XIANG Mian, YI Benshun, ZHOU Bingtao, TAN Jianjun, ZHU Li. Analysis of Running Parameters Using IMU and Multi-modal Network[J]. Geomatics and Information Science of Wuhan University, 2024, 49(7): 1079-1087. DOI: 10.13203/j.whugis20220229
Citation: XIANG Mian, YI Benshun, ZHOU Bingtao, TAN Jianjun, ZHU Li. Analysis of Running Parameters Using IMU and Multi-modal Network[J]. Geomatics and Information Science of Wuhan University, 2024, 49(7): 1079-1087. DOI: 10.13203/j.whugis20220229

Analysis of Running Parameters Using IMU and Multi-modal Network

More Information
  • Received Date: June 23, 2023
  • Available Online: November 20, 2023
  • Objectives 

    Real-time measurement of running speed and stride length is of great significance in avoiding injury and improving exercise efficiency.

    Methods 

    We propose a method using inertial measurement unit (IMU) to detect these two indicators. First, 3 IMU are placed on the foot, calf and thigh of the 10 runners which we recruited, and 5 137 data of gait cycles are collected. Second, principal component analysis is used to analyze the data, and Pearson correlation coefficient is used to discuss the relationship between the detection indicators of running and the sensor position and physical parameters. Then a multi-modal attention-long short-term memory (M-Att-LSTM ) is proposed for feature extraction, two long short-term memory (LSTM) modules with attention mechanism are used to extract features of acceleration and angle, and regression fitting is carried out.

    Results 

    The experiment result shows that M-Att-LSTM has errors of 0.058 m/s in speed and 0.023 m in stride, the standard deviation is 0.013 m/s and 0.022 m, respectively.Both indicators are better than pure Att-LSTM.

    Conclusions 

    The studies show that multi-modal network can improve network processing capabilities, compared with relevant researches in recent years, our study has obvious advantages in error control.

  • [1]
    黄东晋, 姚院秋, 丁友东, 等. 基于Kinect的虚拟健身跑锻炼系统[J]. 图学学报, 2017, 38(5): 789-795.

    Huang Dongjin, Yao Yuanqiu, Ding Youdong, et al. Virtual Running Exercise System Based on Kinect[J]. Journal of Graphics, 2017, 38(5): 789-795.
    [2]
    宋淑华, 刘坚, 高春刚, 等. 递增负荷运动对中长跑运动员心率变异性的影响[J]. 山东体育学院学报, 2010, 26(10): 62-65.

    Song Shuhua,Liu Jian,Gao Chungang, et al. Influen‑ce on Heart Rate Variability of Middle-Long Distance Athletes During Progressive Increasing Load Exercise[J]. Journal of Shandong Institute of Physical Education and Sports, 2010, 26(10): 62-65.
    [3]
    段子才, 张戈. 不同步频和步幅的5 km跑过程中运动员心率变化的对比研究[J]. 体育科学, 2006, 26(4): 65-66.

    Duan Zicai, Zhang Ge. Comparative Study on Athlete’s Heart Rate Change of 5 km Running at Different Stride Frequency and Length[J].China Sport Scien‑ce, 2006, 26(4): 65-66.
    [4]
    王俊清, 张希妮, 罗震, 等. 步频再训练对跑步时下肢冲击的生物力学影响研究[J]. 应用力学学报, 2020, 37(5): 2167-2175.

    Wang Junqing, Zhang Xini, Luo Zhen, et al. The Influence of Cadence Retraining on Impact Forces and Lower Extremity Biomechanics During Running[J]. Chinese Journal of Applied Mechanics, 2020, 37(5): 2167-2175.
    [5]
    陈国良, 杨洲. 基于加速度量测幅值零速检测的计步算法研究[J]. 武汉大学学报(信息科学版), 2017, 42(6): 726-730.

    Chen Guoliang, Yang Zhou. Step Counting Algorithm Based on Zero Velocity Update[J]. Geomatics and Information Science of Wuhan University, 2017, 42(6): 726-730.
    [6]
    张小红, 罗科干, 陶贤露, 等. 一种基于穿戴式MEMS传感器状态识别的多部位PDR算法[J]. 武汉大学学报(信息科学版), 2021, 46(12): 1791-1801.

