Recognition of Abnormal Gait Based on Vibration Signal

WANG Cheng-liang; LIU Yi-luo

doi:10.12263/DZXB.20210871

您当前的位置：

首页 >

文章列表页 >

Recognition of Abnormal Gait Based on Vibration Signal

PAPERS | 更新时间：2025-12-08

- Recognition of Abnormal Gait Based on Vibration Signal
- ACTA ELECTRONICA SINICA Vol. 51, Issue 8, Pages: 2088-2097(2023)
- 作者机构：
  
  重庆大学计算机学院，重庆 400044
- 作者简介：
- 基金信息：
  
  Chongqing Technology Innovation and Application Development Special Major Theme Project(cstc2019jscx-zdztzxX0037;cstc2019jscx-gksbX0038)
- DOI：10.12263/DZXB.20210871
  CLC： TP391;
- Received：09 July 2021，
  
  Revised：2021-10-29，
  
  Published：25 August 2023
- 稿件说明：
移动端阅览
汪成亮,刘艺锣.基于震动信号的异常步态识别[J].电子学报,2023,51(08):2088-2097.

WANG Cheng-liang,LIU Yi-luo.Recognition of Abnormal Gait Based on Vibration Signal[J].ACTA ELECTRONICA SINICA,2023,51(08):2088-2097.
汪成亮,刘艺锣.基于震动信号的异常步态识别[J].电子学报,2023,51(08):2088-2097. DOI： 10.12263/DZXB.20210871.

WANG Cheng-liang,LIU Yi-luo.Recognition of Abnormal Gait Based on Vibration Signal[J].ACTA ELECTRONICA SINICA,2023,51(08):2088-2097. DOI： 10.12263/DZXB.20210871.

摘要

异常步态的识别对老年人的健康看护有很大帮助.现有的相关研究主要通过图像采集设备或穿戴设备获取相关特征信息进行识别，这些方法大多都具有侵入性或对用户有较高的操作要求.本文研究实现了一种基于对脚步震动信号为识别源进行异常步态和跌倒检测的系统原型，该系统通过本文设计的应用于大范围数据采集的多传感器协同信号采集方法采集信号，从中分割出有效部分作为活动元，去噪后再使用改进的动态时间规整算法（Dynamic Time Warping，DTW）计算出代表活动元之间差异性的异常指数，接着由K最近邻（K-Nearest Neighbor，KNN）算法分类异常指数，得到初步表征用户步态的推测值，最后由隐马尔科夫模型（Hidden Markov Model，HMM）进一步处理推测值，识别出用户的步态.实验结果表明，本文提出的方法能够有效在不同的步态模式下识别异常步态，在稳定的环境中识别准确率达到96%，在具有不稳定地板的环境中准确率为94%.

Abstract

The recognition of abnormal gait is of great help to the health care of the elderly. Existing related research mainly uses image acquisition equipment or wearable equipment to obtain relevant feature information for identification. Most of these methods are invasive or have high operational requirements for users. This paper studies and realizes a system prototype based on the detection of abnormal gait and fall based on foot vibration signals as the source of identification. This paper first designs a multi-sensor cooperative signal acquisition method to achieve a large range of signal acquisition

and separate the effective part from it as the active element. After the collected active elements are denoised

an improved dynamic time warping algorithm (DTW) is used to calculate the abnormal index representing the difference between active elements

then the abnormal index is classified by the K nearest neighbor (KNN) algorithm

and the inferred value that initially characterizes the user's gait is obtained. The inferred value is further processed by hidden Markov model (HMM) to identify the user's gait. The experimental results show that the method proposed in this paper can effectively identify abnormal gait in different gait modes

with an accuracy of 96% in a stable environment

and an accuracy of 94% in an environment with unstable floors.

关键词

Keywords

references

PIERLEONI P , BELLI A , PALMA L , et al . A high reliability wearable device for elderly fall detection [J ] . IEEE Sensors Journal , 2015 , 15 ( 8 ): 4544 - 4553 .

田皓宇 , 马昕 , 李贻斌 . 基于骨架信息的异常步态识别方法 [J ] . 吉林大学学报(工学版) , 2022 , 52 ( 4 ): 725 - 737 .

TIAN H Y , MA X , LI Y B . Skeleton-based abnormal gait recognition: A survey [J ] . Journal of Jilin University (Engineering and Technology Edition) , 2022 , 52 ( 4 ): 725 - 737 . (in Chinese)

ZENG Y Z , PATHAK P H , MOHAPATRA P . WiWho: WiFi-based person identification in smart spaces [C ] // 2016 15th ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN) . Piscataway : IEEE , 2016 : 1 - 12 .

