Daily planning conversations and AI: Keys for improving construction culture, engagement, planning, and safety.

The construction industry is known for its inherent risks, contributing to ~170,000 workplace injuries and illnesses annually in the United States. Engaging in prejob safety discussions presents a crucial chance to safeguard workers by proactively recognizing hazards and ensuring that crews are well-oriented with safety protocols before commencing work each day. However, research shows prejob meetings are often conducted hastily without the depth required to fully uncover risks. This study examines the characteristics that distinguish high-impact, high-quality prejob safety conversations from lower- quality counterparts. Strategies are provided for improving engagement, psychological safety, hazard analysis, accountability, and leadership support to transform safety talks into dynamic interactions that empower employees to operate safely. Additionally, this study reviews leading-edge artificial intelligence techniques, enabling construction firms to capture, analyze, and optimize their daily planning conversations at scale to drive safety excellence. Implementing the evidence-based strategies discussed allows organizations to realize the immense potential of prejob conversations for preventing injuries and fatalities.

Pre-task planning for construction worker safety and health: Implementation and assessment.

BACKGROUND: Compared to other industry sectors, construction workers experience a disproportionately high rate of occupational injuries and fatalities. As research findings suggest, most of these incidents could be prevented if hazards were proactively recognized and properly addressed. In the construction industry, pre-task planning (PTP) is a preventive process intended to describe each step of work, identify associated safety and health hazards, and recommend controls to eliminate or mitigate the hazards before work begins. Despite its importance, the construction industry lacks comprehensive guidelines to design and implement PTP in a consistent and effective manner. To fill this gap, this study pursued two objectives: (1) identify shortcomings in current PTP practices and explore recommended solutions from practitioners' perspectives and (2) translate research findings into an applied tool to help practitioners assess and improve the quality of their PTP process. METHODS: To fill the gap, 28 construction safety and health professionals and 104 workers were interviewed, and seven onsite PTP sessions were directly observed. RESULTS: Shortcomings of current PTP practices as well as recommended solutions were categorized as (1) planning and implementation, (2) all-trades coordination, (3) engagement and buy-in, (4) training and logistics, (5) workforce diversity and the language barrier, and (6) PTP content accessibility. DISCUSSION/CONCLUSIONS: An effective PTP process should be based on workers' direct involvement and input on task requirements and hazards. It needs to be regularly updated to reflect the changing work conditions. In addition to task-related information, to increase workers' awareness, PTP should paint a holistic view of the project and other trades' scopes.

Effects of an advanced first aid course or real-time video communication with ambulance personnel on layperson first response for building-site severe injury events: a simulation study.

BACKGROUND: The risk of high-energy trauma injuries on construction sites is relatively high. A delayed response time could affect outcomes after severe injury. This study assessed if an advanced first aid course for first aid response for laypersons (employees or apprentices) in the construction industry or real-time video communication and support with ambulance personnel, or neither, together with access to an advanced medical kit, would have an effect on immediate layperson vital responses in a severe injury scenario. METHOD: This was a controlled simulation study. Employees or apprentices at a construction site were recruited and randomly allocated into a group with video support or not, and advanced first aid course or not, and where one group had both. The primary outcomes were correct behavior to recognize and manage an occluded airway and correct behavior to stop life-threatening bleeding from a lower extremity injury. Secondary outcomes included head-to-toe assessment performed, placement of a pelvic sling, and application of remote vital signs monitors. RESULTS: Ninety participants were included in 10 groups of 3 for each of 4 exposures. One group was tested first as a baseline group, and then later after having done the training course. Live video support was effective in controlling bleeding. A first aid course given beforehand did not seem to be as effective on controlling bleeding. Video support and the first aid course previously given improved the ability of bystanders to manage the airway, the combination of the two being no better than each of the interventions taken in isolation. Course exposure and video support together were not superior to the course by itself or video by itself, except regarding placing the biosensors on the injured after video support. Secondary results showed an association between video support and completing a head-to-toe assessment. Both interventions were associated with applying a pelvic sling. CONCLUSION: These findings show that laypersons, here construction industry employees, can be supported to achieve good performance as first responders in a major injury scenario. Prior training, but especially live video support without prior training, improves layperson performance in this setting.

