Case-Based Reasoning for Construction Hazard Identification: Case Representation and Retrieval
MetadataShow full item record
This paper proposes a case-based reasoning (CBR) approach to construction hazard identification that facilitates systematic feedback of past knowledge in the form of incident cases and hazard identification. This paper focuses on two of the key components of the CBR approach: (1) a detailed knowledge representation scheme, developed based on the modified loss causation model, to codify incident cases and past hazard identification and (2) an intelligent retrieval mechanism that can automatically retrieve relevant past cases. The detailed knowledge representation scheme presented herein is designed to model both incident cases and hazard identification so that both types of knowledge repository can be retrieved simultaneously and adapted for use. The scheme also includes a linguistic structure used to facilitate indexing of cases. The retrieval mechanism is based on the concept of similarity scoring. In this paper, a novel scoring technique based on semantic networks is presented. A case study is presented to demonstrate and validate the proposed approach.
Showing items related by title, author, creator and subject.
Case-Based Reasoning Approach to Construction Safety Hazard Identification: Adaptation and UtilizationGoh, Yang Miang; Chua, D. (2010)Risk assessment, consisting of hazard identification and risk analysis, is an important process that can prevent costly incidents. However, due to operational pressures and lack of construction experience, risk assessments ...
Nugraheni, Fitri (2008)This thesis sets out research carried out to investigate the usefulness of a descriptive database of construction methods for safety assessment. In addition, it investigates the possibility of utilising construction images ...
Seligmann, Benjamin; Németh, E.; Hangos, K.; Cameron, I. (2012)A novel hazard identification methodology applied to process systems is presented in this paper. This blended hazard identification (BLHAZID) methodology blends two different types of HAZID methods: the function-driven ...