Real-time conversion of inertial measurement unit data to ankle joint angles using deep neural networks

Senanayake, Damith; Halgamuge, Saman K.; Ackland, David C.

doi:10.1016/j.jbiomech.2021.110552

Cited by 11 publications

(5 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Kinematics can be solved in real-time via inertial measurement units [37] or computer vision [20], where the developed NN can then provide lmt, r, and mLOA estimates for NMS models. Alternatively, the developed NN may be embedded within increasingly prevalent combinations of wearable sensors and computer vision technologies with deep learning methods for estimating biomechanics [38][39][40]. The NN estimated lmt, r, and mLOA may also be used to embed contraction dynamics and to allow equations of motions to be solved in novel physics-informed neural networks [41].…”

Section: Discussionmentioning

confidence: 99%

Real-time calibration-free musculotendon kinematics for neuromusculoskeletal models

Cornish,

Diamond,

Saxby

et al. 2024

Preprint

View full text Add to dashboard Cite

Neuromusculoskeletal (NMS) models enable non-invasive estimation of clinically important internal biomechanics. A critical part of NMS modelling involves estimating musculotendon kinematics, which comprise musculotendon unit lengths, moment arms, and lines of action. Musculotendon kinematics, which are partially dependent on joint motions, define the non-linear mapping of muscle forces to joint moments and contact forces. Currently, real-time computation of musculotendon kinematics requires creation of a per-individual surrogate model. The computational speed and accuracy of these surrogates degrade with increasing number of coordinates. We developed a feed-forward neural network that completely encodes musculotendon kinematics of a target model across a wide anthropometric range, enabling accurate real-time estimates of musculotendon kinematics without need for a priori per-individual surrogate model. Compared to reference, the neural network had median normalized errors ~0.1% for musculotendon lengths, <0.4% for moment arms, and <0.10° for line of action orientations. The neural network was employed within an electromyography-informed NMS model to calculate hip contact forces, demonstrating little difference (normalized root mean square error 1.23±0.15%) compared to using reference musculotendon kinematics. Finally, execution time was <0.04 ms per frame and constant for increasing number of model coordinates. Our approach to musculoskeletal kinematics may facilitate deployment of complex real-time NMS modelling in computer vision or wearable sensors applications to realize biomechanics monitoring, rehabilitation, and disease management outside the research laboratory.

show abstract

Section: Discussionmentioning

confidence: 99%

Real-time calibration-free musculotendon kinematics for neuromusculoskeletal models

Cornish,

Diamond,

Saxby

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Artificial neural networks have been used to analyze large datasets of IMU sensor data, identify human movement patterns and generate joint angles in an automated manner [ 130 , 131 , 132 ]. For example, Senanayake et al (2021) developed a generative adversarial network (GAN) that predicted 3D ankle joint angles using raw IMU data, achieving an accuracy of

and

in dorsiflexion, inversion, and axial rotation, respectively [ 133 ]. Mundt et al (2020) estimated 3D lower limb joint angles during gait using a feedforward neural network and achieved RMS errors lower than

, with the best results in the sagittal motion plane [ 134 ].…”

Section: Discussionmentioning

confidence: 99%

Conversion of Upper-Limb Inertial Measurement Unit Data to Joint Angles: A Systematic Review

Fang

Woodford

Senanayake

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

Inertial measurement units (IMUs) have become the mainstay in motion evaluation outside of the laboratory; however, quantification of 3-dimensional upper limb motion using IMUs remains challenging. The objective of this systematic review is twofold. Firstly, to evaluate computational methods used to convert IMU data to joint angles in the upper limb, including for the scapulothoracic, humerothoracic, glenohumeral, and elbow joints; the second was to quantify the accuracy of these approaches when compared to optoelectronic motion analysis. Fifty-two studies were included. Maximum joint motion measurement accuracy from IMUs was achieved using Euler angle decomposition and Kalman-based filters. This resulted in differences between IMU and optoelectronic motion analysis of 4° across all degrees of freedom of humerothoracic movement. Higher accuracy has been achieved at the elbow joint with functional joint axis calibration tasks and the use of kinematic constraints on gyroscope data, resulting in RMS errors between IMU and optoelectronic motion for flexion–extension as low as 2°. For the glenohumeral joint, 3D joint motion has been described with RMS errors of 6° and higher. In contrast, scapulothoracic joint motion tracking yielded RMS errors in excess of 10° in the protraction–retraction and anterior-posterior tilt direction. The findings of this study demonstrate high-quality 3D humerothoracic and elbow joint motion measurement capability using IMUs and underscore the challenges of skin motion artifacts in scapulothoracic and glenohumeral motion analysis. Future studies ought to implement functional joint axis calibrations, and IMU-based scapular locators to address skin motion artifacts at the scapula, and explore the use of artificial neural networks and data-driven approaches to directly convert IMU data to joint angles.

show abstract

“…The TCN-BiLSTM deep neural network proposed in the present study does not require static calibration of the sensors, significantly improving its applicability in clinical settings and daily life scenarios. Some deep learning algorithms have been developed previously for human gait analysis [46,47]. At the same time, some studies have only carried out a single kinematic or kinetic analysis using the real IMU data.…”

Section: Discussionmentioning

confidence: 99%

Estimation of Lower Limb Joint Angles and Joint Moments during Different Locomotive Activities Using the Inertial Measurement Units and a Hybrid Deep Learning Model

Wang,

Liang,

Afzal

et al. 2023

Sensors

View full text Add to dashboard Cite

Using inertial measurement units (IMUs) to estimate lower limb joint kinematics and kinetics can provide valuable information for disease diagnosis and rehabilitation assessment. To estimate gait parameters using IMUs, model-based filtering approaches have been proposed, such as the Kalman filter and complementary filter. However, these methods require special calibration and alignment of IMUs. The development of deep learning algorithms has facilitated the application of IMUs in biomechanics as it does not require particular calibration and alignment procedures of IMUs in use. To estimate hip/knee/ankle joint angles and moments in the sagittal plane, a subject-independent temporal convolutional neural network-bidirectional long short-term memory network (TCN-BiLSTM) model was proposed using three IMUs. A public benchmark dataset containing the most representative locomotive activities in daily life was used to train and evaluate the TCN-BiLSTM model. The mean Pearson correlation coefficient of joint angles and moments estimated by the proposed model reached 0.92 and 0.87, respectively. This indicates that the TCN-BiLSTM model can effectively estimate joint angles and moments in multiple scenarios, demonstrating its potential for application in clinical and daily life scenarios.

show abstract

Real-time conversion of inertial measurement unit data to ankle joint angles using deep neural networks

Cited by 11 publications

References 13 publications

Real-time calibration-free musculotendon kinematics for neuromusculoskeletal models

Real-time calibration-free musculotendon kinematics for neuromusculoskeletal models

Conversion of Upper-Limb Inertial Measurement Unit Data to Joint Angles: A Systematic Review

Estimation of Lower Limb Joint Angles and Joint Moments during Different Locomotive Activities Using the Inertial Measurement Units and a Hybrid Deep Learning Model

Contact Info

Product

Resources

About