Exploring the effect of human-drone communication modality on safety and balance control in virtual construction environments.

This study examines the impact of Human-Drone Interaction (HDI) modalities on construction workers' safety and balance control within virtual environments. Utilising virtual reality (VR) simulations, the study explored how gesture and speech-based communications influence workers' physical postures and balance, contrasting these modalities with a non-interactive control group. One hundred participants were recruited, and their movements and balance control were tracked using motion sensors while they interacted with virtual drones through either gesture, speech, or without communication. Results showed that interactive modalities significantly improved balance control and reduced the risk of falls, suggesting that advanced HDI can enhance safety on construction sites. However, speech-based interaction increased cognitive workload, highlighting a trade-off between physical safety and mental strain. These findings underscore the potential of integrating intuitive communication methods into construction operations, although further research is needed to optimise these interactions for long-term use and in diverse noise environments.

This study examines the impact of Human-Drone Interaction (HDI) modalities on construction workers' safety and balance control within virtual environments with a human subject experiment. Results showed that interactive modalities significantly improved balance control and reduced the risk of falls.

Welding Spark Detection on Construction Sites Using Contour Detection with Automatic Parameter Tuning and Deep-Learning-Based Filters.

One of the primary causes of fires at construction sites is welding sparks. Fire detection systems utilizing computer vision technology offer a unique opportunity to monitor fires in construction sites. However, little effort has been made to date in regard to real-time tracking of small sparks that can lead to major fires at construction sites. In this study, a novel method is proposed to detect welding sparks in real-time contour detection with deep learning parameter tuning. An automatic parameter tuning algorithm employing a convolutional neural network was developed to identify the optimum hue saturation value. Additional filtering methods regarding the non-welding zone and a contour area-based filter were also newly developed to enhance the accuracy of welding spark prediction. The method was evaluated using 230 welding spark images and 104 videos. The results obtained from the welding images indicate that the suggested model for detecting welding sparks achieves a precision of 74.45% and a recall of 63.50% when noise images, such as flashing and reflection light, were removed from the dataset. Furthermore, our findings demonstrate that the proposed model is effective in capturing the number of welding sparks in the video dataset, with a 95.2% accuracy in detecting the moment when the number of welding sparks reaches its peak. These results highlight the potential of automated welding spark detection to enhance fire surveillance at construction sites.

Development of a Knowledge Graph for Automatic Job Hazard Analysis: The Schema.

In the current practice, an essential element of safety management systems, Job Hazard Analysis (JHA), is performed manually, relying on the safety personnel's experiential knowledge and observations. This research was conducted to create a new ontology that comprehensively represents the JHA knowledge domain, including the implicit knowledge. Specifically, 115 actual JHA documents and interviews with 18 JHA domain experts were analyzed and used as the source of knowledge for creating a new JHA knowledge base, namely the Job Hazard Analysis Knowledge Graph (JHAKG). To ensure the quality of the developed ontology, a systematic approach to ontology development called METHONTOLOGY was used in this process. The case study performed for validation purposes demonstrates that a JHAKG can operate as a knowledge base that answers queries regarding hazards, external factors, level of risks, and appropriate control measures to mitigate risks. As the JHAKG is a database of knowledge representing a large number of actual JHA cases previously developed and also implicit knowledge that has not been formalized in any explicit forms yet, the quality of JHA documents produced from queries to the database is expectedly higher than the ones produced by an individual safety manager in terms of completeness and comprehensiveness.

Enhancing Safety on Construction Sites: A UWB-Based Proximity Warning System Ensuring GDPR Compliance to Prevent Collision Hazards.

