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

• Published in: Journal of biomechanics Vol. 125; p. 110552
• Main Authors: Senanayake, Damith, Halgamuge, Saman, Ackland, David C.
• Format: Journal Article
• Language: English
• Published: Kidlington Elsevier Ltd 26.08.2021; Elsevier Limited
• Subjects: Ankle; Artificial neural networks; Biomechanical model; Conversion; deep learning; Gait; generative adversarial network; Generative adversarial networks; human movement; IMU; Inertial platforms; Inverse kinematics; Kinematics; Laboratories; machine learning; motion analysis; Motion capture; Neural networks; Real time; Rehabilitation; Remote monitoring; Rotation; Telemedicine; Three dimensional motion; Treadmills; Variance analysis; Walking; Wearables; United Kingdom > UK; IMU; generative adversarial network; deep learning; Biomechanical model; human movement; Wearables; kinematics; machine learning; motion analysis
• ISSN: 0021-9290; 1873-2380; 1873-2380
• DOI: 10.1016/j.jbiomech.2021.110552

Joint angle quantification from inertial measurement units (IMUs) is commonly performed using kinematic modelling, which depends on anatomical sensor placement and/or functional joint calibration; however, accurate three-dimensional joint motion measurement remains challenging to achieve. The aims of this study were firstly to employ deep neural networks to convert IMU data to ankle joint angles that are indistinguishable from those derived from motion capture-based inverse kinematics (IK) - the reference standard; and secondly, to validate the robustness of this approach across contrasting walking speeds in healthy individuals. Kinematics data were simultaneously calculated using IMUs and IK from 9 subjects during walking on a treadmill at 0.5 m/s, 1.0 m/s and 1.5 m/s. A generative adversarial network was trained using gait data at two of the walking speeds to predict ankle kinematics from IMU data alone for the third walking speed. There were significant differences between IK and IMU joint angle predictions for ankle eversion and internal rotation during walking at 0.5 m/s and 1.0 m/s (p < 0.001); however, no significant differences in joint angles were observed between the generative adversarial network prediction and IK at any speed or plane of joint motion (p < 0.05). The RMS difference in ankle joint kinematics between the generative adversarial network and IK for walking at 1.0 m/s was 3.8°, 2.1° and 3.5° for dorsiflexion, inversion and axial rotation, respectively. The modeling approach presented for real-time IMU to ankle joint angle conversion, which can be readily expanded to other joints, may provide enhanced IMU capability in applications such as telemedicine, remote monitoring and rehabilitation.