Journal of Civil Engineering and Management

Machine learning of electroencephalography signals and eye movements to classify work-in-progress risk at construction sites

Jui-Sheng Chou, Pin-Chao Liao, Chi-Yun Liu, Chia-Yung Hou — Wed, 12 Mar 2025 00:00:00 +0200

The construction industry has consistently faced high accident rates and delays in recognizing hazards, posing significant risks to onsite personnel. Traditional hazard detection methods are often reactive rather than proactive, emphasizing a pressing need for innovative solutions. Despite advances in safety technology, a considerable gap remains in real-time, accurate hazard recognition at construction sites. Current technologies do not fully leverage physiological data to predict and mitigate risks. This research introduces a groundbreaking approach by employing machine learning to analyze electroencephalography (EEG) signals and eye movement data, enabling real-time differentiation of safe, warning, and hazardous visual cues. A Random Forest model with an impressive classification accuracy of 99.04% has been developed, marking a significant enhancement in identifying potential hazards. The possible impact of integrating EEG and eye movement analyses into wearable devices or onsite sensors is substantial, as it could revolutionize safety protocols in the construction industry, fostering a safer future.

First published online 31 December 2024

A framework for effective construction workers safety training using flipped learning

Wed, 12 Mar 2025 14:43:23 +0200

Effective safety training plays an important part in safety management on construction sites. Construction workers safety and safety training education remain to be the main issues in the construction industry, as current practices rely on traditional methods. These methods often lack classroom interaction, hindering active worker engagement and fail to accommodate diverse learning paces and styles. To enhance safety awareness among workers, there is a need for a more effective system for safety training programs within the construction industry. Therefore, this study aims to comprehensively analyse an experimental intervention using flipped learning to reduce costs and enhance learning outcomes in construction safety training. Flipped learning transforms traditional classroom learning by introducing students to web-based videos, presentations, and readings before class, freeing up in-class time for discussions and problem-solving. An intervention study was carried out to confirm the effectiveness of flipped learning approach within the construction industry. In this study, 40 personnel from a leading construction firm in Pakistan underwent safety training, with 20 following the traditional method and the remaining 20 following the proposed flipped model. The final quiz revealed a score increase from 27.9 to 31.5 in flipped learning, indicating a 12.90% increase. Based on these findings, it is suggested that adopting the flipped learning approach leads to better learning outcomes within the construction industry, as workers can pause, rewind, and replay the lectures at their leisure. This not only makes safety training more accessible but also enhances on-site safety in a cost-effective manner.

Evaluating the e-permit system in construction using stakeholder analysis and network theory

Layal Amer, Mujahed Thneibat, Farouq Sammour, Natalija Lepkova — Mon, 17 Mar 2025 00:00:00 +0200

Electronic building permit systems, integral to e-government services, aim to enhance the efficiency and user experience of the permit process. Despite their widespread adoption, these systems often fall short, complicating and delaying the process. The presence of a variety of stakeholders in such permit systems complicates interactions between actors; nevertheless, no research has examined permit systems from a stakeholder analysis approach. This gap is filled by a formal social network analysis that thoroughly investigates interconnected and multi-level governing systems. This study investigates the electronic building permit system’s successes and failures in the construction industry. A mixed-methods approach was used, including interviews with applicants and employees, process mining analysis of event logs from 50 projects, case study observation, and social network analysis. The findings highlight significant barriers: poor communication and coordination among different agency employees, and a lack of adherence to established timeframes. Additionally, the study reveals that these systems are largely automated versions of their traditional counterparts, lacking substantial redesign or restructuring. Consequently, the researchers recommend a thorough re-evaluation and redesign of the electronic building permit system and propose implementing a one-stop-shop platform to facilitate inter-agency collaboration and streamline both internal and external communications and coordination.