Applying Incremental Deep Neural Networks-based Posture Recognition Model for Injury Risk Assessment in Construction
This work addresses injury risk monitoring for construction workers, but it is incremental as it builds on existing posture recognition methods by adding incremental learning capabilities.
The study tackled the problem of automated injury risk assessment in construction by developing an incremental deep learning model for posture recognition, achieving high F1 scores (0.87 personalized, 0.84 generalized) and demonstrating minor differences in MSDs assessment compared to ground-truth.
Monitoring awkward postures is a proactive prevention for Musculoskeletal Disorders (MSDs)in construction. Machine Learning (ML) models have shown promising results for posture recognition from Wearable Sensors. However, further investigations are needed concerning: i) Incremental Learning (IL), where trained models adapt to learn new postures and control the forgetting of learned postures; ii) MSDs assessment with recognized postures. This study proposed an incremental Convolutional Long Short-Term Memory (CLN) model, investigated effective IL strategies, and evaluated MSDs assessment using recognized postures. Tests with nine workers showed the CLN model with shallow convolutional layers achieved high recognition performance (F1 Score) under personalized (0.87) and generalized (0.84) modeling. Generalized shallow CLN model under Many-to-One IL scheme can balance the adaptation (0.73) and forgetting of learnt subjects (0.74). MSDs assessment using postures recognized from incremental CLN model had minor difference with ground-truth, which demonstrates the high potential for automated MSDs monitoring in construction.