    Zhang Xiaohong, Luo Kegan, Tao Xianlu, et al. A Multi-mouted PDR Algorithm Based on Wearable MEMS Sensors State Recognition[J]. Geomatics and Information Science of Wuhan University, 2021, 46(12): 1791-1801.
    [7]
    张小红, 陶贤露, 王颖喆, 等. 城市场景智能手机GNSS/MEMS融合车载高精度定位[J]. 武汉大学学报(信息科学版), 2022, 47(10): 1740-1749.

    Zhang Xiaohong, Tao Xianlu, Wang Yingzhe, et al. MEMS-Enhanced Smartphone GNSS High-Precision Positioning for Vehicular Navigation in Urban Conditions[J]. Geomatics and Information Science of Wuhan University, 2022, 47(10): 1740-1749.
    [8]
    周丙涛, 陈世强, 程宇阳, 等. 基于足底压力传感器与深度学习的生物身份识别[J]. 仪器仪表学报, 2021, 42(7): 108-115.

    Zhou Bingtao, Chen Shiqiang, Cheng Yuyang, et al. Biometric Identification Based on Plantar Pressure Sensor and Deep Learning[J]. Chinese Journal of Scientific Instrument, 2021, 42(7): 108-115.
    [9]
    邱石, 杜义浩, 王浩, 等. 基于sEMG的下肢运动解析方法研究[J]. 仪器仪表学报, 2018, 39(2): 30-37.

    Qiu Shi, Du Yihao, Wang Hao, et al. Research on Lower Limb Kinematic Analysis Method Based on sEMG[J]. Chinese Journal of Scientific Instrument, 2018, 39(2): 30-37.
    [10]
    王智敏, 陶宝林, 于鹏, 等. 基于可穿戴式惯性测量单元的行人室内定位技术[J].传感器与微系统,2021,40(1): 46-48.

    Wang Zhimin, Tao Baolin, Yu Peng, et al. Indoor Positioning Technology of Pedestrian Based on Wearable IMU[J]. Transducer and Microsystem Technologies, 2021, 40(1): 46-48.
    [11]
    Vezočnik M, Kamnik R, Juric M B. Inertial Sensor-Based Step Length Estimation Model by Means of Principal Component Analysis[J]. Sensors, 2021, 21(10): 3527.
    [12]
    路泽忠, 卢小平, 马靓婷, 等. 双状态机的自适应步态检测算法[J]. 测绘科学, 2021, 46(1): 56-61.

    Lu Zezhong, Lu Xiaoping, Ma Liangting, et al. Adaptive Gait Detection Algorithm Based on Dual State Machine[J]. Science of Surveying and Mapping, 2021, 46(1): 56-61.
    [13]
    李清泉, 陈睿哲, 涂伟, 等. 基于惯性相机的大跨度桥梁线形形变实时测量方法[J]. 武汉大学学报(信息科学版), 2023, 48(11): 1834-1843.

    Li Qingquan, Chen Ruizhe, Tu Wei, et al. Real-Time Vision-Based Deformation Measurement of Long-Span Bridge with Inertial Sensors[J]. Geomatics and Information Science of Wuhan University, 2023, 48(11): 1834-1843.
    [14]
    Su B Y, Wang J, Liu S Q, et al. A CNN-Based Method for Intent Recognition Using Inertial Measurement Units and Intelligent Lower Limb Prosthesis[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering,2019,27(5):1032-1042.
    [15]
    Gao F, Liu G Y, Liang F Y, et al. IMU-Based Locomotion Mode Identification for Transtibial Prostheses, Orthoses, and Exoskeletons[J].IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2020, 28(6): 1334-1343.
    [16]
    Bruinsma J, Carloni R. IMU-Based Deep Neural Networks: Prediction of Locomotor and Transition Intentions of an Osseointegrated Transfemoral Amputee[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering: A Publication of the IEEE Engineering in Medicine and Biology Society, 2021, 29: 1079-1088.
    [17]
    盛敏, 刘双庆, 王婕, 等. 基于GMM-HMM模型的智能下肢假肢运动意图识别[J]. 仪器仪表学报, 2019, 40(5): 169-178.