Construction is known as one of the most dangerous industries in terms of worker safety. Collisions due the excessive proximity of workers to moving construction vehicles are one of the leading causes of fatal and non-fatal accidents on construction sites internationally. Proximity warning systems (PWS) have been proposed in the literature as a solution to detect the risk for collision and to alert workers and equipment operators in time to prevent collisions. Although the role of sensing technologies for situational awareness has been recognised in previous studies, several factors still need to be considered. This paper describes the design of a prototype sensor-based PWS, aimed mainly at small and medium-sized construction companies, to collect real-time data directly from construction sites and to warn workers of a potential risk of collision accidents. It considers, in an integrated manner, factors such as cost of deployment, the actual nature of a construction site as an operating environment and data protection. A low-cost, ultra-wideband (UWB)-based proximity detection system has been developed that can operate with or without fixed anchors. In addition, the PWS is compliant with the General Data Protection Regulation (GDPR) of the European Union. A privacy-by-design approach has been adopted and privacy mechanisms have been used for data protection. Future work could evaluate the PWS in real operational conditions and incorporate additional factors for its further development, such as studies on the timely interpretation of data.

Augmented Hearing of Auditory Safety Cues for Construction Workers: A Systematic Literature Review.

Safety-critical sounds at job sites play an essential role in construction safety, but hearing capability is often declined due to the use of hearing protection and the complicated nature of construction noise. Thus, preserving or augmenting the auditory situational awareness of construction workers has become a critical need. To enable further advances in this area, it is necessary to synthesize the state-of-the-art auditory signal processing techniques and their implications for auditory situational awareness (ASA) and to identify future research needs. This paper presents a critical review of recent publications on acoustic signal processing techniques and suggests research gaps that merit further research for fully embracing construction workers' ASA of hazardous situations in construction. The results from the content analysis show that research on ASA in the context of construction safety is still in its early stage, with inadequate AI-based sound sensing methods available. Little research has been undertaken to augment individual construction workers in recognizing important signals that may be blocked or mixed with complex ambient noise. Further research on auditory situational awareness technology is needed to support detecting and separating important acoustic safety cues from complex ambient sounds. More work is also needed to incorporate context information into sound-based hazard detection and to investigate human factors affecting the collaboration between workers and AI assistants in sensing the safety cues of hazards.

Mobile Device-Based Struck-By Hazard Recognition in Construction Using a High-Frequency Sound.

The construction industry experiences the highest rate of casualties from safety-related accidents at construction sites despite continuous social interest in safety management. Accordingly, various studies have been conducted on safety management, wherein recent studies have focused on its integration with Machine Learning (ML). In this study, we proposed a technology for recognizing struck-by hazards between construction equipment and workers, where a Convolutional Neural Network (CNN) and sound recognition were combined to analyze the changes in the Doppler effect caused by the movements of a subject. An experiment was conducted to evaluate the recognition performance in indoor and outdoor environments with respect to movement state, direction, speed, and near-miss situations. The proposed technology was able to classify the movement direction and speed with 84.4-97.4% accuracy and near-misses with 78.9% accuracy. This technology can be implemented using data obtained through the microphone of a smartphone, thus it is highly applicable and is also effective at ensuring that a worker becomes aware of a struck-by hazard near construction equipment. The findings of this study are expected to be applicable for the prevention of struck-by accidents occurring in various forms at construction sites in the vicinity of construction equipment.

On-Body Placement of Wearable Safety Promotion Devices Based on Wireless Communication for Construction Workers-on-Foot: State-of-the-Art Review.

