sEMG 신호를 이용한 Random Forest, SVM, XGBoost 기반 팔꿈치 각도 분류 성능 비교
Comparison of Elbow Angle Classification Performance Using sEMG-Based Random Forest, SVM, and XGBoost Models
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
This study aimed to develop a machine learning model for classifying elbow angles using sEMG signals. Previous research in rehabilitation and robotic arm control has often combined sEMG and IMU sensors to measure muscle activity and precise angles. However, in rehabilitation, utilizing sEMG signals alone may be more practical than using multiple sensors. The use of sensors like IMUs increases equipment costs and complicates data pro- cessing, making interpretation more challenging. In contrast, sEMG signals reflect muscle activation and can predict angles simply and effectively, making them suitable for assessing elbow movements. This study classified elbow flex- ion and extension angles into 15°, 30°, 45°, 60°, and 90° using only sEMG sensors. sEMG data were collected from the biceps brachii and triceps brachii muscles and analyzed using Random Forest, SVM, and XGBoost models to eval- uate angle classification performance. The experimental results showed high accuracy for all three models, with SVM and XGBoost demonstrating particularly superior performance. These findings suggest that sEMG signals alone can effectively predict elbow angles in applications such as rehabilitation and arm control, providing a valuable tool for assessing and aiding recovery of motor functions in rehabilitation therapy.
Abstract
This study aimed to develop a machine learning model for classifying elbow angles using sEMG signals. Previous research in rehabilitation and robotic arm control has often combined sEMG and IMU sensors to measure muscle activity and precise angles. However, in rehabilitation, utilizing sEMG signals alone may be more practical than using multiple sensors. The use of sensors like IMUs increases equipment costs and complicates data pro- cessing, making interpretation more challenging. In contrast, sEMG signals reflect muscle activation and can predict angles simply and effectively, making them suitable for assessing elbow movements. This study classified elbow flex- ion and extension angles into 15°, 30°, 45°, 60°, and 90° using only sEMG sensors. sEMG data were collected from the biceps brachii and triceps brachii muscles and analyzed using Random Forest, SVM, and XGBoost models to eval- uate angle classification performance. The experimental results showed high accuracy for all three models, with SVM and XGBoost demonstrating particularly superior performance. These findings suggest that sEMG signals alone can effectively predict elbow angles in applications such as rehabilitation and arm control, providing a valuable tool for assessing and aiding recovery of motor functions in rehabilitation therapy.
참고문헌 (20)
- Lockard, M., "Clinical biomechanics of the elbow", J Hand Ther, 19(2), pp.72~81 (2006)
- Ham SH, "Prediction system for diagnosis and treatment of elbow disorders using elbow angle", Master, pp.2020
- Kim BH, "Analysis of shoulder and elbow joint torques of a humanoid robot arm for lifting tasks", J Korean Inst Intell Syst, 25(3), pp.223~228 (2015)
- Kim HS, "Design and force control of an elbow rehabilitation robot based on force measurement", J Inst Control Robot Syst, 21(5), pp.413~420 (2015)
- Kim YK, "Analysis of EMG patterns and joint angle patterns in exoskeleton robot-assisted walking", Master, pp.2022
- Kim JJ, "Real-time monitoring system for upper limb rehabilitation exercise based on CNN-LSTM", J Korea Converg Signal Process, 24(3), pp.134~139 (2023)
- Kim JU, "Development of a knee exoskeleton for rehabilitation based on EMG and IMU sensor feedback", J Biomed Eng Res, 40(6), pp.223~229 (2019)
- Jang JS, "Robot arm control based on user motion recognition using ROS", J Korean Soc Manuf Process Eng, 22(10), pp.29~35 (2023)
- Breiman L, "Random forests", Mach Learn, 45, pp.5~32 (2001)
- Siroky DS, "Navigating random forests and related advances in algorithmic modeling", Statist Surv, 3, pp.147~163 (2009)
- Vapnik V, "Statistical learning theory" (1998), John Wiley & Sons
- Choi JS., "A comparative study on classification performance using SVM and RVM", Master, pp.2012
- Ha JE., "A performance comparison of automatic classification of complaint categories and responsible departments using RandomForest and XGBoost", Master, pp.2017
- Jeong YJ, "Asset price prediction and portfolio optimization using LSTM and XGBoost", Master, pp.2024
- Ghalyan MF, "Human gait cycle classification improvements using median and root mean square filters based on EMG signals", IOP Conf Ser Mater Sci Eng, 1067(1), pp.012146~ (2021)
- Kil TY, "Optimization of multi-class classification for red and white blood cells based on machine learning", Master, pp.2023
- Yoon DH, "Study on bridge safety diagnosis prediction algorithm using machine learning", Master, pp.2022
- Kang YJ, "Prediction model of transmission error in aircraft power transmission systems using machine learning ensemble", pp.2024
- Sommer LF, "Elbow joint angle estimation with surface electromyography using autoregressive models", Proceedings of the 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp.1472~1475 (2018)
- Pan SJ, "A survey on transfer learning", IEEE Trans Knowl Data Eng, 22(10), pp.1345~1359 (2009)