Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Jung Keun Lee has a total of 15 co-authors. Here are the top co-authors by number of shared publications:

  • Chang June Lee

    Department of Integrated Systems Engineering, Hankyong National University, Anseong, 17579, Republic of Korea

    13 shared publications
  • Chang June Lee

    Department of Integrated Systems Engineering, Hankyong National University, Anseong 17579, Republic of Korea

    10 shared publications
  • Ji Seok Choi

    School of ICT, Robotics and Mechanical Engineering, Hankyong National University, Anseong, South Korea

    5 shared publications
  • Ji Hoon Park

    School of ICT, Robotics and Mechanical Engineering, Hankyong National University, Anseong, Gyeonggi, South Korea

    4 shared publications
  • Mi Jin Choi

    Inertial Motion Capture Lab, Department of Mechanical Engineering, Hankyong National University, Anseong 17579, Korea

    4 shared publications
  • Woo Chang Jung

    Inertial Motion Capture Lab, School of ICT, Robotics & Mechanical Engineering, Hankyong National University, 327 Jungang-ro, Anseong 17579, Gyeonggi, Korea

    4 shared publications

Latest Publications

  • Open Access

    Long-duration Recovery of Missing Marker in Optical Motion Capture Using Rigid Body Constraints and IMU Signals

    by Han Sol Woo, Ji Hoon Park, Chang June Lee, Jung Keun Lee

    Optical motion capture (OMC) systems are widely used in rehabilitation, sports, and robotics to obtain accurate segment attitudes. However, OMC marker data can be lost due to occlusions, and reliably recovering data for long-duration missing intervals remains challenging. This study proposes a method for recovering missing markers using inertial measurement unit (IMU) signals and rigid-body constraints. We implemented two recovery methods and validated their performance. The proposed method (M1) combines inter-marker distance constraints with an acceleration constraint, while the comparison method (M2) combines inter-marker distance constraints with a tilt constraint. M1 demonstrated superior performance, with an average root mean squared error that was 3.10 and 3.99 mm lower than that of M2 for the 30 and 180 s missing intervals, respectively. This performance difference arises because M1 directly utilizes measured IMU signals, whereas M2 incurs additional uncertainty due to attitude estimation errors. Furthermore, the proposed method maintained reliable performance even during long-duration missing intervals, as it operates independently of past data, preventing recovery error accumulation. These results demonstrate the feasibility of the proposed IMU-based method for recovering longduration missing marker data in OMC systems.

  • Open Access

    A Multimodal Dataset of Full-Body Kinematics and Kinetics from Laboratory- and Wearable-Based Systems

    by Chang June Lee, Jung Keun Lee

    Kinematic and kinetic biomechanical measurements are critical for understanding human movements. Although laboratory-based systems such as optical motion capture (OMC) and instrumented treadmills provide gold-standard accuracy, their use is confined to controlled laboratory settings. Wearable systems, including inertial motion capture (IMC) and pressure-sensing insoles, enable measurements in real-world conditions but require validation against laboratory-based references. In this study, we present a comprehensive dataset that combines laboratory- and wearable-based systems to capture synchronized full-body kinematic and kinetic measurements. Twelve healthy young adults performed static postures, treadmill walking at multiple speeds and inclines, treadmill running, and functional movement tasks, including squats, weight shifts, and squat jumps. The dataset included raw signals from four measurement systems-OMC, IMC, instrumented treadmill, and insoles-as well as from biomechanical variables derived using a biomechanical model. Synchronized multimodal signals and processed biomechanical variables support diverse applications beyond level walking, including wearable sensor validation, machine learning model training, and gait or movement analysis.

  • Real-Time Recovery of Missing Markers in an Optical Tracking Cluster Using IMU Signals and Rigid-Body Kinematics

