Augmenting Wearable Sensor Data with Physical Constraint for DNN-Based Human-Action Recognition

Hiroki Ohashi, Mohammad Osamh Adel Al-Naser, Sheraz Ahmed, Takayuki Akiyama, Takuto Sato, Phong Nguyen, Katsuyuki Nakamura, Andreas Dengel

In: Time Series Workshop. Time Series Workshop @ ICML located at ICML 2017 August 11-11 Sydney Australia 2017.


A novel data augmentation method suitable for wearable sensor data is proposed. Although numerous studies have revealed the importance of the data augmentation to improve the accuracy and robustness in machine-learning tasks, the data augmentation method that is applicable to wearable sensor data have not been well studied. Unlike the conventional data augmentation methods, which are mainly developed for image and video analysis tasks, this study proposes a data augmentation method that can take an physical constraint of wearable sensors into account. The effectiveness of the proposed method was evaluated with a human-action-recognition task. The experimental results showed that the proposed method achieved better accuracy with significant difference compared to the cases where no data augmentation is applied and where a couple of simple data augmentation is applied.

TSW2017_paper_9.pdf (pdf, 567 KB)

German Research Center for Artificial Intelligence
Deutsches Forschungszentrum für Künstliche Intelligenz