A GRU-Based Model for Detecting Common Accidents of Construction Workers.

Fall accidents in the construction industry have been studied over several decades and identified as a common hazard and the leading cause of fatalities. Inertial sensors have recently been used to detect accidents of workers in construction sites, such as falls or trips. IMU-based systems for detecting fall-related accidents have been developed and have yielded satisfactory accuracy in laboratory settings. Nevertheless, the existing systems fail to uphold consistent accuracy and produce a significant number of false alarms when deployed in real-world settings, primarily due to the intricate nature of the working environments and the behaviors of the workers. In this research, the authors redesign the aforementioned laboratory experiment to target situations that are prone to false alarms based on the feedback obtained from workers in real construction sites. In addition, a new algorithm based on recurrent neural networks was developed to reduce the frequencies of various types of false alarms. The proposed model outperforms the existing benchmark model (i.e., hierarchical threshold model) with higher sensitivities and fewer false alarms in detecting stumble (100% sensitivity vs. 40%) and fall (95% sensitivity vs. 65%) events. However, the model did not outperform the hierarchical model in detecting coma events in terms of sensitivity (70% vs. 100%), but it did generate fewer false alarms (5 false alarms vs. 13).

Quantitative evaluation of the impact of night shifts and alcohol consumption on construction tiling quality.

The adverse effects of night-shift work and alcohol consumption on performance have received considerable attention. However, how night shifts and alcohol affect productivity in workers has not been quantified. This paper describes the experiments featuring multiple tiling tasks and patterns. The tiling quality performed by the graduate student participants in four different statuses was objectively evaluated by an edge-detection computer program. The results indicate that both night shift and alcohol significantly reduce the quality in general, and the effects of the factors on position and alignment-angle qualities were dissimilar in distinct areas due to tile patterns and size. Both night-shift and alcohol conditions affected the basic (-34.01% and -25.79%) and advanced tiling abilities (-40.14% and -26.16%), and night shift had a larger impact than alcohol. These results provide jobsite managers with usable information regarding how night shifts and alcohol affect workers' abilities to execute basic and advanced tasks.