Fall-from-Height Detection Using Deep Learning Based on IMU Sensor Data for Accident Prevention at Construction Sites

Abstract

Workers at construction sites are prone to fall-from-height (FFH) accidents. The severity of injury can be represented by the acceleration peak value. In the study, a risk prediction against FFH was made using IMU sensor data for accident prevention at construction sites. Fifteen general working movements (NF: non-fall), five low-hazard-fall movements, (LF), and five high-hazard-FFH movements (HF) were performed by twenty male subjects and a dummy. An IMU sensor was attached to the T7 position of the subject to measure the three-axis acceleration and angular velocity. The peak acceleration value, calculated from the IMU data, was 4 g or less in general work movements and 9 g or more in FFHs. Regression analysis was performed by applying various deep learning models, including 1D-CNN, 2D-CNN, LSTM, and Conv-LSTM, to the risk prediction, and then comparing them in terms of their mean absolute error (MAE) and mean squared error (MSE). The FFH risk level was estimated based on the predicted peak acceleration. The Conv-LSTM model trained by MAE showed the smallest error (MAE: 1.36 g), and the classification with the predicted peak acceleration showed the best accuracy (97.6%). This study successfully predicted the FFH risk levels and could be helpful to reduce fatal injuries at construction sites.

Near-Miss Detection Metrics: An Approach to Enable Sensing Technologies for Proactive Construction Safety Management

“…According to the WHO, near-misses are defined as a severe mistake with the potential to inflict harm but not due to luck or interception [31]. The OSHA defines a near-miss as an incident which could have led to severe injury or sickness but did not [32]. Another study defines a near-miss as "an unintended incident which, under different circumstances, could have become an accident" [33].…”

Computerized Predictive Analysis of Accidents (FOCOS/PRONTOS System): Study of Rare Cases

“…In this sense, the Computerized Work Readiness Assessment (FOCOS/Prontos System) identifies unsafe behaviors, emotional states, decreases in attention, impairments in concentration, sleep or fatigue issues, and other factors that can lead to accidents. Despite these available technologies, there are still reports of undesirable health and work-related events such as head injuries, eye injuries [2], sprains, strains, stretching injuries, extremity and soft tissue skin injuries [3,4], deaths and injuries from fires and explosions [5] falls from heights and heavy vehicle accidents, which can be fatal [6,7].…”