髋关节角多模型贝叶斯动态估计

张志强; 黄志蓓; 吴健康

doi:10.3724/SP.J.1146.2010.00885

髋关节角多模型贝叶斯动态估计

doi: 10.3724/SP.J.1146.2010.00885

基金项目:

中国新加坡数字媒体研究院(China-Singapore Institute of Digital Media，CSIDM-200802)和国家自然科学基金重点项目(60932001)资助课题

计量
- 文章访问数: 3609
- HTML全文浏览量: 103
- PDF下载量: 880
- 被引次数: 0
出版历程
- 收稿日期: 2010-08-19
- 修回日期: 2010-11-22
- 刊出日期: 2011-04-19

Ambulatory Hip Angle Estimation Using Multiple Model Hybrid Dynamic Bayesian Networks

摘要

摘要: 步态分析在健康监测等领域中有着广泛的应用，精确估计髋关节角是步态分析的前提。但是大腿运动的高度非线性和不确定性，以及微型传感器测量噪声的不稳定性等诸多因素，基于微型惯性传感器的髋关节角精确估计面临着巨大的挑战。该文提出利用混合动态贝叶斯网络、多运动模型和噪声模型对髋关节角的非线性变化和测量噪声的改变进行建模，然后基于穿戴在大腿上的微型加速度传感器获得的测量值，通过高斯粒子滤波算法估计髋关节角度。实验结果表明该方法能够有效提高髋关节角的估计精度。
- 贝叶斯网络 /
- 粒子滤波 /
- 髋关节角估计
Abstract: Hip angle is a major parameter in gait analysis while gait analysis plays important role in healthcare, animation and other applications. Accurate estimation of hip angle using wearable inertial sensors in ambulatory environment remains a challenge, this is mainly because (1) the non-linear nature of thigh movement has not been well addressed, and (2) the variation of micro-inertial sensor measurement noise has not been studied yet. We propose to use Hybrid Dynamic Bayesian Network (HDBN) and multiple motion models and multiple noise models to model the non-linear hip angle dynamics and variation of measurement noise levels. Gaussian Particle Filter (GPF) is employed to estimate the hip angle during gait cycles from the measurements of accelerometers that are attached to the thighs. The experimental results show that the proposed method can achieve significant accuracy improvement over the previous work on the ambulatory hip angle estimation.
- Bayesian network /
- Particle filter /
- Hip angle estimation

HTML全文

参考文献(1)

Baechlin M, Plotnik M, and Roggen D, et al.. Wearable assistant for Parkinsons disease patients with the freezing of gait symptom [J]. IEEE Transactions on Information Technology in Biomedicine, 2010, 14(2): 436-446 .[2] Wittwer J E, Webster K E, and Menz H B. A longitudinal study of measures of walking in people with alzheimers disease [J]. Gait Posture, 2010, 32(1): 113-117. [3] Wong A Y C, Sangeux M, and Baker R. Calculation of joint moments following foot contact across two force plates [J]. Gait Posture, 2010, 31(2): 292-293. [4] Vlasic D, Adelsberger R, and Vannucci G, et al.. Practical motion capture in everyday surroundings [J]. ACM Transactions on Graphics, 2007, 26(3): 35-44. [5] Schepers H M. Ambulatory assessment of human body kinematics and kinetics [D]. [Ph.D. dissertation], University of Twente, 2009. [6] Dejnabadi H, Jolles B M, and Aminian K. A new approach for quantitative analysis of inter-joint coordination during gait [J]. IEEE Transactions on Biomedical Engineering, 2008, 55(2): 755-764.[7] Favre J, Jolles B M, Siegrist O, and Aminian K. Quaternion-based fusion of gyroscopes and accelerometers to improve 3D angle measurement [J]. Electronics Letters, 2006, 42(11): 612-614. [8] Dong L, Wu J K, and Bao X M. Tracking of thigh flexion angle during gait cycles in an ambulatory activity monitoring sensor network [J]. Acta Automatica Sinica, 2006, 32(6): 938-946.[9] Dong L, Wu J K, and Bao X M. A hybrid HMM/Kalman filter for tracking hip angle in gait cycle [J]. IEICE Transection on Information and Systems, 2006, 89(7): 2319-2323.[10] Olanrewajua M J, Huang B, and Artin Afacana. Online composition estimation and experiment validation of distillation processes with switching dynamics [J]. Chemical Engineering Science, 2010, 65(5): 1597-1608. [11] Geromel J C, Goncalves A P C, and Fioravanti A R. Dynamic output feedback control of discrete-time Markov jump linear systems through linear matrix inequalities[J]. SIAM Journal on Control and Optimization, 2009, 48(2): 573-593.[12] Pang S K, Nelson J D B, and Godsill S J, et al.. Video tracking using dual-tree wavelet polar matching and rao-blackwellised particle filter [J]. EURASIP Journal on Advances in Signal Processing, 2009, DOI: 10.1155/ 20091620404. [13] Hutter F and Dearden R. The gaussian particle filter for diagnosis of non-linear systems [C]. Proceedings of the Fourteenth International Workshop on the Principles of Diagnosis, Washington DC, USA, 2003: 65-70.[14] Murray M, Drought A B, and Kory R C. Walking patterns of normal men [J]. The Journal of Bone and Joint Surgery, 1964, 46(2): 335-360.

施引文献

资源附件(0)

访问统计