Please use this identifier to cite or link to this item: https://scholarbank.nus.edu.sg/handle/10635/222830
Title: KNOWLEDGE REPRESENTATION OF WORK AT HEIGHT ACTIVITIES ON CONSTRUCTION SITES
Authors: YONG RUI FATT
Keywords: PFM
Building
Goh Yang Miang
Project and Facilities Management
2013/2014 PFM
Issue Date: 8-Jul-2014
Citation: YONG RUI FATT (2014-07-08). KNOWLEDGE REPRESENTATION OF WORK AT HEIGHT ACTIVITIES ON CONSTRUCTION SITES. ScholarBank@NUS Repository.
Abstract: This paper propose a case-based reasoning (CBR) framework to improve the feedback process by utilizing the lesson learnt from past projects and. In the past few years, there was no significant improvement on reducing the incident rate in construction sector. Instead, the incident rate has increased in 2013. Among all the incidents such as struck by objects, slipped and tripped, falling from height (FFH) has the highest occurrence rate. As such, the aim of this research is to create a standardized and user-friendly framework that can be widely used in construction industry. Hence, the research hypothesis of this paper is that the feedback mechanism can be considerably improved by using the proposed CBR framework and ultimately leads to reduction of incident rate specifically for FFH. Three case studies are presented to illustrate the use of CBR in different context. Moreover, interviews are conducted to obtain the insight of safety professionals regarding how different attributes of a work at height activity can have different impacts in the possibility of causing an incident with relation to influence of degree of similarity between two cases. In addition, the relative importance rating or weightage of each attribute will be ranked by the interviewee. After the cases were collected, it is designed to be represented by a set of attributes which describe the context of an activity. The list of case attributes were generated through study from different guidelines and reports published by the government. In addition, a linguistic structure is developed to help in indexing vocabulary of case. The retrieval tools that are used in case retrieval process are the flat memory searching approach, local similarity scoring using the principle of dualistic variable, global similarity scoring associated with the weightage provided during interviews. Ultimately, the additional recommended actions to be implemented in new scenario will be identified after retrieving the most similar case. As such, a CBR framework is established and modified with proper case representation and case retrieval process. Nonetheless, further works such as case adaptation and case mining has to be done to fully complete the CBR framework.
URI: https://scholarbank.nus.edu.sg/handle/10635/222830
Appears in Collections:Bachelor's Theses

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
Yong Rui Fatt 2013-2014.pdf1.28 MBAdobe PDF

RESTRICTED

NoneLog In

Page view(s)

7
checked on Jan 26, 2023

Download(s)

7
checked on Jan 26, 2023

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.