This is a sample code of data augmentation methods for wearable sensor data (time-series data). The example code writen in Jupyter notebook can be found here or here. For more details, please refer to the the paper below.
T. T. Um et al., “Data augmentation of wearable sensor data for parkinson’s disease monitoring using convolutional neural networks,” in Proceedings of the 19th ACM International Conference on Multimodal Interaction, ser. ICMI 2017. New York, NY, USA: ACM, 2017, pp. 216–220. [arXiv]
Data augmentation is consider as a standard preprocessing in various recognition problems (e.g. image recognition), which gives additional performance improvement by providing more data. Data augmentation can be also interpreted as injecting human's prior knowledge about label-preserving transformation and giving regularization by data. This code provides a simple approach to augment time-series data, e.g., wearable sensor data, by applying various distortions to the data.
Please see the jupyter notebook file (here or here) for more examples
You need to pre-install numpy, matplotlib, scipy, and transforms3d for running the code. (You can install them using pip
)
You can freely modify this code for your own purpose. However, please leave the citation information untouched when you redistributed the code to others. If this code helps your research, please cite the paper.
@inproceedings{TerryUm_ICMI2017,
author = {Um, Terry T. and Pfister, Franz M. J. and Pichler, Daniel and Endo, Satoshi and Lang, Muriel and Hirche, Sandra and Fietzek, Urban and Kuli\'{c}, Dana},
title = {Data Augmentation of Wearable Sensor Data for Parkinson's Disease Monitoring Using Convolutional Neural Networks},
booktitle = {Proceedings of the 19th ACM International Conference on Multimodal Interaction},
series = {ICMI 2017},
year = {2017},
isbn = {978-1-4503-5543-8},
location = {Glasgow, UK},
pages = {216--220},
numpages = {5},
doi = {10.1145/3136755.3136817},
acmid = {3136817},
publisher = {ACM},
address = {New York, NY, USA},
keywords = {Parkinson\&\#39;s disease, convolutional neural networks, data augmentation, health monitoring, motor state detection, wearable sensor},
}
此处可能存在不合适展示的内容,页面不予展示。您可通过相关编辑功能自查并修改。
如您确认内容无涉及 不当用语 / 纯广告导流 / 暴力 / 低俗色情 / 侵权 / 盗版 / 虚假 / 无价值内容或违法国家有关法律法规的内容,可点击提交进行申诉,我们将尽快为您处理。