Uncertainty Quantification for Deep Context-Aware Mobile Activity Recognition and Unknown Context Discovery

Abstract

Activity recognition in wearable computing faces two key challenges: i) activity characteristics may be context-dependent and change under different contexts or situations; ii) unknown contexts and activities may occur from time to time, requiring flexibility and adaptability of the algorithm. We develop a context-aware mixture of deep models termed the $\alpha$-$\beta$ network coupled with uncertainty quantification (UQ) based upon maximum entropy to enhance human activity recognition performance. We improve accuracy and F score by 10% by identifying high-level contexts in a data-driven way to guide model development. In order to ensure training stability, we have used a clustering-based pre-training in both public and in-house datasets, demonstrating improved accuracy through unknown context discovery.

Cite

Text

Huo et al. "Uncertainty Quantification for Deep Context-Aware Mobile Activity Recognition and Unknown Context Discovery." Artificial Intelligence and Statistics, 2020.

Markdown

[Huo et al. "Uncertainty Quantification for Deep Context-Aware Mobile Activity Recognition and Unknown Context Discovery." Artificial Intelligence and Statistics, 2020.](https://mlanthology.org/aistats/2020/huo2020aistats-uncertainty/)

BibTeX

@inproceedings{huo2020aistats-uncertainty,
  title     = {{Uncertainty Quantification for Deep Context-Aware Mobile Activity Recognition and Unknown Context Discovery}},
  author    = {Huo, Zepeng and PakBin, Arash and Chen, Xiaohan and Hurley, Nathan and Yuan, Ye and Qian, Xiaoning and Wang, Zhangyang and Huang, Shuai and Mortazavi, Bobak},
  booktitle = {Artificial Intelligence and Statistics},
  year      = {2020},
  pages     = {3894-3904},
  volume    = {108},
  url       = {https://mlanthology.org/aistats/2020/huo2020aistats-uncertainty/}
}