High auditory noise levels and limited visibility are often considered among the main factors that hinder seamless communication on construction sites. Many previous research studies have leveraged technology to overcome these obstacles and communicate using the hearing, sight and touch senses. However, the technological efficacy does not secure the users' perceptivity of the wireless communication devices. Statistical data regarding the number of fatal accidents on construction sites have remained steady despite regular efforts. This study analyzed prior research on wearable safety promotion devices for personnel that move around the jobsite on foot. A seven-point checklist was utilized to shortlist prior studies (2005-2021) attempting to provide safety information wirelessly to the construction workers-on-foot. The reasoning behind various on-body placements was investigated along with the information conveyed using the three communication modalities. A novel communication network is also introduced to visualize the technical details. Lastly, limitations and future recommendations have been presented to gain insights about the factors that might affect the placement of the wearable safety promotion devices.

Industrial construction safety policies and practices with cost impacts in a COVID-19 pandemic environment: A Louisiana DOW case study.

There are always significant challenges in improving the safety culture by changing and adding additional safety protocols. The unknown impacts of COVID-19 and how it quickly spreads led the industry to institute essential safety protocols. This paper addresses two problem statements. The first problem statement is: what are the additional safety protocols for process safety, construction & maintenance, and personal protective equipment requirements? The second problem statement is: what are the cost and schedule impacts of industrial construction projects resulting from implementing safety protocols and process safety during construction with the added PPE? While complying with added safety protocols, the industrial construction industry cannot forget that it has a distinct reputation for high incident rates and less than desirable safety performance. In 2017, the construction industry suffered 971 fatalities. This alarming number is compared to 1123 total fatalities in 2017 for the Gulf Coast States. The objective is to share the rationale and practices of social distancing, required additional PPE, and personal hygiene practices to reduce spreading and outbreaks during a pandemic within an industrial construction environment. Before any construction work, the process safety teams must clear, isolate, and tag out process lines, equipment, and instruments to be repaired or replaced. The information presented demonstrates the significant cost and schedule impacts that industrial construction companies will encounter during a pandemic like COVID-19. This paper aims to improve safety processes, cost & schedule impacts, and prescribe additional personal protective equipment in industrial construction during a pandemic such as COVID-19. The COVID-19 pandemic spread globally in a very short period. The reactions in mitigating the spread were suggestive, with little to no data on safety protective equipment and practices. The contribution this paper addresses are how to employ efficient safety practices and policies during a pandemic in an industrial construction environment.

Wearable Inertial Measurement Unit Sensing System for Musculoskeletal Disorders Prevention in Construction.

Construction workers executing manual-intensive tasks are susceptible to musculoskeletal disorders (MSDs) due to overexposure to awkward postures. Automated posture recognition and assessment based on wearable sensor output can help reduce MSDs risks through early risk-factor detection. However, extant studies mainly focus on optimizing recognition models. There is a lack of studies exploring the design of a wearable sensing system that assesses the MSDs risks based on detected postures and then provides feedback for injury prevention. This study aims at investigating the design of an effective wearable MSDs prevention system. This study first proposes the design of a wearable inertial measurement unit (IMU) sensing system, then develops the prototype for end-user evaluation. Construction workers and managers evaluated a proposed system by interacting with wearable sensors and user interfaces (UIs), followed by an evaluation survey. The results suggest that wearable sensing is a promising approach for collecting motion data with low discomfort; posture-based MSDs risk assessment has a high potential in improving workers' safety awareness; and mobile- and cloud-based UIs can deliver the risk assessment information to end-users with ease. This research contributes to the design, development, and validation of wearable sensing-based injury prevention systems, which may be adapted to other labor-intensive occupations.

Fast Personal Protective Equipment Detection for Real Construction Sites Using Deep Learning Approaches.

The existing deep learning-based Personal Protective Equipment (PPE) detectors can only detect limited types of PPE and their performance needs to be improved, particularly for their deployment on real construction sites. This paper introduces an approach to train and evaluate eight deep learning detectors, for real application purposes, based on You Only Look Once (YOLO) architectures for six classes, including helmets with four colours, person, and vest. Meanwhile, a dedicated high-quality dataset, CHV, consisting of 1330 images, is constructed by considering real construction site background, different gestures, varied angles and distances, and multi PPE classes. The comparison result among the eight models shows that YOLO v5x has the best mAP (86.55%), and YOLO v5s has the fastest speed (52 FPS) on GPU. The detection accuracy of helmet classes on blurred faces decreases by 7%, while there is no effect on other person and vest classes. And the proposed detectors trained on the CHV dataset have a superior performance compared to other deep learning approaches on the same datasets. The novel multiclass CHV dataset is open for public use.

