INTEGRATION OF BIOPHYSICS AND INFORMATION TECHNOLOGIES FOR MODELING HUMAN BIOMECHANICAL MOVEMENTS USING 3D SENSORS AND MACHINE LEARNING

• Nodira Fayzieva

  Toshkent davlat tibbiyot universiteti

  Author

• Rashidov Abrorxo’ja

  Toshkent davlat tibbiyot universiteti

  Author

Human biomechanical movement analysis plays a crucial role in biophysics, rehabilitation medicine, sports science, and intelligent human–machine interaction systems. This study focuses on the integration of biophysics and information technologies for modeling human biomechanical movements, particularly gait and upper limb motions, using 3D sensor technologies and machine learning methods. Motion data were acquired using inertial measurement units (IMUs), optical motion capture systems, and depth sensors to record spatial–temporal kinematic parameters. Biophysical signal processing techniques, including noise filtering, drift compensation, and quaternion-based orientation reconstruction, were applied to ensure accurate motion representation. Extracted kinematic features such as joint angles, velocity, and acceleration were utilized to train machine learning models, including Random Forest, Long Short-Term Memory (LSTM) networks, and Transformer-based architectures. The results demonstrate that deep learning models effectively capture temporal dependencies in biomechanical signals, achieving high accuracy in movement classification and trajectory prediction. The proposed biophysics–IT integrated approach provides a robust framework for objective movement assessment and has significant potential applications in clinical rehabilitation, sports performance analysis, robotics, and intelligent biomedical systems.

• pdf

This work is licensed under a Creative Commons Attribution 4.0 International License.