Enhancing construction safety: predicting worker sleep deprivation using machine learning algorithms.

Sleep deprivation is a critical issue that affects workers in numerous industries, including construction. It adversely affects workers and can lead to significant concerns regarding their health, safety, and overall job performance. Several studies have investigated the effects of sleep deprivation on safety and productivity. Although the impact of sleep deprivation on safety and productivity through cognitive impairment has been investigated, research on the association of sleep deprivation and contributing factors that lead to workplace hazards and injuries remains limited. To fill this gap in the literature, this study utilized machine learning algorithms to predict hazardous situations. Furthermore, this study demonstrates the applicability of machine learning algorithms, including support vector machine and random forest, by predicting sleep deprivation in construction workers based on responses from 240 construction workers, identifying seven primary indices as predictive factors. The findings indicate that the support vector machine algorithm produced superior sleep deprivation prediction outcomes during the validation process. The study findings offer significant benefits to stakeholders in the construction industry, particularly project and safety managers. By enabling the implementation of targeted interventions, these insights can help reduce accidents and improve workplace safety through the timely and accurate prediction of sleep deprivation.

Early Impacts of the COVID-19 Pandemic on the United States Construction Industry.

The COVID-19 pandemic has been the largest global health crisis in decades. Apart from the unprecedented number of deaths and hospitalizations, the pandemic has resulted in economic slowdowns, widespread business disruptions, and significant hardships. This study focused on investigating the early impacts of the COVID-19 pandemic on the U.S. construction industry since the declaration of the national emergency on 13 March 2020. The study objectives were achieved through 34 telephone interviews with project managers, engineers, designers, and superintendents that represented different states and distinct industry sectors in the United States (U.S.). The interviewees offered information on their experience with the pandemic, including the general and adverse effects experienced, new opportunities created, and risk management efforts being undertaken. The reported adverse effects included significant delays on projects, inability to secure materials on time, reduction in productivity rates, material price escalations, and others. The new opportunities that were created included projects involving the fast-track construction of medical facilities, construction of residential buildings, transportation-related work, and opportunities to recruit skilled workers. The risk management measures that were widely adopted included measures to enhance safety and reduce other project risks. The safety measures adopted included requiring employees to wear cloth face masks, adoption of social distancing protocols, staggering of construction operations, offering COVID-19-related training, administering temperature checks prior to entry into the workplace, and others. Measures to manage other project risks included the formation of a task force team to review the evolving pandemic and offer recommendations, advocating that construction businesses be deemed essential to combat delays and taking advantage of government relief programs. The study findings will be useful to industry stakeholders interested in understanding the early impacts of the pandemic on the construction industry. Industry stakeholders may also build upon the reported findings and establish best practices for continued safe and productive operations.

Hazard Recognition Patterns Demonstrated by Construction Workers.

Construction workers fail to recognize a large number of safety hazards. These unrecognized safety hazards can lead to unintended hazard exposure and tragic safety incidents. Unfortunately, traditional hazard recognition interventions (e.g., job hazard analyses and safety training) have been unable to tackle the industry-wide problem of poor hazard recognition levels. In fact, emerging evidence has demonstrated that traditional hazard recognition interventions have been designed without a proper understanding of the challenges workers experience during hazard recognition efforts. Interventions and industry-wide efforts designed based on a more thorough understanding of these challenges can yield substantial benefits-including superior hazard recognition levels and lower injury rates. Towards achieving this goal, the current investigation focused on identifying hazard categories that workers are more proficient in recognizing and others that they are less proficient in recognizing (i.e., hazard recognition patterns). For the purpose of the current study, hazards were classified on the basis of the energy source per Haddon's energy release theory (e.g., gravity, motion, electrical, chemical, etc.). As part of the study, 287 workers representing 57 construction workplaces in the United States were engaged in a hazard recognition activity. Apart from confirming previous research findings that workers fail to recognize a disproportionate number of safety hazards, the results demonstrate that the workers are more proficient in recognizing certain hazard types. More specifically, the workers on average recognized roughly 47% of the safety hazards in the gravity, electrical, motion, and temperature hazard categories while only recognizing less than 10% of the hazards in the pressure, chemical, and radiation hazard categories. These findings can inform the development of more robust interventions and industry-wide initiatives to tackle the issue of poor hazard recognition levels in the construction industry.