Automating the Estimation of Productivity Metrics for Construction Workers Using Deep Learning and Kinematics

Abstract

In this study, a novel method for direct work estimation is used to classify whether a painteris performingdirect workor not.The aim is to build an accurate and reliable work classification algorithmthatcanhelp monitorconstruction sites.The method utilizes adeep learning algorithmusing convolutional and long short-term memory layersto classify multivariate time-series data collected from five inertial measurement units (IMUs)mounted on the workers’arms, torso,and legs.Three models are developed, differing in window sizes from 3 seconds to 7 seconds.Thebest performingmodel achieves an accuracy of 90%and anF1-score of 87.6%. This is thefirst step towards a general model that canclassify productivity measures for workers on construction sites, which will be a valuableinput formonitoringconstruction sitesandfuture analyses.

Review of Emerging Technologies for Reducing Ergonomic Hazards in Construction Workplaces

“…Unlike the network map of wearable sensors, these two categories' coauthorship network maps show sparse clusters. The largest coauthorship cluster in XR consists of a group of researchers from Aarhus University, Denmark [77,78]. However, the coauthorship network map for exoskeletons and robotics shows similar cluster sizes, with researchers from the Georgia Institute of Technology [15,79] contributing the highest number of publications (N = 4).…”