Analyzing construction safety through time series methods

摘要: The construction industry produces a large amount of data on daily basis. However, existing sets have not been fully exploited in analyzing the safety factors projects. Thus, this work describes how temporal analysis techniques can be applied to improve management data. Various time series (TS) methods were adopted for identifying leading indicators or predictors accidents. set used herein was obtained from company that is based Singapore and contains inspection scores, accident cases, project-related collected 2008 2015. Five projects with complete sufficient selected set. filtered contained 23 potential (predictors input variables) accidents (output dependent variable). TS analyses identify suitable each five Subsequently, variables develop three different models predicting occurrences, vector error correction model found best model. It had lowest root mean squared value analyzed. This study provides insights into companies utilize high risk