Spelling suggestions: "subject:"[een] GENETIC ALGORITHMS"" "subject:"[enn] GENETIC ALGORITHMS""
91 |
Scheduling trucks in port container terminals by a genetic algorithmZhang, Yuxuan, January 2005 (has links)
Thesis (M. Phil.)--University of Hong Kong, 2006. / Title proper from title frame. Also available in printed format.
|
92 |
A comparison of simulated annealing and genetic algorithms for the genome mapping problemsGunnels, John A. 10 August 1993 (has links)
The data used for the construction of genome maps is imperfect, therefore the
mapping of a physically linear structure must take place in a very uneven feature space.
As the number of genes to be ordered grows, it appears to be impractical to use
exhaustive search techniques to find the optimal mapping. In this paper we compare
genetic algorithms and simulated annealing, two methods that are widely believed to
be well-suited to non-smooth feature spaces, and find that the genetic algorithm
approach yields superior results. Here we present performance profiles of comparable
implementations of both genetic algorithms and simulated annealing. We have
translated the problem to a form comparable to the shortest-path problem and found
that the ability of a genetic algorithm to combine different partial solutions seems to be
responsible for its superiority over the simulated annealing method. This is because in
the genome mapping problem, as in the Traveling Salesman Problem, good solutions
tend to be rather sparse and because optimal subtours tend to be components of nearly
optimal tours. / Graduation date: 1994
|
93 |
A Method for Aircraft Concept Exploration using Multicriteria Interactive Genetic AlgorithmsBuonanno, Michael Alexander 28 November 2005 (has links)
The problem of aircraft concept selection has become increasingly difficult in recent years due to changes in the primary evaluation criteria of concepts. In the past, performance was often the primary discriminator whereas modern programs have placed increased emphasis on factors such as environmental impact, economics, supportability, aesthetics, and other metrics. The revolutionary nature of the vehicles required to simultaneously meet these conflicting requirements has prompted a shift from design using historical data regression techniques for metric prediction to the use of sophisticated physics-based analysis tools that are capable of analyzing designs outside of the historical database. The use of optimization methods with these physics-based tools, however, has proven difficult because of the tendency of optimizers to exploit assumptions present in the models and drive the design towards a solution which, while promising to the computer, may be infeasible due to factors not considered by the computer codes. In addition to this difficulty, the number of discrete options available at this stage may be unmanageable due to the combinatorial nature of the concept selection problem, leading the analyst to select a sub-optimum baseline vehicle. Some extremely important concept decisions, such as the type of control surface arrangement to use, are frequently made without sufficient understanding of their impact on the important system metrics due to a lack of historical guidance, computational resources, or analysis tools.
This thesis discusses the difficulties associated with revolutionary system design, and introduces several new techniques designed to remedy them. First, an interactive design method has been developed that allows the designer to provide feedback to a numerical optimization algorithm during runtime, thereby preventing the optimizer from exploiting weaknesses in the analytical model. This method can be used to account for subjective criteria, or as a crude measure of un-modeled quantitative criteria. Other contributions of the work include a modified Structured Genetic Algorithm that enables the efficient search of large combinatorial design hierarchies and an improved multi-objective optimization procedure that can effectively optimize several objectives simultaneously. A new conceptual design method has been created by drawing upon each of these new capabilities and aspects of more traditional design methods.
The ability of this new technique to assist in the design of revolutionary vehicles has been demonstrated using a problem of contemporary interest: the concept exploration of a supersonic business jet. This problem was found to be a good demonstration case because of its novelty and unique requirements, and the results of this proof of concept exercise indicate that the new method is effective at providing additional insight into the relationship between a vehicle's requirements and its favorable attributes.
|
94 |
SIRMs Fuzzy Controller via Genetic Algorithms for Inverted Pendulum SystemsLee, Wen-jeng 24 June 2004 (has links)
We use non-binary coding, elitist strategy, increasing mutation rate, extinction, and immigration strategy to improve the simple genetic algorithms in this study. We expect that the search technique can avoid falling into the local optimum due to the premature convergence, and purse the chance that finding the near-optimal parameters in the larger searching space could be obviously increased.
We utilize SIRMs(Single Input Rule Modules) fuzzy controller for the stabilization control of inverted pendulum systems, and the dynamic importance degrees are built such that the angular control of the pendulum takes priority over the position control of the cart. We utilize modified genetic algorithms(MGA) to automatically tuning scaling factors of SIRMs fuzzy controller. From computer simulations, the pendulum control and the cart position control can fastly be stabilized.
|
95 |
The Deployment of Energy-Efficient Wireless Sensor Networks using Genetic AlgorithmsLiu, Mao-Tsung 11 September 2006 (has links)
Recently, wireless sensor networks have attracted a lot of attention. Such environments may consist of many inexpensive nodes, each capable of collecting, storing, and processing environmental information, and communicating with base station nodes through wireless links. In this paper, we survey a fundamental problem in wireless sensor networks, the energy consumption problem, which reflects how well a sensor field is deployed. Therefore, a critical aspect of applications with wireless sensor networks is network lifetime. Furthermore, one of the fundamental issues in sensor networks is the coverage problem, which reflects how well a sensor network is monitored or tracked by sensors. We formulate this problem as a decision problem, whose goal is to determine whether every point in the service area of the sensor network is covered by at least k sensors, where k is a given parameter. In this paper, we propose an energy-efficient method based on Genetic Algorithms to deal with the deployment problem of wireless sensor networks such that it provides target-location and surveillance services.
|
96 |
Optimization of transition state structures using genetic algorithms /Bungay, Sharene D., January 2000 (has links)
Thesis (M.Sc.)--Memorial University of Newfoundland, 2000. / Bibliography: leaves 80-82.
|
97 |
Hearing aid fitting with genetic algorithms /Durant, Eric Alan, Wakefield, Gregory H. January 2002 (has links)
Thesis (Ph. D.)--University of Michigan, 2002. / Includes bibliographical references. Also available on the Internet.
|
98 |
Construction of efficient fractional factorial mixed-level designsGuo, Yong, Simpson, James R. January 2003 (has links)
Thesis (M.S.)--Florida State University, 2003. / Advisor: Dr. James R. Simpson, Florida State University, College of Engineering, Dept. of Industrial and Manufacturing Engineering. Title and description from dissertation home page (viewed Mar. 2, 2004). Includes bibliographical references.
|
99 |
Application of genetic algorithms to the design of microstrip antennas, wire antennas and microwave absorbersChoo, Hosung. January 2003 (has links)
Thesis (Ph. D.)--University of Texas at Austin, 2003. / Vita. Includes bibliographical references. Available also from UMI Company.
|
100 |
Evolutionary optimisation of production-control systems /Mok, Pik-yin. January 2001 (has links)
Thesis (Ph. D.)--University of Hong Kong, 2002. / Includes bibliographical references (leaves 451-486).
|
Page generated in 0.0359 seconds