    Sheng Min, Liu Shuangqing, Wang Jie, et al. Motion Intent Recognition of Intelligent Lower Limb Prosthesis Based on GMM-HMM[J]. Chinese Journal of Scientific Instrument, 2019, 40(5): 169-178.
    [18]
    Yu S Y, Yang J F, Huang T H, et al. Artificial Neural Network-Based Activities Classification, Gait Phase Estimation, and Prediction[J].Annals of Biomedical Engineering,2023,51(7):1471-1484.
    [19]
    Baniasad M, Martin R, Crevoisier X, et al. Automatic Body Segment and Side Recognition of an Inertial Measurement Unit Sensor During Gait[J]. Sensors, 2023, 23(7): 3587.
    [20]
    Do T N, Liu R, Yuen C, et al. Personal Dead Reckoning Using IMU Device at Upper Torso for Walking and Running[C]//IEEE Sensors, Orlando, USA, 2016.
    [21]
    Elshehabi M,Del Din S,Hobert M A,et al.Walking Parameters of Older Adults from a Lower Back Inertial Measurement Unit, a 6-Year Longitudinal Observational Study[J].Frontiers in Aging Neuroscien‑ce, 2022, 14: 789220.
    [22]
    Koroglu M T, Yilmaz A,Saul C J.A Deep Learning Strategy for Stride Detection[C]//IEEE Sensors, New Delhi, India, 2018.
    [23]
    Anwary A R, Yu H N, Vassallo M. Optimal Foot Location for Placing Wearable IMU Sensors and Automatic Feature Extraction for Gait Analysis[J]. IEEE Sensors Journal, 2018, 18(6): 2555-2567.
    [24]
    Hutabarat Y, Owaki D, Hayashibe M. Quantitative Gait Assessment with Feature-Rich Diversity Using Two IMU Sensors[J]. IEEE Transactions on Medical Robotics and Bionics, 2020, 2(4): 639-648.
    [25]
    Uno Y, Ogasawara I, Konda S, et al. Validity of Spatio-Temporal Gait Parameters in Healthy Young Adults Using a Motion-Sensor-Based Gait Analysis System (ORPHE ANALYTICS) During Walking and Running[J]. Sensors (Basel, Switzerland), 2022, 23(1): 331.
    [26]
    路永乐, 陈永炜, 邸克, 等. 基于MEMS惯性传感器的高精度步长估计算法[J]. 中国惯性技术学报, 2018, 26(2): 167-172.

    Lu Yongle, Chen Yongwei, Di Ke, et al. High-Precision Step-Length Estimation Method Based on MEMS Inertial Sensor[J]. Journal of Chinese Inertial Technology, 2018, 26(2): 167-172.
    [27]
    Sui J D, Chang T S. IMU Based Deep Stride Length Estimation with Self-supervised Learning[J]. IEEE Sensors Journal, 2021, 21(6): 7380-7387.
  • Related Articles

    [1]LIU Xiaojie, ZHAO Chaoying, LI Bin, WANG Wenda, ZHANG Qin, GAO Yang, CHEN Liquan, WANG Baohang, HAO Junming, YANG Xiaohui. Identification and Dynamic Deformation Monitoring of Active Landslides in Jishishan Earthquake Area (Gansu, China) Using InSAR Technology[J]. Geomatics and Information Science of Wuhan University, 2025, 50(2): 297-312. DOI: 10.13203/j.whugis20240054
    [2]YANG Chengsheng, LI Xiaoyang, ZHANG Qin, WEI Yunjie, LI Zufeng, ZHU Sainan. Monitoring and Analysis of Post-Earthquake Landslide in Sindhupalchowk District, Nepal Based on InSAR Technology[J]. Geomatics and Information Science of Wuhan University, 2023, 48(10): 1684-1696. DOI: 10.13203/j.whugis20230258
    [3]LI Menghua, ZHANG Lu, DONG Jie, CAI Jiehua, LIAO Mingsheng. Detection and Monitoring of Potential Landslides Along Minjiang River Valley in Maoxian County, Sichuan Using Radar Remote Sensing[J]. Geomatics and Information Science of Wuhan University, 2021, 46(10): 1529-1537. DOI: 10.13203/j.whugis20210367
    [5]ZHAO Chaoying, LIU Xiaojie, ZHANG Qin, PENG Jianbing, XU Qiang. Research on Loess Landslide Identification, Monitoring and Failure Mode with InSAR Technique in Heifangtai, Gansu[J]. Geomatics and Information Science of Wuhan University, 2019, 44(7): 996-1007. DOI: 10.13203/j.whugis20190072
    [6]ZHOU Lü, GUO Jiming, HU Jiyuan, ZHANG Di, CHEN Ming, YANG Fei. Accuracy Verification and Analysis of Ground-based Synthetic Aperture Radar Based on Two-dimensional Deformation Field[J]. Geomatics and Information Science of Wuhan University, 2019, 44(2): 289-295. DOI: 10.13203/j.whugis20170085
    [7]WENG Yinkan, LI Song, YANG Jinling, YI Hong, WANG Hong, MA Yue. Fast Solution to the RCS of Corner Reflector for the SAR Radiometric Calibration[J]. Geomatics and Information Science of Wuhan University, 2015, 40(11): 1551-1556. DOI: 10.13203/j.whugis20130613
    [8]ZHAO Chaoying, ZHANG Qin, ZHU Wu1 LU Zhong, . Monitoring on Xi'an Ground Fissures Deformation with TerraSAR-X Data[J]. Geomatics and Information Science of Wuhan University, 2012, 37(1): 81-85.
    [9]uemin, ZHU Jianjun, WANG Changcheng, YI Heng. A New Method for CR Point Identification and It's Application to Highway Deformation Monitoring[J]. Geomatics and Information Science of Wuhan University, 2011, 36(6): 699-703.
    [10]XIAO Ping, LI Deren. Land Use/Cover Change Detection Based on Artificial Neural Network[J]. Geomatics and Information Science of Wuhan University, 2002, 27(6): 586-590.
  • Cited by

