Estimating lower-limb joint torques during gait using inertial measurement units (IMUs) has attracted growing attention in biomechanics and wearable sensing. Conventional approaches rely on inverse dynamics based on segmental kinematics and ground reaction forces, requiring force sensors or full-body sensor setups. This study proposes a recurrent neural network (RNN) method to estimate lower-limb joint torques using segmental kinematic data from a limited number of IMUs.Twelve healthy participants performed treadmill walking and running under twelve different conditions to generate training data. Model inputs included center-of-mass accelerations and angular velocities of the pelvis and shank.Results demonstrated two key findings. First, a model using three IMUs achieved performance comparable to a seven-IMU model, with hip flexion torque errors of approximately 0.18 Nm/kg, demonstrating strong effectiveness with a reduced sensor configuration. Second, while inverse dynamics exhibited an error increase of 0.28 Nm/kg from the ankle to the hip, the proposed model showed only a 0.01 Nm/kg increase and achieved approximately 0.13 Nm/kg lower error at the hip.These results indicate that accurate and efficient joint torque estimation is feasible using an RNN with fewer wearable sensors.

This study assessed the accuracy and reliability of a 2D image-based deep learning algorithm for posture analysis by comparing it with a 3D motion capture system. Twenty healthy adult males participated, and nine balance parameters were measured using both methods: body tilt (ML/AP), shoulder tilt, pelvis tilt (ML/AP), knee tilt, left/right varus/valgus, and forward head posture. We evaluated agreement and reliability using root mean square error (RMSE), mean absolute error (MAE), Pearson correlation coefficients, and intraclass correlation coefficients (ICC). Most parameters exhibited RMSE and MAE within 3°, while forward head posture, pelvis tilt (AP), and varus/valgus had errors below 10°. High correlations were found for shoulder tilt (r = 0.886) and forward head posture (r = 0.681), whereas knee tilt and left varus/valgus showed lower correlations due to methodological differences. Both methods demonstrated high repeatability (3D: ICC > 0.90, 2D: ICC > 0.80), with moderate-to-high agreement between methods (ICC ≥ 0.5 for most parameters). Shoulder tilt (ICC = 0.919) and forward head posture (ICC = 0.799) showed particularly high agreement. These findings indicate that 2D image-based posture analysis can provide accurate and reliable assessments comparable to 3D motion capture, presenting a more accessible and cost-effective alternative for posture evaluation in clinical and research contexts.

As the population ages, the concept of active seniors has been emerging recently. Among various body parts that are cared for by an active elderly, the shoulder has a unique exercise structure. Therefore, the incidence of shoulder injuries might be high. In the case of a shoulder disease, the method of measuring the movement angle of the shoulder is mainly used. To measure the movement angle of a shoulder accurately, a goniometer is used. In addition, we suggested self-diagnosis, believing that if shoulder disease could be detected early through self-diagnosis, rapid treatment will be possible. This paper measured and compared shoulder angles with the goniometer, OpenCV, and motion capture systems to determine measurement errors between them. Through experimental results of this paper, the possibility of self-diagnosis with precise measurement of the movement angle of a shoulder oneself with a goniometer was confirmed even if the expert could not measure the shoulder angle.

This paper proposes a walking position tracking method using inertial measurement unit (IMU) based on kinematic model of human body and walking cycle analysis. A kinematic model of lower body consisting of 9 coordinate frames and 7 links is used to estimate walking trajectory of the body based on rotation angles of the lower body measured by IMU. In this method, the position of left or right end frame of the lower body which is in contact with the ground is first identified and set as the reference position. The position of the base frame attached on the center of pelvis is then computed using the kinematic model and the reference position. One can switch the reference position with the position of the other end frame at the moment of heel strike. The proposed position tracking method was experimentally validated. Experimental result showed that position tracking errors were within 1.4% of walking distance for straight walking and 2.2% for circular walking.