Wearable sensor based multimodal human activity recognition exploiting the diversity of classifier ensemble

@inproceedings{Guo2016WearableSB,
  title={Wearable sensor based multimodal human activity recognition exploiting the diversity of classifier ensemble},
  author={Haodong Guo and Ling Chen and Liangying Peng and Gencai Chen},
  booktitle={UbiComp},
  year={2016}
}
Effectively utilizing multimodal information (e.g., heart rate and acceleration) is a promising way to achieve wearable sensor based human activity recognition (HAR). In this paper, an activity recognition approach MARCEL (<u>M</u>ultimodal <u>A</u>ctivity <u>R</u>ecognition with <u>C</u>lassifier <u>E</u>nsemble) is proposed, which exploits the diversity of base classifiers to construct a good ensemble for multimodal HAR, and the diversity measure is obtained from both labeled and unlabeled… CONTINUE READING
Highly Cited
This paper has 18 citations. REVIEW CITATIONS

Similar Papers

Loading similar papers…