The Influence of Hard Hat Design Features on Head Acceleration Attenuation.

This study evaluated the performance of 6 commercially available hard hat designs-differentiated by shell design, number of suspension points, and suspension tightening system-in regard to their ability to attenuate accelerations during vertical impacts to the head. Tests were conducted with impactor materials of steel, wood, and lead shot (resembling commonly seen materials in a construction site), weighing 1.8 and 3.6 kg and dropped from 1.83 m onto a Hybrid III head/neck assembly. All hard hats appreciably reduced head acceleration to the unprotected condition. However, neither the addition of extra suspension points nor variations in suspension tightening mechanism appreciably influenced performance. Therefore, these results indicate that additional features available in current hard hat designs do not improve protective capacity as related to head acceleration metrics.

Associations between a safety prequalification survey and worker safety experiences on commercial construction sites.

BACKGROUND: While assessment of subcontractors' safety performance during project bidding processes are common in commercial construction, the validation of organizational surveys used in these processes is largely absent. METHODS: As part of a larger research project called Assessment of Contractor Safety (ACES), we designed and tested through a cross-sectional study, a 63-item organizational survey assessing subcontractors' leading indicators of safety performance. We administered the ACES Survey to 43 subcontractors on 24 construction sites. Concurrently, we captured the safety climate of 1426 workers on these sites through worker surveys, as well as injury rates, for the duration of the project. RESULTS: At the worksite level, higher average ACES scores were associated with higher worker safety climate scores (P < .01) and lower rates of injury involving days away (P < .001). Within subcontracting companies, no associations were observed between ACES and worker safety climate scores and injuries. CONCLUSIONS: These results suggest the overall and collective importance of the construction project and its worksite in mediating worker experiences, perhaps somewhat independent of the individual subcontractor level.

Incorporating Worker Awareness in the Generation of Hazard Proximity Warnings.

Proximity warning systems for construction sites do not consider whether workers are already aware of the hazard prior to issuing warnings. This can generate redundant and distracting alarms that interfere with worker ability to adopt timely and appropriate avoidance measures; and cause alarm fatigue, which instigates workers to habitually disable the system or ignore the alarms; thereby increasing the risk of injury. Thus, this paper integrates the field-of-view of workers as a proxy for hazard awareness to develop an improved hazard proximity warning system for construction sites. The research first developed a rule-based model for the warning generation, which was followed by a virtual experiment to evaluate the integration of worker field-of-view in alarm generation. Based on these findings, an improved hazard proximity warning system incorporating worker field-of-view was developed for field applications that utilizes wearable inertial measurement units and localization sensors. The system's effectiveness is illustrated through several case studies. This research provides a fresh perspective to the growing adoption of wearable sensors by incorporating the awareness of workers into the generation of hazard alarms. The proposed system is anticipated to reduce unnecessary and distracting alarms which can potentially lead to superior safety performance in construction.

Effects of working posture and roof slope on activation of lower limb muscles during shingle installation.

