Biomechanical Ambulatory Assessment of 3D Knee Angle Using Novel Inertial Sensor-Based Technique

Abstract

Three-dimensional (3D) knee angle measurement is one of the key measures in human gait analysis. Inertial sensor capable of measuring joint motion under unconstrained conditions is a practical tool for clinical evaluation and rehabilitation. An inertial measurement unit (IMU) consisting of accelerometer and gyroscope allows orientation measurement in 3D with an additional sensor (i.e., magnetometer). However, ferromagnetic interference negatively affects the performance of magnetometer and thus reduces measurement accuracy. In this study, a technique based on nonlinear autoregressive neural network with exogenous inputs (NARX) is presented to measure 3D segmental orientation during gait without the use of magnetometer. With IMUs attached to the thigh and shank, 3D knee angles in long-distance treadmill walking were computed and validated against an optical motion analysis system as the gold standard. Pseudo-integrator (PI) was also compared to the reference system for benchmarking. The learning capability of NARX was further assessed with the comparison of complementary filter (CF) to the reference system. The proposed NARX model was shown to outperform PI with biases between-3.5°and-0.2°, and root mean square errors between 4.5°and 2.5°. Results demonstrated the capability of NARX in providing accurate estimates of 3D knee joint angle while avoiding interference as encountered in systems incorporating magnetometer, suggesting that NARX is feasible to computing long-term ambulatory measurements of body segment orientation and 3D joint angles. INDEX TERMS 3D knee angle, gait analysis, NARX network, pseudo-integration, segmental orientation.

Visual Gait Analysis Based on UE4

“…Sensors 2023, 23, 5463 2 of 12 joint angles using inertial sensors, NARX can avoid the influence of magnetometers, accurately estimate 3D knee joint angles and measure 3D joint angles in the long term [17]. In the same year, a full-body wireless wearable motion-sensing system was reported by Lee et al to study the motion of human lower limbs and arms, which can reconstruct simple 3D human body models in real-time using quaternion data measured by sensors [18].…”

“…Figueiredo et al proposed a wearable inertial sensor system for real-time detection of 3D angular velocity and 3D acceleration for up to six lower limbs and trunk segments, and sagittal joint angle for up to six lower limb joints [ 16 ], but they do not have a 3D model which was used to show the human gait. Tham et al demonstrated that when measuring joint angles using inertial sensors, NARX can avoid the influence of magnetometers, accurately estimate 3D knee joint angles and measure 3D joint angles in the long term [ 17 ]. In the same year, a full-body wireless wearable motion-sensing system was reported by Lee et al to study the motion of human lower limbs and arms, which can reconstruct simple 3D human body models in real-time using quaternion data measured by sensors [ 18 ].…”

Simultaneous exercise recognition and evaluation in prescribed routines: Approach to virtual coaches

“…Other RNNs are also used to estimate the joints orientation. To estimate the joint angles from gyroscopes and accelerometers, [54] proposes a NARX; and [134] also includes the magnetometer data with NARX and LSTMs.…”

“…the joint or segment orientation or location. In this review, we found 26 works that use reference data, that can be obtained from a stereophotogrammetric system (17/26) [21], [27], [34], [49], [53], [54], [56], [58], [68], [69], [86], [90], [91], [103], [111], [114], [115], electro-goniometer and encoders (2/26) [71], [84] or inertial sensors (7/26) [29], [100], [109], [134], [147], [148], [155]. Fig.…”

Moving on: measuring movement remotely after stroke

“…The estimated variables can be used to extract gait parameters of interest. For instance, IMU data has been used to estimate gait events (Pacini Panebianco et al, 2018), walking speed (Sabatini et al, 2005), joint angles (Muro-de-la-Herran et al, 2014;Tham et al, 2021), foot pose and trajectory (Okkalidis et al, 2020a) etc. We also employ this 'physical model' approach in Chapters VI -X for estimating ground reaction forces, Centre of Mass (CoM) velocity, and relative movement of feet and CoM.…”