Abstracts – Browse Results
Click on the titles below to expand the information about each abstract.
Viewing 1 results ...
Tan, Y, Smith, N J and Bower, D A (2003) Improving risk identification by utilizing hybrid intelligent reasoning. In: Greenwood, D J (Ed.), Proceedings 19th Annual ARCOM Conference, 3-5 September 2003, Brighton, UK. Association of Researchers in Construction Management, Vol. 1, 359–68.
- Type: Conference Proceedings
- Keywords: case-based reasoning; decision support; reasoning; risk identification; rule-based reasoning
- ISBN/ISSN: 0 9534161 8 6
- URL: http://www.arcom.ac.uk/-docs/proceedings/ar2003-359-368_Tan_Smith_and_Bower.pdf
- Abstract:
Risk management is an important project management tool that is in order the understanding of the scope and potential problems related to projects to support decision making. Despite the wide variety of methods in existence, the application of risk management in practice is still limited. One reason relates to the level of accuracy and complexity of current analysis tools, accurate analysis relies upon the identification of realistic risk factors. Risk identification is about trying to forecast potential sources of risk that might impact on successful completion of a project. Risk identification is a key part of risk management and it identifies the potential sources of risk. Risk forecasting considers the probability and impact of these sources. Popular risk identification methods are mostly based on expert knowledge, so identification largely depends on the involvement and the sophistication of experts. Subjective judgement and intuition usually accompany the experts’ opinion; this could be expressed as the impact of human behaviour. In order to reduce such subjectivity and enhance knowledge sharing, artificial intelligent techniques can be utilised. An intelligent system provides storage to accumulate retrievable knowledge and reasoning in an impartial way so that a common acceptable solution can be achieved. This paper introduces a hybrid approach to modelling risk identification in construction projects. Case-based reasoning and rule-based reasoning are two artificial intelligent paradigms that have already proved to be successful in managing knowledge. The integration of Case-based reasoning and Rule-based reasoning is particularly useful for project knowledge in relation to risk. Case-based reasoning matches the manner that humans solve problems by remembering past similar experience, which can provide compelling support for forecasting and then decision making. Rule-based reasoning provides suggestions on the basis of a situation detection mechanism that relies on structured prior knowledge when there are no matching cases in case base. A pilot study has shown that the approach is feasible and this will soon be fully tested using project data.