WANG X C , RISTIC-DURRANT D , SPRANGER M , et al . Gait assessment system based on novel gait variability measures [C ] // 2017 International Conference on Rehabilitation Robotics (ICORR) . Piscataway : IEEE , 2017 : 467 - 472 .

GEIGER J T , KNEIßL M , SCHULLER B W , et al . Acoustic gait-based person identification using hidden Markov models [C ] // Proceedings of the 2014 Workshop on Mapping Personality Traits Challenge and Workshop . New York : ACM , 2014 : 25 - 30 .

HE S M , XIE K , CHEN W W , et al . Energy-aware routing for SWIPT in multi-hop energy-constrained wireless network [J ] . IEEE Access , 2018 , 6 : 17996 - 18008 .

YAO L X , KUSAKUNNIRAN W , WU Q , et al . Robust CNN-based gait verification and identification using skeleton gait energy image [C ] // 2018 Digital Image Computing: Techniques and Applications (DICTA) . Piscataway : IEEE , 2019 : 1 - 7 .

BABAEE M , LI L W , RIGOLL G . Gait recognition from incomplete gait cycle [C ] // 2018 25th IEEE International Conference on Image Processing (ICIP) . Piscataway : IEEE , 2018 : 768 - 772 .

NGUYEN T N , HUYNH H H , MEUNIER J . Skeleton-based abnormal gait detection [J ] . Sensors , 2016 , 16 ( 11 ): 1792 .

ZHANG H , YE C . RGB-D camera based walking pattern recognition by support vector machines for a smart rollator [J ] . International Journal of Intelligent Robotics and Applications , 2017 , 1 ( 1 ): 32 - 42 .

LIAO R J , CAO C S , GARCIA E B , et al . Pose-based temporal-spatial network (PTSN) for gait recognition with carrying and clothing variations [C ] // Chinese Conference on Biometric Recognition . Cham : Springer , 2017 : 474 - 483 .

RONAO C A , CHO S B . Human activity recognition using smartphone sensors with two-stage continuous hidden Markov models [C ] // 2014 10th International Conference on Natural Computation (ICNC) . Piscataway : IEEE , 2014 : 681 - 686 .

SAN-SEGUNDO R , BLUNCK H , MORENO-PIMENTEL J , et al . Robust human activity recognition using smartwatches and smartphones [J ] . Engineering Applications of Artificial Intelligence , 2018 , 72 : 190 - 202 .

LIN F , WANG A S , ZHUANG Y , et al . Smart insole: A wearable sensor device for unobtrusive gait monitoring in daily life [J ] . IEEE Transactions on Industrial Informatics , 2016 , 12 ( 6 ): 2281 - 2291 .

PAN S J , WANG N N , QIAN Y Q , et al . Indoor person identification through footstep induced structural vibration [C ] // Proceedings of the 16th International Workshop on Mobile Computing Systems and Applications . New York : ACM , 2015 : 81 - 86 .

CLEMENTE J , SONG W Z , VALERO M , et al . Indoor person identification and fall detection through non-intrusive floor seismic sensing [C ] // 2019 IEEE International Conference on Smart Computing (SMARTCOMP) . Piscataway : IEEE , 2019 : 417 - 424 .

CLEMENTE J , LI F Y , VALERO M , et al . Smart seismic sensing for indoor fall detection, location, and notification [J ] . IEEE Journal of Biomedical and Health Informatics , 2020 , 24 ( 2 ): 524 - 532 .

汪成亮 , 郑诚 , 曾卓 . 基于软件定义智能的睡眠动作识别 [J ] . 电子学报 , 2021 , 49 ( 1 ): 85 - 89 .

WANG C L , ZHENG C , ZENG Z . Sleep action recognition based on software-defined intelligence [J ] . Acta Electronica Sinica , 2021 , 49 ( 1 ): 85 - 89 . (in Chinese)

PAN S J , BONDE A , JING J , et al . BOES: Building occupancy estimation system using sparse ambient vibration monitoring [C ] // Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2014 . San Diego : SPIE , 2014 : 406 - 421 .

Pan S J , TONG Y , MOSTAFA M , et al . FootprintID: Indoor Pedestrian Identification through Ambient Structural Vibration Sensing [C ] // 2017 ACM Interact . Mob . Wearable Ubiquitous Technol (UBICOMP). New York : ACM , 2017 : 89 - 120 .

CHEN W Q , GUAN M N , WANG L , et al . FLoc: Device-free passive indoor localization in complex environments [C ] // 2017 IEEE International Conference on Communications (ICC) . Piscataway : IEEE , 2017 : 1 - 6 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

No data

Related Author

No data

Related Institution

No data

⁰