Deep ConvLSTM With Self-Attention for Human Activity Decoding Using Wearable Sensors
Deep ConvLSTM With Self-Attention for Human Activity Decoding Using Wearable Sensors
复制标题
DOI：
10.1109/jsen.2020.3045135
复制
发表时间：
2021-03-15
影响因子：
4.3
通讯作者：
Gupta, Sukrit
中科院分区：
文献类型：
--
作者：
Singh, Satya P.;Sharma, Madan Kumar;Gupta, Sukrit
从可穿戴传感器准确解码人类活动可以帮助与医疗保健和环境感知相关的应用。在这个领域中，目前的方法使用递归和/或卷积模型来从来自多个传感器的时间序列数据中捕获时空特征。我们提出了一种深度神经网络架构，它不仅可以捕获多个传感器时间序列数据的时空特征，还可以通过自我注意机制来选择和学习重要的时间点。我们在六个公共数据集上展示了所提出的方法在不同数据采样策略中的有效性，并证明了自注意机制使用递归和卷积网络的组合在深度网络上显着提高了性能。我们还表明，所提出的方法提供了一个统计上显着的性能增强比以前的国家的最先进的方法测试数据集。所提出的方法为更好地从多个身体传感器解码人类活动开辟了途径。建议模型的代码实现可在https://github.com/isukrit/encodingHumanActivity上获得
Decoding human activity accurately from wearable sensors can aid in applications related to healthcare and context awareness. The present approaches in this domain use recurrent and/or convolutional models to capture the spatio-temporal features from time-series data from multiple sensors. We propose a deep neural network architecture that not only captures the spatio-temporal features of multiple sensor time-series data but also selects, learns important time points by utilizing a self-attention mechanism. We show the validity of the proposed approach across different data sampling strategies on six public datasets and demonstrate that the self-attention mechanism gave a significant improvement in performance over deep networks using a combination of recurrent and convolution networks. We also show that the proposed approach gave a statistically significant performance enhancement over previous state-of-the-art methods for the tested datasets. The proposed methods open avenues for better decoding of human activity from multiple body sensors over extended periods of time. The code implementation for the proposed model is available at https://github.com/isukrit/encodingHumanActivity