A Hybrid HMM/Kalman Filter for Tracking Hip Angle in Gait Cycle

Dong, Li; Wu, Jiankang; Bao, Xiaoming

doi:10.1093/ietisy/e89-d.7.2319

Cited by 18 publications

(18 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on the change of the hip angle and the angular speed of the thigh, the movement of the thigh, as shown in Fig. 1, can be segmented into four phases [10,16].…”

Section: Gait Segmentation and Characteristicsmentioning

confidence: 99%

“…Figure 5 shows a short segment of the estimation results of our method. The estimation results using the same model in [10] are shown in Fig. 5a.…”

Section: Parameters Initializationmentioning

confidence: 99%

“…We used the state dynamic model of [10], but with MNM. It means that we keep the state dynamic equation all the same at all phases as [10]. The average estimation errors for GPF-I and GPF-II are 4.28°, and 4.19°respectively.…”

Section: Initial Valuementioning

confidence: 99%

“…Dong et al [9] considered the temporal dynamic properties and assumed that the dynamic model of thighs was linear, and used extended Kalman filter (EKF) to estimate the hip angle from the accelerometer measurements. In [10], Dong et al further improved their work and paid attention to nonlinearity of the motion. They used Hidden Markov Model (HMM) to detect the critical events in gait cycle, and then updated the results by EKF.…”

Section: Introductionmentioning

confidence: 99%

“…Hip angle estimation result using the model proposed by[10]. b Hip angle estimation result using MNM without MDM.…”

mentioning

confidence: 99%

See 4 more Smart Citations

Ambulatory Hip Angle Estimation using Gaussian Particle Filter

Zhang

Huang

2009

J Sign Process Syst Sign Image Video Technol

View full text Add to dashboard Cite

Hip angle is a major parameter in gait analysis while gait analysis plays an important role in healthcare, animation and other applications. Accurate estimation of hip angle using wearable inertial sensors in ambulatory environment remains a challenge 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) to model the nonlinear hip angle dynamics and variation of measurement noise levels, and Gaussian Particle Filter (GPF) to estimate the hip angle during gait cycles from the measurements of the wearable accelerometers that are attached to the thighs. The experiments have been conducted and the results have shown that the proposed method can achieve significant accuracy improvement over the previous work on the ambulatory hip angle estimation.

show abstract

“…Based on the change of the hip angle and the angular speed of the thigh, the movement of the thigh, as shown in Fig. 1, can be segmented into four phases [10,16].…”

Section: Gait Segmentation and Characteristicsmentioning

confidence: 99%

“…Figure 5 shows a short segment of the estimation results of our method. The estimation results using the same model in [10] are shown in Fig. 5a.…”

Section: Parameters Initializationmentioning

confidence: 99%

Section: Initial Valuementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…Hip angle estimation result using the model proposed by[10]. b Hip angle estimation result using MNM without MDM.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Ambulatory Hip Angle Estimation using Gaussian Particle Filter

Zhang

Huang

2009

J Sign Process Syst Sign Image Video Technol

View full text Add to dashboard Cite

show abstract

A comparison of machine learning models’ accuracy in predicting lower-limb joints’ kinematics, kinetics, and muscle forces from wearable sensors

Moghadam

Yeung

Choisne

2023

Sci Rep

View full text Add to dashboard Cite

A combination of wearable sensors’ data and Machine Learning (ML) techniques has been used in many studies to predict specific joint angles and moments. The aim of this study was to compare the performance of four different non-linear regression ML models to estimate lower-limb joints’ kinematics, kinetics, and muscle forces using Inertial Measurement Units (IMUs) and electromyographys’ (EMGs) data. Seventeen healthy volunteers (9F, 28 ± 5 years) were asked to walk over-ground for a minimum of 16 trials. For each trial, marker trajectories and three force-plates data were recorded to calculate pelvis, hip, knee, and ankle kinematics and kinetics, and muscle forces (the targets), as well as 7 IMUs and 16 EMGs. The features from sensors’ data were extracted using the Tsfresh python package and fed into 4 ML models; Convolutional Neural Networks (CNN), Random Forest (RF), Support Vector Machine, and Multivariate Adaptive Regression Spline for targets’ prediction. The RF and CNN models outperformed the other ML models by providing lower prediction errors in all intended targets with a lower computational cost. This study suggested that a combination of wearable sensors’ data with an RF or a CNN model is a promising tool to overcome the limitations of traditional optical motion capture for 3D gait analysis.

show abstract

Multi-model adaptation for thigh movement estimation using accelerometers

Zhang

Huang

et al. 2011

IET Signal Process.

View full text Add to dashboard Cite

A Hybrid HMM/Kalman Filter for Tracking Hip Angle in Gait Cycle

Cited by 18 publications

References 0 publications

Ambulatory Hip Angle Estimation using Gaussian Particle Filter

Ambulatory Hip Angle Estimation using Gaussian Particle Filter

A comparison of machine learning models’ accuracy in predicting lower-limb joints’ kinematics, kinetics, and muscle forces from wearable sensors

Multi-model adaptation for thigh movement estimation using accelerometers

Contact Info

Product

Resources

About