期刊
INFORMATION FUSION
卷 53, 期 -, 页码 80-87出版社
ELSEVIER
DOI: 10.1016/j.inffus.2019.06.014
关键词
Body sensor networks; Human activity recognition; Deep residual network; Multi-sensor data fusion
资金
- National Natural Science Foundation of China [61672135]
- National Science Foundation of China - Guangdong Joint Foundation [U1401257]
- Sichuan Science-Technology Support Plan Program [2018GZ0236, 2017FZ0004]
- Fundamental Research Funds for the Central Universities [2672018ZYGX2018J057, ZYGX2015KYQD136]
To facilitate data-driven and informed decision making, a novel deep neural network architecture for human activity recognition based on multiple sensor data is proposed in this work. Specifically, the proposed architecture encodes the time series of sensor data as images (i.e., encoding one time series into a two-channel image), and leverages these transformed images to retain the necessary features for human activity recognition. In other words, based on imaging time series, wearable sensor-based human activity recognition can be realized by using computer vision techniques for image recognition. In particular, to enable heterogeneous sensor data to be trained cooperatively, a fusion residual network is adopted by fusing two networks and training heterogeneous data with pixel-wise correspondence. Moreover, different layers of deep residual networks are used to deal with dataset size differences. The proposed architecture is then extensively evaluated on two human activity recognition datasets (i.e., HHAR dataset and MHEALTH dataset), which comprise various heterogeneous mobile device sensor combinations (Le., acceleration, angular velocity, and magnetic field orientation). The findings demonstrate that our proposed approach outperforms other competing approaches, in terms of accuracy rate and F1-value.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据