Background: Real-time ergonomic risk assessment in manufacturing environments is challenged by severe class imbalance in high-risk postures and the need for deployment-efficient models. Conventional oversampling techniques may violate biomechanical constraints, limiting their suitability for human motion data. Objectives: This study aimed to compare multiple machine learning models for real-time ergonomic risk assessment while addressing data imbalance using biomechanically appropriate learning strategies and evaluating both predictive performance and deployment efficiency. Design: Comparative study. Methods: A large-scale workplace safety dataset comprising image-based skeletal keypoints was analyzed. To mitigate class imbalance without generating biomechanically implausible samples, cost-sensitive learning and focal loss were employed instead of synthetic oversampling. Subject-wise data splitting was applied to prevent data leakage. Five model families, including Random Forest, convolutional neural networks, and a lightweight graphbased network, were evaluated using accuracy, F1-score, area under the receiver operating characteristic curve (AUC), and high-risk recall. Statistical significance was assessed using bootstrap confidence intervals and McNemar and DeLong tests. Results: The lightweight graph-based model demonstrated competitive classification performance while maintaining reduced computational complexity. Although none of the models achieved the predefined high-risk recall threshold, statistically significant performance differences were observed across model families. Conclusion: The findings suggest that biomechanically informed imbalance handling improves methodological validity in ergonomic risk assessment. While deployment feasibility appears promising, further empirical validation on edge hardware is required.

INTRODUCTION
SUBJECTS AND METHODS
    Subjects (Dataset)
    Study Design and Procedures
    Subject-Wise Data Splitting
    Outcome Measures
    Safety Performance Thresholds
    Data Processing
    Model Architectures
    Model Training
    Statistical Analysis
RESULTS
    Model Performance Comparison
    Computational Resource Requirements
DISCUSSION
    Methodological Considerations: Addressing ClassImbalance
    Temporal Limitations and Implications for ExposureAssessment
    Edge Device Deployment: Theoretical vs. EmpiricalValidation
CONCLUSION
FUNDING
CONFLICTS OF INTEREST
AUTHOR CONTRIBUTIONS
REFERENCES

• Jingrui Wu(College of Medical Technology, Xi'an Medical College, Xi'an, Shaanxi, China)
• Jeongjae An(Department of Physical Therapy, Kyungwoon University, Gumi, Republic of Korea)
• Jageung Paeng(Department of Physical Therapy, Kyungwoon University, Gumi, Republic of Korea)
• Gagi Yu(Department of Physical Therapy, Kyungwoon University, Gumi, Republic of Korea)
• Haolin Su(Department of Physical Therapy, Kyungwoon University, Gumi, Republic of Korea)
• Haichao Du(Department of Physical Therapy, Kyungwoon University, Gumi, Republic of Korea)
• Ning Huo(Department of Physical Therapy, Kyungwoon University, Gumi, Republic of Korea)
• Geon Shin(Department of Physical Therapy, Kyungwoon University, Gumi, Republic of Korea)
• Wansuk Choi(Department of Physical Therapy, Kyungwoon University, Gumi, Republic of Korea) Corresponding author
• Yuemei Jin(Department of Practical Theology, Mokwon University, Daejeon, Republic of Korea)