3D ground reaction force (GRF) estimation during walking is important for gait and inverse dynamics analyses. Recent studies have estimated 3D GRF based on kinematics measured from optical or inertial motion capture systems without force plate measurement. A neural network (NN) could be used to estimate ground reaction forces. The NN network approach based on segment kinematics requires the selection of optimal inputs, including kinematics type and segments. This study aimed to select optimal input kinematics for implementing an NN for each foot’s GRF estimation. A two-stage NN consisting of a temporal convolution network for gait phase detection and a gated recurrent unit network was developed for GRF estimation. To implement the NN, we conducted level/inclined walking and level running on a force-sensing treadmill, collecting datasets from seven male participants across eight experimental conditions. Results of the input selection process indicated that the center of mass acceleration among six kinematics types and trunk, pelvis, thighs, and shanks among 15 individual segments showed the highest correlations with GRFs. Among four segment combinations, the combination of trunk, thighs, and shanks demonstrated the best performance (root mean squared errors: 0.28, 0.16, and 1.15 N/kg for anterior-posterior, medial-lateral, and vertical components, respectively).
Estimating energy expenditure is essential in monitoring the intensity of physical activity and health status. Energy expenditure can be estimated based on wearable sensors such as inertial measurement unit (IMU). While a variety of methods have been developed to estimate energy expenditure during day-to-day activities, their performances have not been thoroughly evaluated under walking conditions according to various speeds and inclines. This study investigated IMU-based neural network models for energy expenditure estimation under various walking conditions and comparatively analyzed their performances in terms of sensor attachment locations and training/testing datasets. In this study, two neural network models were selected based on a previous study (Slade et al., 2019): (M1) a multilayer perceptron using sensor signals during each gait cycle, and (M2) a recurrent neural network using sensor signal sequences of a fixed window size. The results revealed the following: (i) the performance of the foot attachment model was the best among the five sensor attachment locations (0.89 W/kg for M1 and 1.14 W/kg for M2); and (ii) although the performance of M1 was superior to that of M2, M1 requires accurate gait detection for data segmentation by each stride, which hinders the usefulness of M2.
Citations
Citations to this article as recorded by
Development of a Novel Ventilation Estimation Model Based on Convolutional Neural Network (CNN) Jeongyeon Chu, Jaehyon Baik, Kangsu Jeong, Seungwon Jung, Youngjin Park, Hosu Lee Journal of Korea Robotics Society.2025; 20(1): 138. CrossRef
Recently, the estimation of joint kinetics such as joint force and moment using wearable inertial sensors has received great attention in biomechanics. Generally, the joint force and moment are calculated though inverse dynamics using segment kinematic data, ground reaction force, and moment. However, this approach has problems such as estimation error of kinematic data and soft tissue artifacts, which can lead to inaccuracy of joint forces and moments in inverse dynamics. This study aimed to apply a recurrent neural network (RNN) instead of inverse dynamics to joint force and moment estimation. The proposed RNN could receive signals from inertial sensors and force plate as input vector and output lower extremity joints forces and moments. As the proposed method does not depend on inverse dynamics, it is independent of the inaccuracy problem of the conventional method. Experimental results showed that the estimation performance of hip joint moment of the proposed RNN was improved by 66.4% compared to that of the inverse dynamics-based method.
Inertial measurement unit (IMU)-based 3D joint angle estimation have a wide range of important applications, among them, in gait analysis and exoskeleton robot control. Conventionally, the joint angle was determined via the estimation of 3D orientation of each body segment using 9-axis IMUs including 3-axis magnetometers. However, a magnetometer is limited by magnetic disturbance in the vicinity of the sensor, which highly affects the accuracy of the joint angle. Accordingly, this study aims to estimate the joint angle using the 6-axis IMU signals composed of a 3-axis accelerometer and a 3-axis gyroscope without a magnetometer. This paper proposes a recurrent neural network (RNN) model, which indirectly utilizes the joint kinematic constraint and thus estimates joint angles based on 6-axis IMUs without using a magnetometer signal. The performance of the proposed model was validated for a mechanical joint and human elbow joint, under magnetically disturbed environments. Experimental results showed that the proposed RNN approach outperformed the conventional approach based on a Kalman filter (KF), i.e., RNN 3.48° vs. KF 10.01° for the mechanical joint and RNN 7.39° vs. KF 21.27° for the elbow joint.
