Discovery of new safety knowledge from mining large injury dataset in construction. (December 2021)

• Record Type: Journal Article
• Authors: Xu, Xiaoxiao; Zou, Patrick X.W.
• Is Part Of: Safety science. Volume 144(2021)
• Publication Date: 2021-12
• Subjects: Construction safety -- Injury -- Incident -- Knowledge discovery -- Visualisation -- Association rule mining; Industrial accidents -- Periodicals; Accident Prevention -- Periodicals; Safety -- Periodicals; Travail -- Accidents -- Périodiques; 363.11
• DOI: 10.1016/j.ssci.2021.105481
• Languages: English
• ISSNs: 0925-7535

Abstract

Highlights: Hand, foot, eye and face are the most injury-prone body parts. A negative correlation between age and probability of injury for the age of over 30. Main causes of injury are being hit by objects, weight bearing and hitting objects. Safety capacity, protection and emergency response are considered in strategies. Abstract: Safety in construction continues to remain as the 3rd most serious occupational problem worldwide. Previous research mainly used questionnaire surveys or interviews to obtain "cross-sectional" data, which may be difficult to extract patterns and gain new knowledge for improving safety performance. This research aims to discover the characteristics, patterns, mechanisms and knowledge from mining a large injury dataset, and to develop strategies for mitigating safety risks, and reducing accidents and injuries so that to improve construction safety performance. A large set of injury and incident data recorded by construction companies over a period of 11 years was used in this research. Statistical analysis, visualisation analysis and association rule mining (ARM) methods were applied to mine and analyse this large dataset. "Injury time", "injured body locations, organs and systems", "age distribution of injured", "causes, nature and relationships of injury, and injured body parts" "changing trends of incidents", were analysed in depth to discover new safety knowledge. Based on the knowledge and mechanism discovered, this study proposed five strategies for improving construction safety performance covering safety skills, safety awareness, safety protection and emergency response. This research would be valuable to both researchers and practitioners. Researchers would benefit from gaining a deeper understanding of the characteristics of construction safety injuries, application of data mining methods, and relevant future research directions, while practitioners would benefit by learning about the strategies proposed to mitigate injury risks and prevent incidents.