(2013) On Effective Task Classification for Supporting Job Hazard Analysis

 
Using text classification as a method to simulate the logics of JHA and automatically extract potentially relevant safety tips from existing documents prepared manually by subject experts.
 
The dangers of the construction industry due to the risk of fatal hazards, such as falling from extreme heights, being struck by heavy equipment or materials, and the possibility of electrocution, are well known. The concept of Job Hazard Analysis is commonly used to mitigate and control these occupational hazards. This technique analyzes the major tasks in a construction activity, identifies all potential task-related hazards, and suggests safe approaches to reduce or avoid each of these hazards. In this paper, the authors explore the possibility of leveraging existing construction safety resources to assist JHA, aiming to reduce the level of human effort required. Specifically, the authors apply ontology-based text classification (TC) to match safe approaches identified in existing resources with unsafe scenarios. These safe approaches can serve as initial references and enrich the solution space when performing JHA. Various document modification strategies are applied to existing resources in order to achieve superior TC effectiveness. The end result of this research is a construction safety domain ontology and its underlying knowledge base. A user scenario is also discussed to demonstrate how the ontology supports JHA in practice.

 

Related Publication:

Chi, N.W., Lin, K.Y., Hsieh, S.H. (article in press, first published online on June 18, 2014) “Using Ontology-Based Text Classification to Assist Job Hazard Analysis”, Advanced Engineering Informatics, Elsevier.

Chi, N.W., Lin, K.Y., Hsieh, S.H. (2013) “On Effective Text Classification for Supporting Job Hazard Analysis”, ASCE International Workshop on Computing in Civil Engineering 2013 (IWCCE 2013), June 23 – 25, 2013, Los Angeles, California.

Chi, N.W., Lin, K.Y., Hsieh, S.H. (2012), “Extracting Construction Safety Domain Ontology from Job Hazard Analysis Databases and Construction Safety Standards”, in the proceedings of the International Conference on Computing in Civil and Building Engineering (ICCCBE) 2012, June 27 – 29, 2012, Moscow, Russia.