A Big-Data-based platform of workers' behavior: Observations from the field. (August 2016)

• Record Type: Journal Article
• Authors: Guo, S.Y.; Ding, L.Y.; Luo, H.B.; Jiang, X.Y.
• Is Part Of: Accident analysis and prevention. Volume 93(2016)
• Page Start: 299
• Page End: 309
• Publication Date: 2016-08
• Subjects: Big Data -- Behavior-Based Safety -- Behavior observation -- Intelligent video surveillance -- Mobile application -- HDFS; Accidents -- Prevention -- Periodicals; Accident Prevention -- Periodicals; Accidents -- Prévention -- Périodiques; 363.106
• DOI: 10.1016/j.aap.2015.09.024
• Languages: English
• ISSNs: 0001-4575

Abstract

Highlights: A Big-Data-based platform for behavior observation is developed. A behavioral risk knowledge base is established with a list of critical unsafe behaviors and Work Breakdown Structure. Intelligent video surveillance and a mobile application are used to collect data from a metro construction site. Hadoop Distributed File System guarantees the effective data storage. Abstract: Behavior-Based Safety (BBS) has been used in construction to observe, analyze and modify workers' behavior. However, studies have identified that BBS has several limitations, which have hindered its effective implementation. To mitigate the negative impact of BBS, this paper uses a case study approach to develop a Big-Data-based platform to classify, collect and store data about workers' unsafe behavior that is derived from a metro construction project. In developing the platform, three processes were undertaken: (1) a behavioral risk knowledge base was established; (2) images reflecting workers' unsafe behavior were collected from intelligent video surveillance and mobile application; and (3) images with semantic information were stored via a Hadoop Distributed File System (HDFS). The platform was implemented during the construction of the metro-system and it is demonstrated that it can effectively analyze semantic information contained in images, automatically extract workers' unsafe behavior and quickly retrieve on HDFS as well. The research presented in this paper can enable construction organizations with the ability to visualize unsafe acts in real-time and further identify patterns of behavior that can jeopardize safety outcomes.