Semi-supervised near-miss fall detection for ironworkers with a wearable inertial measurement unit

Abstract

Accidental falls (slips, trips, and falls from height) are the leading cause of occupational death and injury in construction. As a proactive accident-prevention measure, near-miss can provide valuable data about the causes of accidents, but collecting near miss information is challenging because current data collection systems can largely be affected by retrospective and qualitative decisions of individual workers. In this context, this study aims to develop a method that can automatically detect and document near-miss falls based upon a worker's kinematic data captured from wearable inertial measurement units (WIMUs). A semi-supervised learning algorithm (i.e., One-Class Support Vector Machine) was implemented for detecting the near-miss falls in this study. Two experiments were conducted for collecting the near-miss falls of ironworkers and these data were used to test developed near-miss fall detection approach. This WIMU-based approach will help identify ironworker near-miss falls without disrupting jobsite work and can help prevent fall accidents.

The Role of Safety-specific Transformational Leadership in Reducing Near Miss Incidents, Using Safety Climate as a Mediator

“…Safety climate as a mediator between safety-specific transformational and near misses. As compared to occupational accidents and injuries, gathering data on near misses is far more difficult and complex (Yang, Ahn, Vuran, & Aria, 2015) although assessing near misses' situation can be equally or more important than accidents or injuries. Near miss incidents provide insight into the causes of accidents or injuries and help in evading future safety mishaps (Cambraia, Saurin, & Formoso, 2010).…”

“…In various industries information on near misses is used to correct flaws in the system to prevent future accident and injuries (Wright & Van Der Schaaf, 2004). Thus it is imperative to evaluate near miss incidents, as the overall situation of workplace safety cannot be explained without assessing them (Yang et al, 2015). The empirical work using safety climate as a mediator between safety-specific transformational leadership and near misses is limited.…”

“…The frequency of near miss incidents shows organizational seriousness about workplace safety (Phimister et al, 2003). If the frequency is higher it highlights that these incidents are not taken seriously thus showing an intended negligence towards safety lapses which can cause serious accidents and injuries in the future (Yang et al, 2015). As the near miss incidents given an opportunity to the organization to plug the gaps, improve working condition, and put more emphasis on safety so that their workers are clear that safety is not to be compromised at any cost.…”

Safety Helmet Wearing Management System for Construction Workers Using Three-Axis Accelerometer Sensor

“…In previous studies in which three-axis accelerometer sensors were used to recognize activities, the sensors were attached to smartphones, wearable devices, body parts, etc. and the data were analyzed [27][28][29][30][31][32].…”

Review of fall detection techniques: A data availability perspective

“…Yang et al [53] present a semi-supervised approach to detect near-miss falls for ironworkers. They emphasize that collecting and labelling data for near-miss falls is very difficult and use abnormal signals as stand-ins for near misses.…”