    by Ji Hoon Park, Chang June Lee, Jung Keun Lee

    Optical motion capture (OMC) systems that use optical tracking clusters are widely used in rehabilitation and related clinical applications because they can accurately compute segment orientation. OMC-derived orientation is widely used as a reference for validating inertial measurement unit (IMU)-based orientation estimation algorithms. However, missing markers owing to occlusion occur frequently, which makes the OMC-based computation of segment orientation infeasible. Therefore, reliable missing marker recovery is essential in practice. Existing methods rely either on post-processing approaches that cannot be applied in real time or on IMU-based orientation of which errors can affect recovery performance. This paper proposes a real-time method for the recovery of missing markers using IMU signals and rigid-body kinematics but without IMU-based orientation. We implemented three methods based on rigid-body kinematics to evaluate recovery performance, all of which utilize intermarker distance: Method 1 (M1) using accelerometer signals; Method 2 (M2) using gyroscope signals; and the proposed Method 3 (M3) using both accelerometer and gyroscope signals. In addition, a Kalman filter-based method using IMU-based orientation (Method 4, M4) was implemented for comparison. Recovery performance was evaluated based on the number of missing markers (1 or 2) and the duration of the missing interval (5 s or 30 min). In the comparison among methods based on rigid-body kinematics, M1 showed degraded performance when two markers were missing, whereas M2 exhibited drift errors during prolonged missing intervals (30 min). In contrast, the proposed method (M3) consistently achieved low root mean squared errors of 2.25–4.23 mm and 4.05–7.08 mm for one and two missing markers, respectively, during the 5 s interval, and 1.10–3.52 mm and 3.72–5.92 mm during the 30 min interval. In comparison with the method using IMU-based orientation, M3 outperformed M4 under disturbed conditions. In particular, because M3 uses only accelerometer and gyroscope signals without relying on a magnetometer, it is inherently free from error propagation from magnetic disturbances to orientation estimation and, consequently, to recovery performance. In contrast, M4 showed degraded recovery performance due to disturbance-induced orientation estimation errors. These experimental results indicate that the proposed method enables the real-time recovery of missing marker data with high accuracy, even in disturbed conditions and over long missing intervals.

  • Open Access

    Lower-limb Joint Torque Estimation During Gait Using a Recurrent Neural Network based on IMU-derived Segmental Kinematics

    by Chang June Lee, Jung Keun Lee

    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.

  • Open Access

    Effects of Gyroscope Bias Augmentation on Recurrent Neural Network Model Performance for Attitude Estimation

    by Ji Hoon Park, Chang June Lee, Jung Keun Lee

    The 6-axis inertial measurement unit-based attitude estimation is widely used in fields such as biomechanics and unmanned aerial vehicles. The 6-axis IMU signals, comprising 3-axis gyroscope and accelerometer data, provide crucial information for attitude estimation. However, measurement errors, particularly gyroscope bias, can reduce the estimation accuracy. Gyroscope bias augmentation can address this issue in end-to-end machine learning models; however, its effect on model performance has not been thoroughly investigated. This study investigated the effect of gyroscope bias augmentation range on the performance of an end-to-endmodel for attitude estimation, specifically focusing on varying biasmagnitudes. To this end, models were trained using data with different bias augmentation ranges. The performance of each model was then observed on signals with different bias magnitudes. The analysis revealed a generalization–precision trade-off relationship in the influence of bias augmentation range on the estimation performance. A narrower augmentation range exposed the model to smaller bias magnitudes during training, leading to superior performance within that range. However, the performance significantly degraded when encountering larger bias magnitudes that were not experienced during training. Conversely, models trained with a wider augmentation range were exposed to a broader spectrum of bias magnitudes, thereby enabling them to maintain relatively stable estimation performance even under larger biases. However, their performance deteriorated in the small bias range. These results indicate that, given known bias characteristics, selecting an appropriate bias augmentation range during training can help balance generalization and precision.

  • Open Access

    Analytical Formulation of Relationship Between Sensors and Euler Angle Errors for Arbitrary Stationary Alignment Based on Accelerometer and Magnetometer

    by Chang June Lee, Jung Keun Lee

    An attitude and heading reference system (AHRS) based on the inertial measurement unit is crucial for various applications. In an AHRS, stationary alignments are performed to determine the initial orientation of the sensor frame with respect to the navigation frame. However, the stationary alignment accuracy is affected by sensor error factors. Therefore, several studies have attempted to analyze and minimize the effects of these errors. However, there have been no studies describing and analyzing the Euler angle errors for various sensor orientations. This paper presents the analytical formulation of the relationship between the sensor and the Euler angle errors based on accelerometer and magnetometer signals, regardless of alignment between the sensor and the navigation frames. We selected three-axis attitude determination (TRIAD) as the stationary alignment method and considered the scale, installation, and the offset errors, including noise and constant bias, as sensor error factors. The presented formulation describes the relationship between the sensor error factors and the Euler angle errors as a linear equation. To analyze the Euler angle errors, we performed both sensor-aligned and sensor-misaligned simulations in which the Euler angles were 0° and arbitrary, respectively. The results showed that the presented error formulation could describe the total Euler angle errors and the partial errors induced by each sensor error factor for both the sensor-aligned conditions and the arbitrary Euler angle configurations. Thus, the effects of each sensor error factor on the Euler angle errors can be analytically investigated using the presented formulations for random alignment.