http://hdl.handle.net/10397/1236 Search the Channel search http://repository.lib.polyu.edu.hk/jspui/simple-search http://hdl.handle.net/10397/1298 Title: An intelligent decision support system in construction management by data warehousing technique<br/><br/>Authors: Cao, Ying; Chau, Kwok-wing; Anson, M.; Zhang, Jianping<br/><br/>Abstract: The integration of a Data Warehouse and a Decision Support System (DSS) can provide construction managers with sufficient information for decision making without interrupting daily work of an On-Line Transaction Processing system. In this paper, the concepts of the data warehouse, On-Line Analysis Processing and DSS are first reviewed. The method of creating a data warehouse is then shown, changing the data in the data warehouse into a multidimensional data cube and integrating the data warehouse with a DSS. An application example is given to illustrate the use of the Construction Management Decision Support System developed in this study. This prototype system can enable the right data to be tracked down and provides the required information in a direct, rapid and meaningful way. Construction managers can view data from various perspectives with significantly reduced query time, thus making decisions more efficiently. Moreover, the approach can be applied to other fields.<br/><br/>Description: DOI: 10.1007/3-540-45785-2_28 Tue, 01 Jan 2002 00:00:00 GMT http://hdl.handle.net/10397/1297 Title: Algal bloom prediction with particle swarm optimization algorithm<br/><br/>Authors: Chau, Kwok-wing<br/><br/>Abstract: Precise prediction of algal booms is beneficial to fisheries and environmental management since it enables the fish farmers to gain more ample time to take appropriate precautionary measures. Since a variety of existing water quality models involve exogenous input and different assumptions, artificial neural networks have the potential to be a cost-effective solution. However, in order to accomplish this goal successfully, usual problems and drawbacks in the training with gradient algorithms, i.e., slow convergence and easy entrapment in a local minimum, should be overcome first. This paper presents the application of a particle swarm optimization model for training perceptrons to forecast real-time algal bloom dynamics in Tolo Harbour of Hong Kong, with different lead times on the basis of several input hydrodynamic and/or water quality variables. It is shown that, when compared with the benchmark backward propagation algorithm, its results can be attained both more accurately and speedily.<br/><br/>Description: DOI: 10.1007/11596448_95 Sat, 01 Jan 2005 00:00:00 GMT http://hdl.handle.net/10397/1296 Title: Intelligence-based educational package on fluid mechanics<br/><br/>Authors: Chau, Kwok-wing<br/><br/>Abstract: From the student feedback questionnaire, some students opined that the concepts of fluid mechanics are quite abstract and that they have difficulty in grasping the phenomena in real life situation. Hence, it demands some innovative learning methodologies to help arouse their interest. This paper depicts the development and implementation of an interactive teaching package on learning of basic fluid mechanics with a knowledge-based system approach. The prototype package is designed to guide engineering students in self-directed learning through the processes of interaction, reflection, and application, thus furnishing an opportunity of stimulating pedagogical environment. Diagnostic assessment is undertaken for every scenario of possible prompted answer on a specific topic, so as to evaluate the most probable shortfall or misconception of that particular student.<br/><br/>Description: DOI: 10.1007/11553939_107 Sat, 01 Jan 2005 00:00:00 GMT http://hdl.handle.net/10397/1295 Title: Application of PGA on optimization of distribution of shopping centers<br/><br/>Authors: Yu, Bin; Cheng, Chuntian; Yang, Zhong-Zheng; Chau, Kwok-wing<br/><br/>Abstract: In this study, the distribution of shopping centers is optimized in terms of realizing the shortest car-based shopping trips in an urban area. Modal split is performed between road and public traffic networks is calculated, and then the interaction between land-use and transportation in the context of choice of shopping destinations is modeled to build the optimal function. Parallel genetic algorithm (PGA) is applied to solve the optimal problem on distribution of the area of shopping centers. Several problems in application of PGA are discussed. A case study is undertaken in order to examine the effectiveness of this method.<br/><br/>Description: DOI: 10.1007/11558590_58 Sat, 01 Jan 2005 00:00:00 GMT