Applying Incremental Deep Neural Networks-based Posture Recognition Model for Injury Risk Assessment in Construction

TL;DR

This paper develops an incremental deep learning model for posture recognition in construction, enabling adaptive injury risk assessment with high accuracy and minimal forgetting, advancing automated MSDs monitoring.

Contribution

It introduces a novel incremental CLN model with effective IL strategies for posture recognition and MSDs assessment in construction environments.

Findings

High recognition performance with F1 scores of 0.87 (personalized) and 0.84 (generalized)

Balanced adaptation and forgetting achieved with Many-to-One IL scheme

MSDs assessment results closely match ground-truth data

Abstract

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.