    Periodical cited type(34)

    1. 祝会忠,桂宇强,沈祎凡,王强. 基于GNSS-IR高度角偏差修正方法的研究与评估. 大地测量与地球动力学. 2025(02): 111-115 .
    2. 王笑蕾,杨泽艺,何秀凤,宋敏峰. GPS L2P(Y)信号在GNSS-IR技术中的特殊误差源及改正方法. 武汉大学学报(信息科学版). 2024(01): 122-130 .
    3. 郑南山,何佳星,丁锐,章恒一. 基于轨迹聚类的GNSS-IR多系统组合土壤湿度估计方法. 武汉大学学报(信息科学版). 2024(01): 37-46 .
    4. 刘善伟,梁承佳,万玮,张洁,马望. 一种考虑地形影响的GNSS-IR冻土冻融形变监测方法. 武汉大学学报(信息科学版). 2024(01): 77-89 .
    5. 邓垦,周佩元,杜兰,蔡巍. 多系统单频紧组合GNSS-R测高方法. 武汉大学学报(信息科学版). 2024(01): 146-155 .
    6. 黄令勇,李世忠,夏俊明,王海岩,孙越强,杨日新,杜起飞,黄志勇. 岸基条件下的星载GNSS-R干涉测高精度验证评估. 测绘学报. 2024(02): 239-251 .
    7. 王笑蕾,南阳,何秀凤,宋敏峰. 考虑潮波特性的GNSS-IR潮位反演方法. 测绘学报. 2024(03): 482-492 .
    8. 郭斐,陈惟杰,朱逸凡,张小红. 一种融合相位、振幅与频率的GNSS-IR土壤湿度反演方法. 武汉大学学报(信息科学版). 2024(05): 715-721 .
    9. 刘续,王式太,钟振华,殷敏,魏嘉林,姜新伟. 不同极化方式天线对GNSS-IR高度反演的影响. 导航定位学报. 2024(05): 139-148 .
    10. 余锐,刘洋,王清泉,高建伟,张郁,胡羽丰. 长时序多模多频GNSS-IR潮位反演综合比较分析. 武汉大学学报(信息科学版). 2024(12): 2210-2222 .
    11. 宋敏峰,何秀凤,王笑蕾. 顾及残余信噪比差异的地基GNSS反射干涉信号冰期探测法. 测绘学报. 2024(12): 2295-2304 .
    12. 王笑蕾,牛紫瑾,何秀凤,李润川. 沿海沉降变化GNSS定位及GNSS-IR组合监测. 测绘学报. 2023(01): 32-40 .
    13. Xiaolei WANG,Zijin NIU,Xiufeng HE,Runchuan LI. Monitoring of Coastal Subsidence Changes Based on GNSS Positioning and GNSS-IR. Journal of Geodesy and Geoinformation Science. 2023(02): 71-80 .
    14. 宋敏峰,何秀凤,王笑蕾,肖儒雅,贾东振,李伟强. 顾及地球曲率及椭球高的GNSS-R几何计算方法. 测绘学报. 2023(06): 884-894 .
    15. 桑文刚,王昭然,张兴国,靳奉祥. 岸基GPS-R水面高反演测站时空布局优化. 测绘通报. 2023(09): 40-45 .
    16. 聂士海,王龙,王梦柯,李鹏,梁磊,黄丹妮,刘斌. 结合机器学习的GNSS-IR多卫星双频组合土壤湿度反演. 测绘通报. 2023(10): 98-104 .
    17. 薛张芳,刘立龙,吴昊舰,张志,刘睿国. 利用CEEMDAN进行GNSS-MR雪深反演. 大地测量与地球动力学. 2022(01): 25-28 .