One of the problems in inverse dynamics calculation for the inertial measurement unit (IMU)-based joint force and torque estimation is the amplified signal noises of segment kinematic data mainly due to the differentiation procedure and segmental soft tissue artifacts. In order to deal with this problem, appropriate filtering methods are often recommended for signal enhancement. Conventionally, a low-pass filter (LPF) is widely used for the kinematic data. However, the zero-phase LPF requires post-processing, while the real-time LPF causes an unignorable time lag. For this reason, it is inappropriate to use the LPF for real-time joint torque estimation. This paper proposes a Kalman filter (KF) for inverse dynamics of IMUbased joint torque estimation in real time without any time lag, while utilizing the smoothing capability of the KF. Experimental results showed that the proposed KF outperformed a real-time LPF in the estimation accuracy of hip joint force and torque during jogging on the spot by 100 and 29%, respectively. Although the proposed KF requires the process of adjusting covariance according to the dynamic conditions, it can be expected to improve the estimation performance in the field where joint force and torque need to be estimated in real time.
Citations
Citations to this article as recorded by
Wearable Inertial Sensors-based Joint Kinetics Estimation of Lower Extremity Using a Recurrent Neural Network Ji Seok Choi, Chang June Lee, Jung Keun Lee Journal of the Korean Society for Precision Engineering.2023; 40(8): 655. CrossRef
Estimation of the relative position between the body segments is an important task in inertial sensor-based human motion tracking. Conventionally, the relative position is determined using orientations and constant segment vectors that connect from segment to joint center, based on the assumption that the segments are rigid. However, the human body segments are non-rigid, which leads to an inaccurate relative position estimation. This paper proposes a relative position estimation method based on inertial sensor signals, considering the non-rigidity of the human bodies. Considering that the effects of non-rigidity are highly correlated with a specific variable, the proposed method uses time-varying segment vectors determined by the specific physical variable, instead of using constant segment vectors. Verification test results for an upper-body model demonstrates the superiority of the proposed method over the conventional method: The averaged root mean square error of the sternum-to-forearm estimation from the conventional method was 34.19 ㎜, while the value from the proposed method was 16.67 ㎜.
Citations
Citations to this article as recorded by
Wearable Inertial Sensors-based Joint Kinetics Estimation of Lower Extremity Using a Recurrent Neural Network Ji Seok Choi, Chang June Lee, Jung Keun Lee Journal of the Korean Society for Precision Engineering.2023; 40(8): 655. CrossRef
Ergonomic guidelines for the design interfaces of additive modules for manual wheelchairs: sagittal plane Bartosz Wieczorek, Mateusz Kukla, Łukasz Warguła, Marcin Giedrowicz Scientific Reports.2023;[Epub] CrossRef
Effects of the Selection of Deformation-related Variables on Accuracy in Relative Position Estimation via Time-varying Segment-to-Joint Vectors Chang June Lee, Jung Keun Lee JOURNAL OF SENSOR SCIENCE AND TECHNOLOGY.2022; 31(3): 156. CrossRef
Application of Artificial Neural Network for Compensation of Soft Tissue Artifacts in Inertial Sensor-Based Relative Position Estimation Ji Seok Choi, Jung Keun Lee Journal of the Korean Society for Precision Engineering.2022; 39(3): 233. CrossRef
In the case of dynamic sports activities such as skiing and sprints, it is difficult to apply optical motion capture systems because of measurement volume limitation. Alternatively, the use of inertial measurement unit (IMU) as a motion sensor has gained attention. This paper proposes a drift reduction method in the IMU-based joint angle estimation for dynamic motion-involved sports applications. To resolve the problem of conventional IMU-based methods significantly reducing performance under highly dynamic conditions, the proposed method applies a correction method using joint constraint. The proposed method is the complementary filter based on the previous drift reduction technique using the joint constraint, but performs in real time. The proposed method was validated by comparing the estimation accuracy with conventional methods under various dynamic conditions. The results showed that the proposed method was superior to the methods that did not use the constraint. While the proposed method was 0.19° less accurate than the non-realtime method of the reference, it is more practical due to its realtime correction capability.
Citations
Citations to this article as recorded by
Wearable Inertial Sensors-based Joint Kinetics Estimation of Lower Extremity Using a Recurrent Neural Network Ji Seok Choi, Chang June Lee, Jung Keun Lee Journal of the Korean Society for Precision Engineering.2023; 40(8): 655. CrossRef
A Recurrent Neural Network for 3D Joint Angle Estimation based on Six-axis IMUs but without a Magnetometer Chang June Lee, Woo Jae Kim, Jung Keun Lee Journal of the Korean Society for Precision Engineering.2023; 40(4): 301. CrossRef
Motion capture and evaluation system of football special teaching in colleges and universities based on deep learning Xiaohui Yin, C. Chandru Vignesh, Thanjai Vadivel International Journal of System Assurance Engineering and Management.2022; 13(6): 3092. CrossRef
First
Prev