Awkward and extreme kneeling during roofing generates high muscular tension which can lead to knee musculoskeletal disorders (MSDs) among roofers. However, the combined impact of roof slope and kneeling posture on the activation of the knee postural muscles and their association to potential knee MSD risks among roofers have not been studied. The current study evaluated the effects of kneeling posture and roof slope on the activation of major knee postural muscles during shingle installation via a laboratory assessment. Maximum normalized electromyography (EMG) data were collected from knee flexor and extensor muscles of seven subjects, who mimicked the shingle installation process on a slope-configurable wooden platform. The results revealed a significant increase in knee muscle activation during simulated shingle installation on sloped rooftops. Given the fact that increased muscle activation of knee postural muscles has been associated with knee MSDs, roof slope and awkward kneeling posture can be considered as potential knee MSD risk factors. Practitioner Summary: This study demonstrated significant effects of roof slope and kneeling posture on the peak activation of knee postural muscles. The findings of this study suggested that residential roofers could be exposed to a greater risk of developing knee MSDs with the increase of roof slope during shingle installation due to increased muscle loading. Abbreviations: MSDs: musculoskeletal disorders; EMG: electromyography; ANOVA: analysis of variance; MNMA: maximum normalized muscle activation; RF: rectus femoris; VL: vastus lateralis; VM: vastus medialis; BF: biceps femoris; S: semitendinosus.

Effects of working posture, lifting load, and standing surface on postural instability during simulated lifting tasks in construction.

Postural instability is a major contributor to fatal and nonfatal falls in the construction industry. This study investigated the effects of working posture, lifting load and standing surface on perceived postural instability. Thirty young males performed simulated lifting tasks in construction using six different postures under four experimental conditions (2 loads × 2 surfaces). Results showed working postures with bending at the waist and overhead carrying were associated with high postural instability. With lifting load and inclined standing surface both significantly increased postural instability for all working postures except the full squatting. Full squatting with lifting load was more stable than without load for the flat surface, but opposite for the inclined surface. These findings indicate three investigated factors had not only significant main effects, but also complicated interaction effects on postural instability, implying that all three factors should be considered simultaneously for the real practice on fall prevention in construction. Practitioner summary: The leading causes of worker deaths in the construction industry were falls. This study showed that working postures with waist bending and overhead carrying were associated with high postural instability. With lifting load and inclined standing surface both significantly increased postural instability for all working postures except the full squatting.

Robust Construction Safety System (RCSS) for Collision Accidents Prevention on Construction Sites.

A proximity warning system to detect the presence of a worker/workers and to warn heavy equipment operators is highly needed to prevent collision accidents at construction sites. In this paper, we developed a robust construction safety system (RCSS), which can activate warning devices and automatically halt heavy equipment, simultaneously, to prevent possible collision accidents. The proximity detection of this proposed system mainly relies on ultra-wideband (UWB) sensing technologies, which enable instantaneous and simultaneous alarms on (a) a worker's personal safety (personal protection unit (PPU)) device and (b) hazard area device (zone alert unit (ZAU)). This system also communicates with electronic control sensors (ECSs) installed on the heavy equipment to stop its maneuvering. Moreover, the RCSS has been interfaced with a global positioning system communication unit (GCU) to acquire real-time information of construction site resources and warning events. This enables effective management of construction site resources using an online user interface. The performance and effectiveness of the RCSS have been validated at laboratory scale as well as at real field (construction site and steel factory). Conclusively, the RCSS can significantly enhance construction site safety by pro-actively preventing collision of a worker/workers with heavy equipment.

Safety Distance Identification for Crane Drivers Based on Mask R-CNN.

Tower cranes are the most commonly used large-scale equipment on construction site. Because workers can't always pay attention to the environment at the top of the head, it is often difficult to avoid accidents when heavy objects fall. Therefore, safety construction accidents such as struck-by often occurs. In order to address crane issue, this research recorded video data by a tower crane camera, labeled the pictures, and operated image recognition with the MASK R-CNN method. Furthermore, The RGB color extraction was performed on the identified mask layer to obtain the pixel coordinates of workers and dangerous zone. At last, we used the pixel and actual distance conversion method to measure the safety distance. The contribution of this research to safety problem area is twofold: On one hand, without affecting the normal behavior of workers, an automatic collection, analysis, and early-warning system was established. On the other hand, the proposed automatic inspection system can help improve the safety operation of tower crane drivers.