    18. 张一,周立. 基于NARX回归神经网络的岸基GNSS-IR有效波高反演模型分析. 测绘通报. 2022(02): 90-94 .
    19. 桑文刚,刘迎春,何秀凤,王昭然. 库区GNSS-R精细化反演水面高度及其验证研究. 全球定位系统. 2022(01): 43-48 .
    20. 游高冲,郭杭,罗孝文,尹海博,王朝阳. 基于LS-SVM的多系统融合GNSS-MR潮位反演. 海洋学研究. 2022(01): 72-80 .
    21. 贾秀丽. 高斯过程回归辅助下的GPS干涉反射积雪深度估测. 测绘通报. 2022(07): 78-82 .
    22. 刘睿国,刘立龙,吴晗,薛张芳,吴昊舰,张志. 奇异谱分析在GNSS-MR海平面高度反演中的应用. 无线电工程. 2022(11): 1994-1999 .
    23. 王笑蕾,何秀凤,宋敏峰,陈殊,牛紫瑾. 多模多频GNSS-IR水位反演中的频间偏差分析及改正. 测绘学报. 2022(11): 2328-2338 .
    24. 邓攀,王泽民,安家春,张辛,于秋则,孙伟. 利用小波分解的GNSS-R雪厚反演改进算法. 武汉大学学报(信息科学版). 2021(06): 863-870 .
    25. Shuangcheng ZHANG,Meiling ZHOU,Yajie WANG,Ning LIU,Qi LIU,Jilun PENG. Ground-based GPS Used in the Snow Depth Survey of Greenland. Journal of Geodesy and Geoinformation Science. 2021(02): 47-55 .
    26. 张双成,王涛,王丽霞,张京江,刘宁,赵桂生. BDS/GPS多卫星解译土壤湿度变化研究. 测绘科学. 2021(07): 7-14 .
    27. 王笑蕾,何秀凤,陈殊,张勤,宋敏峰. 地基GNSS-IR风速反演原理及方法初探. 测绘学报. 2021(10): 1298-1307 .
    28. 吕铮,冯威,黄丁发. GNSS SNR信号反演大坝水位变化. 大地测量与地球动力学. 2020(02): 146-151 .
    29. 任超,潘亚龙,梁月吉,张志刚,黄仪邦. 基于GPS-IR的土壤湿度多星非线性回归估算模型. 遥感信息. 2020(02): 14-18 .
    30. 边少锋,周威,刘立龙,李厚朴,刘备. 小波变换与滑动窗口相结合的GNSS-IR雪深估测模型. 测绘学报. 2020(09): 1179-1188 .
    31. 王韩波,李红彦,张志刚,潘亚龙,李现广. 基于小波分析和LS-SVM的积雪厚度多星融合反演. 测绘科学. 2020(12): 95-101 .
    32. 李毅,任超,张志刚,梁月吉,潘亚龙. 基于多元线性回归的GPS-IR积雪深度反演研究. 遥感技术与应用. 2020(06): 1312-1319 .
    33. 张双成,武慧琳,张化疑,南阳,刘焱熊,周兴华,刘奇. 中国沿海GPS站用于潮波系数提取分析. 海洋测绘. 2019(03): 1-5+15 .
    34. 周威,黄良珂,刘立龙,陈军,李松青. 基于GLONASS-MR技术的雪深探测研究. 地球物理学进展. 2019(05): 1842-1848 .

    Other cited types(15)

Catalog

    Article views (251) PDF downloads (78) Cited by(49)
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return