Construction sites need to be monitored continuously to detect unsafe conditions and protect workers from potential injuries and fatal accidents. In current practices, construction-safety monitoring relies heavily on manual observation, which is labor-intensive and error-prone. Due to the complex environment of construction sites, it is extremely challenging for safety inspectors to continuously monitor and manually identify all incidents that may expose workers to safety risks. There exist many research efforts applying sensing technologies to construction sites to reduce the manual efforts associated with construction-safety monitoring. However, several bottlenecks are identified in applying these technologies to the onsite safety monitoring process, including (1) recognition and registration of potential hazards, (2) real-time detection of unsafe incidents, and (3) reporting and sharing of the detected incidents with relevant participants in a timely manner. The objective of this study was to create and evaluate a low-cost automated safety monitoring system to assist in the construction-safety monitoring process. This paper presents a framework for this safety monitoring system as a cloud-based real time on-site application. The system integrates Bluetooth low-energy (BLE)-based location detection technology, building information model (BIM)-based hazard identification, and a cloud-based communication platform. Potential unsafe areas are defined automatically or manually in a BIM model. Real-time worker locations are acquired to detect incidents where workers are exposed to predefined risks. Then, the safety monitoring results are instantly communicated over the cloud for effective safety management. Through a real-world construction site case study, the system successfully demonstrated the capability to detect unsafe conditions and collect and analyze the trajectories of workers with respect to potential safety hazards. The results indicate that the proposed approach can assist in the construction site monitoring process and potentially improve site safety.

The dynamic nature and limited work space of roadway work zones contribute to dangerous working environments for construction workers. This environment can result in hazardous proximity situations because pedestrian workers are required to operate in close proximity to heavy construction equipment. A total of 609 work zone personnel fatalities were reported in 2012. Previous analysis of work zone fatality data found that the majority of the pedestrian worker and mobile object struck-by fatalities resulted when pedestrian workers were struck by construction equipment. These statistics indicate that current safety practices for pedestrian workers and equipment operators are inadequate. The objective of this study was to create and evaluate a proximity detection and alert system using Bluetooth sensing technology. The scope included hazardous proximity situations between pedestrian workers and construction equipment in roadway work zones at grade. Evaluation metrics were implemented to assess the tested proximity sensing systems including the cost, time and ease of calibration, required hardware, system capabilities, and many others. Commercially available radio frequency identification (RFID) and magnetic field proximity sensing systems were also evaluated to provide a basis for comparison. Various interaction scenarios between pedestrian workers and construction equipment were used in the evaluation of the system. The performance evaluation based on the statistical results showed that all the tested systems were considered reliable with minimal false alarm rates. However, the magnetic system showed a significant drop in its coverage range, while still providing reliable coverage measures, with a set of tests that were more dynamic than other sets of tests. The created Bluetooth system provided the highest level of simplicity with its minimized infrastructure, ease of calibration, and ease of installation. In sum, experimental results demonstrate that the created proximity detection and alert system (1) requires minimal infrastructure; (2) provides adequate alerts to equipment operators and pedestrian workers; and (3) provides, through an alert, an additional layer of hazard avoidance in real time during hazardous-proximity situations in roadway work zones.

Wearable sensing devices (WSDs) are increasingly helping workers stay safe and healthy in several industries. However, workers, especially in the construction industry, have shown some aversion towards the use of WSDs due to their ability to capture specific information that may be considered personal and private. However, this revered information may provide some critical insight needed by management to plan and optimize worksite safety and support technology adoption in decision making. Therefore, there is a need to develop personalized WSD systems that are mutually beneficial to workers and management to ensure successful WSD integration. The present study aims to contribute to knowledge and practice by filling this critical gap using insight from 330 construction workers with experience using WSDs. The results from this study indicate that all 11 WSD functions identified through this study play a vital role in improving worker safety and health and that approximately two out of three workers are open to sharing the physiological and environmental information captured using these WSDs with their management. However, functions for detecting workers’ proximity to workplace hazards, specifically energized electrical materials, toxic gas, and fire/smoke, were the most critical functions that had mutual value to workers and management. Finally, the present study proposed and evaluated a phased personalized WSD system that should encourage successful WSD integration.

Despite regular safety inspections and safety planning, numerous fatal accidents related to scaffold take place at construction sites. Current practices relying on human inspection are not only impractical but also ineffective due to dynamic construction activities. Furthermore, a scaffold typically consists of multiple bays and stories, which leads to complexity in its structural behaviors with various modes of failure. However, previous studies considered only a limited number of failure cases for a simple one-bay scaffold while exploring machine-learning (ML) approaches to predict safety conditions. Thus, the authors have proposed an approach to monitor a complicated scaffolding structure in real time. This study explored a method of classifying scaffolding failure cases and reliably predicting safety conditions based on strain data sets from scaffolding columns. Furthermore, the research team successfully enhanced the predicting accuracy of ML classification by the proposed self-multiplication method to increase the number of features such as strain data sets. Implementation of the proposed methodology is expected to enable the monitoring of a large, complex system at construction sites.