面向腕臂动作识别的加速度计数据分析

朱国康; 周涛

doi:10.13433/j.cnki.1003-8728.20180163

面向腕臂动作识别的加速度计数据分析

doi: 10.13433/j.cnki.1003-8728.20180163

朱国康,
周涛

1.
安徽大学电子信息工程学院, 合肥 230601

基金项目:

国家自然科学基金项目（61503235、61603057、61602295、61663007、61672032）资助

详细信息

作者简介:
朱国康(1987-),讲师,博士,研究方向为数字信号处理、数据挖掘与分析,gzhu@ahu.edu.cn

计量
- 文章访问数: 314
- HTML全文浏览量: 35
- PDF下载量: 86
- 被引次数: 0
出版历程
- 收稿日期: 2017-05-02
- 刊出日期: 2018-09-05

Elbow-wrist Activity Recognition via Accelerometer Data Analysis

1.
School of Electronics and Information Engineering, Anhui University, Hefei 230601, China

摘要

摘要: 加速度传感器技术的不断发展和成熟为可穿戴设备的智能交互提供了新的途径。以可穿戴设备中的加速度计所捕捉的数据为支撑，对人的运动模式进行识别进而推断行为意图以实现智能化人机交互的方式，目前已受到人们的广泛关注。针对上述问题，本文基于循环神经网络的技术框架，提出一种高效的腕臂动作识别方法。该方法以单门控机制有效利用时序相关信息，对腕部可穿戴设备的三轴加速度计信号进行深度挖掘。实验结果表明，本文所提出的方法相较传统的机器学习方法而言性能更为可靠，能以更为简洁的网络结构取得与当前主流的循环神经网络算法同样的识别精度。
- 可穿戴设备 /
- 加速度计 /
- 传感器 /
- 循环神经网络 /
- 动作识别
Abstract: The present development of acceleration sensor technology provides a new way to the intelligent interaction of wearable devices. Nowadays, many researchers are interesting in identifying human activities through the data obtained by the accelerometers integrated in the wearable devices, and then inferring the behavior intentions for intelligent human-computer interaction. An efficient method of recognizing elbow-wrist activities is presented based on the recurrent neural network framework in this paper. The proposed method can deeply exploits the relevant sequential information embedded in the wearable tri-axis accelerometer data via a single-gated recurrent neural network. The experimental results show that the method proposed in this paper is more reliable than traditional machine learning methods, and is more concise in network structure to achieve an acceptable performance of elbow-wrist activity recognition compared with the current mainstream recurrent neural network algorithms.
- wearable device /
- accelerometer /
- sensor /
- recurrent neural network /
- activity recognition

HTML全文

参考文献(20)

[1]	Mintel Group Ltd. Digital trends-China-March 2016[EB/OL]. 2016. https://store.mintel.com/digital-trends-china-march-2016
[2]	Thorp E O. The invention of the first wearable computer[C]//Proceedings of the 2nd IEEE International Symposium on Wearable Computers. Washington, DC:IEEE, 1998:4-8
[3]	Kantar Worldpanel ComTech's. Quarterly report for wearable technology[EB/OL]. (2016-05-04) https://www.kantarworldpanel.com/global/News/Kantar-Launches-Quarterly-Report-for-Wearable-Technology
[4]	Choi E S, Bang W C, Cho S J, et al. Beatbox music phone:gesture-based interactive mobile phone using a tri-axis accelerometer[C]//Proceedings of International Conference on Industrial Technology. Hongkong, China:IEEE, 2005:97-102
[5]	Fujimoto T, Nakajima H, Tsuchiya N, et al. Wearable human activity recognition by electrocardiograph and accelerometer[C]//Proceedings of the 2013 IEEE 43rd International Symposium on Multiple-Valued Logic. Washington, DC:IEEE, 2013:12-17
[6]	Yurur O, Liu C H, Moreno W. Unsupervised posture detection by smartphone accelerometer[J]. Electronics Letters, 2013,49(8):562-564
[7]	Rodriguez-Martin D, Samà A, Perez-Lopez C, et al. SVM-based posture identification with a single waist-located triaxial accelerometer[J]. Expert Systems with Applications, 2013,40(18):7203-7211
[8]	Rodríguez-Martín D, Samà A, Pérez-López C, et al. Posture transition identification on PD patients through a SVM-based technique and a single waist-worn accelerometer[J]. Neurocomputing, 2015,164:144-153
[9]	Ahmed M E, Song J B. Non-parametric bayesian human motion recognition using a single MEMS tri-axial accelerometer[J]. Sensors, 2012,12(10):13185-13211
[10]	Gao L L, Campbell H A, Bidder O R, et al. A web-based semantic tagging and activity recognition system for species' accelerometry data[J]. Ecological Informatics, 2013,13:47-56
[11]	Zhou Y H, Cheng Z X, Jing L, et al. Pre-classification based hidden Markov model for quick and accurate gesture recognition using a finger-worn device[J]. Applied Intelligence, 2014,40(4):613-622
[12]	Martens J, Sutskever I. Learning recurrent neural networks with Hessian-free optimization[C]//Proceedings of the 28th International Conference on Machine Learning. Bellevue, Washington:ICML, 2011:1033-1040
[13]	Cho K, Van Merrienboer B, Gulcehre C, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation[J]. Computer Science, 2014
[14]	Mazumdar J, Harley R G. Recurrent neural networks trained with backpropagation through time algorithm to estimate nonlinear load harmonic currents[J]. IEEE Transactions on Industrial Electronics, 2008,55(9):3484-3491
[15]	Bersini H, Gorrini V. A simplification of the backpropagation-through-time algorithm for optimal neurocontrol[J]. IEEE Transactions on Neural Networks, 1997,8(2):437-441
[16]	Ketkar N. Deep Learning with Python[M]. Berkeley, CA:Apress, 2017
[17]	Johnson R, Zhang T. Accelerating stochastic gradient descent using predictive variance reduction[C]//Proceedings of the 26th International Conference on Neural Information Processing Systems. Cambridge:NIPS, 2013:315-323
[18]	Breiman L. Random forests[J]. Machine Learning, 2001, 45(1):5-32
[19]	Bartlett P, Freund Y, Lee W S, et al. Boosting the margin:a new explanation for the effectiveness of voting methods[J]. Annals of Statistics, 1998,26(5):1651-1686
[20]	Ukil A. Support vector machine[J]. Computer Science, 2002, 1(4):1-28