New technologies are transforming how buildings are being constructed. Building Information Modeling, intelligent hardware and sensing technologies are changing the ways of construction and building industries used to be.
Construction companies suffer huge losses due to labor fatalities and injuries. The traditional approaches are time-consuming, inefficient, inaccurate and heavily relies on human observation. 3D vision systems (Kinect) and inertia measurement unit (IMU) have been employed to identify motion related hazards to improve construction safety condition. At the same time, wearable neural monitoring systems, electroencephalogram (EEG), have a great potential in creating new possibilities in traditional construction industry.
Jiayu Chen*, Jun Qiu and Changbum Ahn, 2016, “Automated Construction Awkward Posture Recognition Through Supervised Motion Tensor Decomposition”, Automation in Construction, 2016, (Under Review)
Di Wang, Fei Dai, Dong Zhao, Xiaobing Wu and Jiayu Chen*, 2016, “Monitoring Workers’ Attention and Vigilance in Construction Activities through a Wireless and Wearable Electroencephalography System”, Automation in Construction, (Under Review)
Jiayu Chen* , John E. Taylor and Semra Comu, 2016, “Assessing Task Mental Workload in Construction Projects: A Novel Electroencephalography Approach”, (Under Review)
Jiayu Chen*, Xinyi Song and Zhenghang Lin, “Revealing the ‘Invisible Gorilla’ in Construction: Estimating Construction Safety through Mental Workload Assessment“, Automation in Construction ,2016, 63: 163-173.
Developing Brain-Computer Interfacing Theory and Models for Construction Hazard Detection through EEG Bispectrum Analysis
PI, #51508487, The National Natural Science Foundation of China (NSFC), Jan 2016- Dec 2017, RMB 230,000
Construction companies can accrue losses due to labor fatalities and injuries. Since more than 70% of all accidents are related to human activities, detecting and mitigating human-related risks hold the key to improving the safety conditions within the construction industry. Previous studies have revealed that the psychological and emotional conditions of workers can contribute to fatalities and injuries. The research in the area of neural science and psychology suggest that inattentional blindness is one major cause of unexpected human related accidents. Due to the limitation of human mental workload, laborers are vulnerable to unexpected hazards while focusing on complicated construction tasks. The ability to detect the mental conditions of workers could reduce unexpected injuries. This project aims to develop a measurement approach to evaluate hazards through neural time–frequency analysis. This project developed a prototype for a wearable electroencephalography (EEG) safety helmet that enables the collection of the neural information required as input for the measurement approach.
Mitigating Human-related Hazards in Construction Projects: An Agile Framework for Jobsite Safety Assessment through Integrating Multiple Data Sources
PI, #9048083, Hong Kong General Research Fund (GRF) – Early Career Scheme, 2016- 2019, HKD 456,050
Construction companies incur financial losses and negative impacts to reputation due to labor fatalities and injuries. Since more than 70% of all accidents are related to human activities, detecting and mitigating risks associated with human behavior can improve the negative public perception of the construction industry. Because construction environments are dynamic and human behavior is unpredictable, conventional observational approaches to detecting these risks have proven to be time-consuming and unreliable. Sensing technologies such as RGB-D cameras, IMUs and RFIDs have been introduced to automatically detect human motion in relation to its surrounding environment. However, these technologies currently lack a universal data integration and processing framework, which is problematic because it results in noisy, incomplete, and incompatible data. This proposed research aims to develop an agile framework to: 1) accurately collect multiple human behavior-related sensing data, 2) efficiently detect anomalies and hazards, and 3) correctly assess jobsite safety conditions. The goal of the research is to design a generic and self-adaptive framework that can integrate new and cumulative data sources. Specifically, the framework will: 1) define an agile protocol to collect, clean, unify and merge data from multiple sensing sources, 2) propose procedures and models to automatically recognize dangerous activities through temporal data segments processed according to the protocol, and 3) assess safety conditions on specific projects and compare them to benchmarks.