Inception neural network for human activity recognition using wearable sensor

Duo CHAI; Cheng XU; Jie HE; Shao-yang ZHANG; Shi-hong DUAN; Yue QI

doi:10.11959/j.issn.1000-436x.2017262

您当前的位置：

首页 >

文章列表页 >

Inception neural network for human activity recognition using wearable sensor

Papers | 更新时间：2024-06-05

- Inception neural network for human activity recognition using wearable sensor
- Journal on Communications Vol. 38, Issue Z2, Pages: 122-128(2017)
- 作者机构：
  
  1. 北京科技大学计算机与通信工程学院，北京 100083
  2. 材料领域知识工程北京市重点实验室，北京100083
- 作者简介：
- 基金信息：
  
  The National Key R＆D Program of China(2016YFC0901303);The National Natural Science Foundation of China(61671056);The National Natural Science Foundation of China(61302065);The National Natural Science Foundation of China(61304257);The National Natural Science Foundation of China(61402033);The Natural Science Foundation of Beijing(4152036);The Special Program for Science and Technology of Tianjin(16ZXCXSF00150)
- DOI：10.11959/j.issn.1000-436x.2017262
  CLC： TP391
- Online First：2017-11，
  
  Published：25 November 2017
- 稿件说明：
移动端阅览
Duo CHAI, Cheng XU, Jie HE, et al. Inception neural network for human activity recognition using wearable sensor[J]. Journal on Communications, 2017, 38(Z2): 122-128.
DOI：

Duo CHAI, Cheng XU, Jie HE, et al. Inception neural network for human activity recognition using wearable sensor[J]. Journal on Communications, 2017, 38(Z2): 122-128. DOI： 10.11959/j.issn.1000-436x.2017262.

摘要

通过迁移深度神经网络在图像识别方面的经验，提出了一种基于Inception神经网络和循环神经网络结合的深度学习模型（InnoHAR），该模型端对端地输入多通道传感器的波形数据，利用 1×1 卷积对多通道数据的有机组合，不同尺度的卷积提取不同尺度的波形特征，最大池化过滤微小扰动造成的假阳性，结合时间特征提取（GRU）为时序特征建模，充分利用数据特征完成分类任务。相比已知最优的神经网络模型，在识别准确度上有近 3%的提升，达到了state-of-the-art的水平，同时可以保证低功耗嵌入式平台的实时预测，且在网络结构组成上更加丰富，具有更大的潜力和挖掘空间。

Abstract

The experience from computer vision was learned

an innovative neural network model called InnoHAR (inception neural network for human activity recognition) based on the inception neural network and recurrent neural network was put forward

which started from an end-to-end multi-channel sensor waveform data

followed by the 1×1 convolution for better combination of the multi-channel data

and the various scales of convolution to extract the waveform characteristics of different scales

the max-pooling layer to prevent the disturbance of tiny noise causing false positives

combined with the feature of GRU helped to time-sequential modeling

made full use of the characteristics of data classification task.Compared with the state-of-the-art neural network model

the InnoHAR model has a promotion of 3% in the recognition accuracy

which has reached the state-of-the-art on the dataset we used

at the same time it still can guarantee the real-time prediction of low-power embedded platform

also with more space for future exploration.

关键词

Keywords

references

XU C , HE J , ZHANG X T , et al . Detection of freezing of gait using template-matching-based approaches [J ] . Journal of Sensors , 2017 , 2017 ( 2 ): 1 - 8 .

XU C , HE J , ZHANG X T , et al . Geometrical kinematic modeling on human motion using method of multi-sensor fusion [J ] . Information Fusion , 2017

MARGARITO J , HELAOUI R , BIANCHI A M , et al . User independent recognition of sports activities from a single wrist-worn accelerometer:a template-matching-based approach [J ] . IEEE Transactions on Bio-medical Engineering , 2015 , 63 ( 4 ): 788 - 796 .

ROY P C , GIROUX S , BOUCHARD B , et al . A possibilistic approach for activity recognition in smart homes for cognitive assistance to alzheimer’s patients [C ] // Activity Recognition in Pervasive Intelligent Environments . Atlantis Press , 2011 : 33 - 58 .

SZEGEDY C , LIU W , JIA Y , et al . Going deeper with convolutions [C ] // Computer Vision and Pattern Recognition . 2014 : 1 - 9 .

HE K , ZHANG X , REN S , et al . Deep residual learning for image recognition [C ] // Computer Vision and Pattern Recognition . 2015 : 770 - 778 .

BENGIO Y , LECUN Y . Convolutional networks for images,speech,and time-series [J ] . Convolutional Networks for Images,Speech and Time Series , 1995 .

GERS F A , SCHRAUDOLPH N N , SCHMIDHUBER J , et al . Learning precise timing with lstm recurrent networks [J ] . Journal of Machine Learning Research , 2003 , 3 ( 1 ): 115 - 143 .

ORDÓÑEZ F J , ROGGEN D . Deep convolutional and LSTM Recurrent neural networks for multimodal wearable activity recognition [J ] . Sensors , 2016 , 16 ( 1 ):115.

GERS F A , SCHRAUDOLPH N N, SCHMIDHUBER J , et al . Learn ing precise timing with lstm recurrent networks [J ] . Journal of Machine Learning Research , 2003 , 3 ( 1 ): 115 - 143 .

XU C , HE J , ZHANG X T , et al . Toward Near-Ground Localization:Modeling and Applications for TOA Ranging Error [J ] . IEEE Transactions on Antennas ＆ Propagation , 2017 , 65 ( 10 ): 5658 - 5662 .

CHAVARRIAGA R , SAGHA H , CALATRONI A , et al . The opportunity challenge:a benchmark database for on-body sensor-based activity recognition [J ] . Pattern Recognition Letters , 2013 , 34 ( 15 ): 2033 - 2042 .

Views

2064

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Sequential image deep learning-based Wi-Fi human activity recognition method

Review of unsupervised anomaly detection techniques for medical imaging

Target visibility prediction method based on cost-sensitive CNN-BiLSTM network

Multi-modal semantics aided mmWave beam prediction method in industrial haze environment

Robust RF fingerprint identification under temporal domain shifts via confidence discrepancy and entropy minimization

Related Author

Qizhen ZHOU

Jianchun XING

Qiliang YANG

Deshuai HAN

Zhao Yingcheng

Song Xiaogang

Shi Zhenghao

You Zhenzhen

Related Institution

College of Defense Engineering,Army Engineering University of PLA

College of Combat Support,Rocket Force University of Engineering

School of Computer Science and Engineering, Xi’an University of Technology

Shaanxi Key Laboratory for Network Computing and Security Technology

Human Machine Integration Intelligent Robot Shaanxi Provincial University Engineering Research Center

AI问答

⁰