Studying Accuracy of Machine Learning Models Trained on Lab Lifting Data in Solving Real-World Problems Using Wearable Sensors for Workplace Safety
This addresses the challenge of applying lab-trained models to real-world workplace safety, but it appears incremental as it focuses on improving an existing approach without introducing a new paradigm.
The paper tackled the problem of porting a machine learning model trained on lab data for lifting identification to real-world scenarios using wearable sensors, finding that performance was much lower than on training data, and they explored causes and proposed four potential solutions to increase model performance.
Porting ML models trained on lab data to real-world situations has long been a challenge. This paper discusses porting a lab-trained lifting identification model to the real-world. With performance much lower than on training data, we explored causes of the failure and proposed four potential solutions to increase model performance