”