No description available.

We use the elitist and extinction policies to improve the simple genetic algorithm in this study. We expect that the search technique can avoid falling into the local maximum due to the premature convergence, and the chance of finding the near-optimal parameter in the larger searching space could be obviously increased. The accelerometer is then taken as the sensor for output measurement, and the designed controller is implemented to actively suppress the vibration of the plain that is due to the excitation effect of the high-speed and precision positioning of the linear motor. From the computer simulations and the experimented results, it is obvious that the near-optimal controller designed by using genetic approach with elitist and extinction can improve the effect of vibration suppression; the settling time is also decrease. For the vibration suppressions of high-speed precision positioning problems, the results are satisfactory in the cases of short, middle and long distance.

ABSTRACT In this dissertation, several adaptive control design schemes for a class of nonlinear systems are proposed. The first topic of the research is concerned with self-tuning PID controller design. The main problem of designing PID controller is how to determine the values of three control gains, i.e., proportional gain , integral gain , and derivative gain . We attempt to use the technique of adaptive control based on the Lyapunov approach to design the PID controller for some class of partially known nonlinear systems. Three PID control gains are adjusted on-line such that better output performance can be achieved. The stability of the closed-loop PID control systems is analyzed and guaranteed by introducing a supervisory control and a modified adaptation law with projection. Second, two kinds of adaptive neural control systems including the direct and indirect neural controls are considered by using simple single auto-tuning neuron. We will first propose a novel neuron called auto-tuning neuron and use it to take place of the roles of the traditional neural networks used in the direct and indirect adaptive neural control systems. This can greatly reduce the computational time and network complexities due to the simple configuration of the auto-tuning neuron. It is also easy for hardware implementation. Third, based on the idea borrowed from natural evolution, genetic algorithm can search for optimal or near-optimal solutions for an optimization problem over the search domain. An optimization technique of real-coded genetic algorithm is used to design the PID controller by minimizing the performance index of integrated absolute error. The improvements of our results over that using other methods are also illustrated. In the last part of each section, some computer simulation results will also be provided to illustrate our proposed methods.

Synthetically generated terrain models are useful across a broad range of applications, including computer generated art & animation, virtual reality and gaming, and architecture. Existing algorithms for terrain generation suffer from a number of problems, especially that of being limited in the types of terrain that they can produce and of being difficult for the user to control. Typical applications of synthetic terrain have several factors in common: first, they require the generation of large regions of believable (though not necessarily physically correct) terrain features; and second, while real-time performance is often needed when visualizing the terrain, this is generally not the case when generating the terrain. In this thesis, I present a new, design-by-example method for synthesizing terrain height fields. In this approach, the user designs the layout of the terrain by sketching out simple regions using a CAD-style interface, and specifies the desired terrain characteristics of each region by providing example height fields displaying these characteristics (these height fields will typically come from real-world GIS data sources). A height field matching the user's design is generated at several levels of detail, using a genetic algorithm to blend together chunks of elevation data from the example height fields in a visually plausible manner. This method has the advantage of producing an unlimited diversity of reasonably realistic results, while requiring relatively little user effort and expertise. The guided randomization inherent in the genetic algorithm allows the algorithm to come up with novel arrangements of features, while still approximating user-specified constraints.

Because the government changed laws and opened the market progressively in recent years, the financial market in Taiwan becomes more and more liberal and international; every investor has to face a more complicated investitive environment. They can choice many investitive objects and tools, but how to choice the best one is a big problem for them and the risk in the financial market becomes much higher. Mutual fund is a popular investment tools in recent year. One of the mutual fund¡¦s benefits is the diversity of investment and effectively disperses risk.. In August 2006, the government in Taiwan opens up the market of mutual fund; the investors can buy offshore mutual funds in many channels, so they can choice many kinds of mutual funds, about 1,400 in April 2008. Also, every investor that can beat the level of risk is so different, it maybe make them confused and really want to know which one is much better and do asset allocation very well. Therefore, how to design a good portfolio for different perceived risk levels of investors is a worthful topic in the academia and the really world. This research uses the genetic algorithm to construct mutual fund portfolios based on perceived risk levels, use fund return, standard deviation, Alpha, Beta, Sharpe, IR and Sortino indicators to select funds of a portfolio and calculate portfolio return and standard deviation, then do asset allocation. This research change funds in every portfolio every month using Sliding Windows method from Jan 1, 2001 to Dec 12, 2007, totally 84 times. The result of this research is every portfolio average return wins benchmark index average return. The standard deviation of every portfolio also wins benchmark index standard deviation. It shows this research can beat benchmark index effectively and also can decrease the risk of portfolio return, then we can get a good fund portfolio for different perceived risk levels of investors

