Using neural network to predict performance of design-build projects in Singapore

Ling, Florence Yean Yng; Liu, Min

doi:10.1016/j.buildenv.2004.02.008

Cited by 92 publications

(62 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most of these experience come from the construction industry where an high standardization of processes allows the creation of a common knowledge base. • Managerial approach: ANN (classification type) identify the relation that exists among project performances and key project management levers, as for organizational and managerial factors (Chen et al, 2012;Dvir et al, 2006;Ling and Liu, 2004;Zhang et al, 2003). This paper below belongs to this second research stream.…”

Section: Artificial Neural Networkmentioning

confidence: 99%

Project selection in project portfolio management: An artificial neural network model based on critical success factors

Costantino

Gravio

Nonino

2015

International Journal of Project Management

145

View full text Add to dashboard Cite

Section: Artificial Neural Networkmentioning

confidence: 99%

Project selection in project portfolio management: An artificial neural network model based on critical success factors

Costantino

Gravio

Nonino

2015

International Journal of Project Management

145

View full text Add to dashboard Cite

“…The ANN method has a robust learning capability and fairly accurate prediction ability, even if the information is incomplete, especially for the decision content of this research, which is the complex nonlinear relationships between inputs and outputs (Ling & Liu, 2004). Among the many types of ANNs, the backpropagation learning algorithm with the feedforward architecture is selected to construct the ANN model.…”

Section: Network Architecture and Ann Operationmentioning

confidence: 99%

Artificial Neural Network Based Decision Model for Alternative Workplaces

Kim

Juan

2014

Journal of Asian Architecture and Building Engineering

View full text Add to dashboard Cite

Alternative workplace arrangements (AWAs), enabled by information and communication technology, where employees do not have permanently assigned workspaces on company premises, are likely to continue in the future. However, facility managers have limited tools to select from among the possible choices in which the AWA type is more appropriate considering their organizations' business reasons for adoption and the current readiness condition. The aim of this research is to provide facility managers with an understanding of the decision process for AWA adoption and to develop a decision support model to allow them to select an appropriate AWA type and determine the anticipated satisfaction level. Using the artificial neural network (ANN) method and the case-based reasoning (CBR) technique, the authors have developed and validated a decision model to suggest the most appropriate AWA type given the organization's objectives and the current readiness levels. The proposed approach is tested by evaluating 64 real adoption cases from 19 large hightech companies. The findings reveal that the ANN-based decision model can provide an accurate prediction of the actual values and the support decisions of the facility managers responsible for developing workplace strategies to meet the organization's current and future needs.

show abstract

“…Why does it have to be the learning curve? Wong et al (2007) and Ling and Liu (2004) suggested that the MR approach assumes linear relationship between learning and performance thus leads to unsatisfactory results. In addition, the MR approach might not be feasible, particularly when there are many casual factors while the data used for regression is insufficient (Nembhard and Uzumeri, 2000).…”

Section: The Learning Curvementioning

confidence: 99%

Generic Model for Measuring Benefits of BIM as a Learning Tool in Construction Tasks

Peng

Shen

et al. 2013

J. Constr. Eng. Manage.

View full text Add to dashboard Cite

Over the past years, people's understanding towards Building Information Modeling (BIM) in the architecture, engineering, and construction (AEC) industry has improved significantly. BIM can be diversely recognized as a virtual design and construction environment, a communication vehicle among stakeholders, a lifelong information model, or an education platform that can be used in universities or colleges. BIM can also be used as a learning tool that can aid project teams in familiarizing themselves with a construction task, prior to commencement of the task on site. Yet, little effort has been made to measure the benefits of this kind. The aim of this research is to empirically measure the benefits of BIM as a learning tool in real-life construction tasks. The learning curves of two situations: construction tasks with and construction tasks without BIM are identified by following a series of analytical processes. The two learning curves are compared and the learning effects contributed by BIM are modeled as L effBIM . By inputting their own data, practitioners may use this generic model to measure learning effects contributed by BIM in their own projects. The model can be used to convince potential BIM users by showing empirical evidence of BIM's benefits. It is also hoped that the model can join the concerted efforts to promote BIM's value in the AEC industry.

show abstract

Using neural network to predict performance of design-build projects in Singapore

Cited by 92 publications

References 18 publications

Project selection in project portfolio management: An artificial neural network model based on critical success factors

Project selection in project portfolio management: An artificial neural network model based on critical success factors

Artificial Neural Network Based Decision Model for Alternative Workplaces

Generic Model for Measuring Benefits of BIM as a Learning Tool in Construction Tasks

Contact Info

Product

Resources

About