Hsin-Yun Lee

Integrating Simulation and Ant Colony Optimization to Improve the Service Facility Layout in a Station

A good layout of the service facilities in a station can reduce the total walking distance of passengers to and from various facilities. It improves the overall service efficiency and quality of the station. Over time the original layout of a station may become unsuitable. This is often due to the changes in the number of passengers, the types of passengers, and the surrounding environment. In such cases, a comprehensive review of the layout should be conducted. However, the layouts possible are numerous and should be investigated using quantitative evaluation. This paper proposes an integrated model that estimates the total walking time of a passenger by simulation and searches for a near-optimal layout by ant colony optimization. A high-speed railway station is employed as a case study to evaluate the feasibility of the proposed model. The results indicate that the proposed model can effectively save passengers time and improve the service efficiency of the station.

Decision support for the maintenance management of green areas

For schools, parks, and recreational areas, the maintenance of green areas is important, but it places a heavy burden on both manpower and budget. In this paper, we proposed a model to search for the minimum gardener manpower requirements and a near-optimal maintenance schedule for the green areas. Unlike other applications of ant colony optimization, we grouped the ants into teams to represent gardeners and considered the path of an ant team a schedule solution. We implemented the proposed model using a decision support system called the Garden-Ant. In addition, the feasibility of the model was evaluated on a campus. The results of the evaluation indicated that the proposed model could provide an appropriate maintenance plan, including manpower estimation and an all-inclusive maintenance schedule. Because the complicated calculations are performed by the model instead of by an administrator, the maintenance planning of green areas can be accomplished in an easy and efficient manner.

Activity and value orientated decision support for the development planning of a theme park

The development of a large theme park usually includes multiple phases. The combination and development ordering of facilities in these phases have a great impact on the attractiveness of the theme park. Examples of such facilities are attractions, food service, accommodation, and supporting facilities. Some of these facilities although highly profitable, cannot attract visitors on their own, while others may boost the visitor count, yet by themselves do not make a profit. This research considers the values that each development activity brings to the project, and prioritizes feasible alternatives based on their net present values. Based on the integration of simulation and the genetic algorithm, a decision support system has been developed to determine the combination and ordering of facilities, and the resources needed for each development step. This development plan will provide investors with systematic and quantitative information that will help them to determine the development portfolio of each facility under the constraint of the funding program.

Developing as-built BIM model process management system for general contractors: A case study

AbstractAs the application of building information modeling (BIM) becomes more common, BIM model management becomes necessary and important to enhance the effectiveness of BIM implementation for a general contractor (GC) during the construction phase. Implementation of BIM models in the construction phase, which typically involves participants from different fields, often has numerous BIM-related interfaces and problems. Therefore, feedback from the most recent as-built model tracking and BIM model problems are essential for BIM process management (BIM PM) in the construction field. BIM PM has become the most important aspect of a sound as-built BIM model management strategy. Changes in as-built BIM models should be identified, updated, and tracked for BIM PM, such that version management of as-built BIM models can be improved, while minimizing rework and reducing as-built BIM models development duration. Systematic approaches and information on management platforms for enhancing BIM PM during the constru...

Use of Support Vector Regression to Improve Computational Efficiency of Stochastic Time-Cost Trade-Off

AbstractStochastic time-cost trade-off has been a popular object of investigation in past decades because there are uncertain factors that can be considered when determining the appropriate trade-off between project completion time and cost. Previous studies, however, have implemented a double loop procedure, which performs optimization in the outer loop and simulation in the inner loop. The double loop procedure is ponderous because it requires an unacceptably long computation time (taking hours or days), even for a small to medium project. The present study proposes an integrated system that converts the double loop to single loops,thereby dramatically reducing computation time. This is done by incorporating a support vector regression model to obtain a decision function, which will be used to replace the time-consuming Monte Carlo simulation to evaluate the objective function values for individual solutions. With the objective function values, a multiobjective particle swarm optimization algorithm is d...

An integrated model for planning development projects using ACO and construction simulation

In development projects, especially in a residential development project, the level and the number of facilities and the schedule must be carefully planned to ensure long-term operation and financial stability of the project. This paper proposes an integrated model that estimates the performance of a development project through simulation and searches for a near-optimal plan with the maximum net present value (NPV) using ant colony optimisation. A development project of coastal vacation residences is employed as the case study to evaluate the feasibility of the proposed model. The proposed model provides a solution featuring a near-largest NPV. The complicated and time-consuming calculations of the resource flows between activities can be accomplished through simulation, and the near-optimal development level and schedule of the facilities are assumed. With the support of the proposed model, the decision-making process is made substantially easier for the planner.

Using a Guiding Network to Determine Efficient Evacuation Routes in a Public Building

AbstractPrevious studies of models for evacuation routing usually divide the space into multiple interlinked zones. However, for public buildings that are characterized by a more complicated spatial composition, it may be harder to clearly and objectively define the margins for each zone. This paper proposes an approach that determines the most appropriate guidance locations and assembles them into an efficient guiding network. This allows evacuation routes to be constructed based on the links between starting points, guiding nodes, and terminal points. This approach avoids the difficulty of dividing a space into multiple zones and conforms more to real-life evacuation behavior. This paper also proposes an integrated model that applies simulation to estimate the evacuation time and ant colony optimization algorithms to search for an evacuation routing plan and a near-optimal guiding solution. The feasibility of the model is evaluated through a case of one floor in a hospital building. The results indicate...

A decision support model for scheduling exhibition projects in art museums

The main purpose of scheduling exhibition projects for art museums is to provide the visitors with more exhibitions and to utilize the galleries as fully as possible. Because the combinations of possible exhibitions for all galleries at any given time are numerous, it is difficult for the art museums planner to make an optimal decision. Therefore, this paper developed a decision support model with genetic algorithms, called SCHEMA (SCHeduling Exhibitions for Museum of Art). In the model the galleries are the resource which the exhibitions utilize in the sequence of their priority values. The models evaluation shows to be significantly effective in planning time, percent usage of the gallery, and the number of exhibitions scheduled. Because all the complex computations are done by the model, the decision making process of the scheduling stage is speeded up considerably.

A hybrid system for planning the development level of resort

In todays world, a resort is a popular place that provides not only relaxation and recreation but also beautiful surroundings, high quality food, even facilities to exercise and do other healthy activities. Planning the development level is one of the more important processes in a resort development project. However, planners often subjectively overestimate the project or cater to the preferences of the investors, resulting in an over-developed or imbalanced development. This paper provides a system that helps the planner to search for near-optimal amenity development level. Integrating genetic algorithms and simulation, it employs a dual-loop optimization model to propose advice to be used in the planning stage. Because the complex and dynamic analysis is done by the system instead of by the planner, it speeds up the decision-making process of the planning stage.

A DECISION SUPPORT SYSTEM FOR EXPOSITION TIMETABLING USING ANT COLONY OPTIMIZATION

The exposition industry has developed rapidly in recent years. For exposition centers, exposition timetabling is a complicated problem. The timetables arranged by the administrators usually result in an imbalanced usage percentage between showgrounds and a low total usage percentage for all showgrounds. In this paper, we developed a decision support system that considers the characteristics of exposition timetabling. The proposed system applies ant colony optimization for determining the near-optimal timetable of expositions. The ants are grouped into teams representing multi-layer ant paths for priority ranking. This improvement allows us to classify candidate expositions with different time preferences. The showground timetabling of an exposition center is used to validate the proposed system. The timetable proposed by the decision support system ensures a higher efficiency and a higher total usage percentage of the showgrounds than the timetable proposed by a human expert.