In this thesis we have proposed a variable-length multiobjective genetic algorithm to solve heterogeneous wireless transmitter placement with multiple constraints. Among many factors that may affect the result of placement, we focus on four major requirements, coverage, cost, data rate demand, and overlap. In the proposed algorithm we release the need for the upper bound number of transmitters that is a major constraint in the existing methods and achieve better wireless transmitter placement while considering the transmitter position and design requirement simultaneously. In experiments, we use the free space propagation model, the large scale propagation model which considers the shadowing effect, and the extended Hata-Okumura model to predict the path loss in a real two dimensional indoor environment, and an outdoor environment and even a real three dimensional outdoor environment. Experimental results show that the proposed algorithm can find many feasible solutions for all test cases under four objectives.

The manual trial and error has been widely used in the past, but such approach is inefficient. In recent years, many heuristic algorithms used in a wide range of applications have been developed. These algorithms have more efficiency than traditional ones, because they can locate the best solution. Every algorithm has its own niche application in different problems. In this study, the boundary parameters of the hydrodynamic-based tidal model are calibrated by using the Simulated Annealing algorithms (SA). The objective is to minimize the deviation between the estimated results acquired from the simulation model and the real tidal data along Taiwan coast. Based on the real physics distribution of the boundary parameters, we aimed to minimize the sum of each station¡¦s root mean square error (RMSE). Genetic Algorithms (GAs) and Simulated Annealing Algorithms on parameters calibration for tidal model are compared under the same condition. GAs is superior on solving the problems mentioned above while both algorithms showed improved results. By setting the initial solution derived from GAs, the solving efficiency of SA can be improved in this study.

The k-LCS problem is to find the longest common subsequence (LCS) of k input sequences. It is difficult while the number of input sequences is large. In the past, researchers focused on finding the LCS of two sequences (2-LCS). However, there is no good algorithm for finding the optimal solution of k-LCS up to now. For solving the k-LCS problem, in this thesis, we first propose a mixed algorithm, which is a combination of a heuristic algorithm, genetic algorithm (GA) and ant colony optimization (ACO) algorithm. Then, we propose an enhanced ACO (EACO) algorithm, composed of the heuristic algorithm and matching pair algorithm (MPA). In our experiments, we compare our algorithms with expansion algorithm, best next for maximal available symbol algorithm, GA and ACO algorithm. The experimental results on several sets of DNA and protein sequences show that our EACO algorithm outperforms other algorithms in the lengths of solutions.

Genetic Algorithm (GA) as a class of Evolutionary Algorithm (EA) is a search algorithm based on the mechanics of natural selection and natural genetics. This dissertation presents the description, solving procedures and application of GA. The definitions of selection, crossover and mutation operators are given in details and an application based on GA in Time Table Problem (TTP) is performed in a new way. Due to its high capability of overall search, GA is particularly appropriate for solving timetabling and scheduling problems. TTP (Time Table Problem) which belongs to NP-hard problem is a special problem concerning resource management. In this dissertation, a new chromosome coding is designed in order to solve TTP more effectively. And the result presented by MATLAB will converge to a steady condition.

Genetinių algoritmų panaudojimo galimybės ir paplitimas nuolat didėja. Daugelyje nagrinėtų mokslinių darbų, genetiniai algoritmai yra naudojami uždavinių optimizavimui. Optimizavimui naudojama daug skirtingų metodų. Sprendžiant konkretų uždavinį mokslinėje literatūroje paprastai pritaikoma keletas metodų tam, kad būtų pagerinti gauti rezultatai, t.y., išbandoma keletas strategijų. Deja, nepavyko rasti tyrimų, kaip tos pačios genetinės paieškos strategijos gali būti pritaikytos kitoms analogiškoms problemoms spręsti. Šiame darbe pateikiama probleminės srities apžvalga, tyrimo aprašymas bandymų rezultatai ir išvados. / The use of genetic algorithms considerably increases. In some research works GA‘s are investigated to optimize graph problems. There are many different strategies for GA optimization. Unfortunately, there are no investigations if a strategy, suitable for a particular graph problem, will be useful solving other graph problems. In this work I originated, described and developed some GA learning strategy elements. Also I developed some that are available in other research works. These elements are: generation of initial population, selection of individuals, mutation, crossover and some other parameters. All possible strategies (about 300) are tested in this work for three graph problems: shortest path, longest path and traveling salesman problem. Results are summarized and described.