In this thesis, we have proposed a novel microarray gene selection algorithm consisting of five processes for solving gene expression classification problem. A normalization process is first used to remove the differences among different scales of genes. Second, an efficient gene ranking process is proposed to filter out the unrelated genes. Then, the genetic algorithm is adopted to find the informative gene subsets for each class. For each class, these informative gene subsets are adopted to classify the testing dataset separately. Finally, the separated classification results are fused to one final classification result. In the first experiment, 4 microarray datasets are used to verify the performance of the proposed algorithm. The experiment is conducted using the leave-one-out-cross-validation (LOOCV) resampling method. We compared the proposed algorithm with twenty one existing methods. The proposed algorithm obtains three wins in four datasets, and the accuracies of three datasets all reach 100%. In the second experiment, 9 microarray datasets are used to verify the proposed algorithm. The experiment is conducted using 50% VS 50% resampling method. Our proposed algorithm obtains eight wins among nine datasets for all competing methods.

The flow shop scheduling problems with fuzzy processing times and fuzzy due dates are investigated in this paper. The concepts of earliness and tardiness are interpreted by using the concepts of possibility and necessity measures that were developed in fuzzy sets theory. And the objective function will be taken into account through the different combinations of possibility and necessity measures. The genetic algorithm will be invoked to tackle these objective functions. A new idea based on longest common substring will be introduced at the best-keeping step. This new algorithm reduces the number of generations needed to reach the stopping criterion. Also, we implement the algorithm on CUDA. The numerical experiments show that the performances of the CUDA program on GPU compare favorably to the traditional programs on CPU.

Genetic algorithms (GAs) are global optimization methods that can be applied to almost all problems, requiring only proper fitness function to evaluate. However, one problem of general GA is slow convergence. An improved GA is presented to speed up the efficiency of searching for global optimum in this author. The concept of this proposed method uses a few cost to obtain better individuals in initial population, and the evolution of GA is divided into two-stage with the concept of the genetic evolution process, which uses to improve efficiency. An improved GA with finite-difference time-domain (FDTD) will be applied to optimize mushroom-type EBG structures, which can obtain a wide range stop-band by adjusting the position of via with different patch size cascaded without changing via size, then the simulation and measurement results are also compared. In addition, the novel steps will be presented to design broadband mushroom-type EBG structures with smaller size systematically.

¡@¡@The dynamic power flow in a dual-input parallel planetary gear train system is simulated in this study. Different wind powers for the small wind turbines are merged to the synchronous generator in this system to simplify and reduce the cost of the system. Nonlinear equations of motion of these gears in the planetary system are derived. The fourth order Runge-Kutta method has employed to calculate the time varied torque, root stress and Hertz stress between engaged gears. The genetic optimization method has also applied to derive the optimized tooth form factors, e.g. module and the tooth face width. ¡@¡@The dynamic power flow patterns in this dual input system under various input conditions, e.g. two equal and unequal input powers, only single available input power, have been simulated and illustrated. The corresponding dynamic stress and safety factor variations have also been explored. Numerical results reveal that the proposed dual-input planetary gear system is feasible. To improve the efficiency of this wind power generation system. An inertia variable flywheel system has also been added at the output end to store or release the kinetic energies at higher or lower wind speed cases. A magnetic density variable synchronous generator has also been studied in this work to investigate the possible efficiency improvement in the system. Numerical results indicate that these inertia variable flywheel and magnetic density variable generator may have advantages in power generation.

Genetic algorithm is often used to find the global optimum in a multi-dimensional search problem. Inspired by the natural evolution process, this algorithm employs three reproduction strategies -- cloning, crossover and mutation -- combined with selection, to improve the population as the evolution progresses from generation to generation. Femtosecond laser pulse tailoring, with the use of a pulse shaper, has become an important technology which enables applications in femtochemistry, micromachining and surgery, nonlinear microscopy, and telecommunications. Since a particular pulse shape corresponds to a point in a highly-dimensional parameter space, genetic algorithm is a popular technique for optimal pulse shape control in femtosecond laser experiments. We use genetic algorithm to optimize third harmonic generation (THG), and investigate various pulse shaper options. We test our setup by running the experiment with varied initial conditions and study factors that affect convergence of the algorithm to the optimal pulse shape. Our next step is to use the same setup to control coherent anti-Stocks Raman scattering. The results show that the THG signal has been enhanced.

In power system reliability analysis, state space pruning has been investigated to improve the efficiency of the conventional Monte Carlo Simulation (MCS). New algorithms have been proposed to prune the state space so as to make the Monte Carlo Simulation sample a residual state space with a higher density of failure states. This thesis presents a modified Genetic Algorithm (GA) as the state space pruning tool, with higher efficiency and a controllable stopping criterion as well as better parameter selection. This method is tested using the IEEE Reliability Test System (RTS 79 and MRTS), and is compared with the original GA-MCS method. The modified GA shows better efficiency than the previous methods, and it is easier to have its parameters selected. This thesis also presents a Dynamic Programming (DP) algorithm as an alternative state space pruning tool. This method is also tested with the IEEE Reliability Test System and it shows much better efficiency than using Monte Carlo Simulation alone.

Hydrocarbon use has been increasing and will continue to increase for the foreseeable future in even the most pessimistic energy scenarios. Over the past few decades, natural gas has become the major player and revenue source for many countries and multinationals. Its presence and power share will continue to grow in the world energy mix. Much of the current gas reserves are found in gas condensate reservoirs. When these reservoirs are allowed to deplete, the pressure drops below the dew point pressure and a liquid condensate will begin to form in the wellbore or near wellbore formation, possibly affecting production. A field optimization includes determining the number of wells, type (vertical, horizontal, multilateral, etc.), trajectory and location of wells. Optimum well placement has been studied extensively for oil reservoirs. However, well placement in gas condensate reservoirs has received little attention when compared to oil. In most cases involving a homogeneous gas reservoir, the optimum well location could be determined as the center of the reservoir, but when considering the complexity of a heterogeneous reservoir with initial compositional variation, the well placement dilemma does not produce such a simple result. In this research, a horizontal well placement problem is optimized by using a modified Genetic Algorithm. The algorithm presented has been modified specifically for gas condensate reservoirs. Unlike oil reservoirs, the cumulative production in gas reservoirs does not vary significantly (although the variation is not economically negligible) and there are possibly more local optimums. Therefore the possibility of finding better production scenarios in subsequent optimization steps is not much higher than the worse case scenarios, which delays finding the best production plan. The second modification is developed in order to find optimum well location in a reservoir with geological uncertainties. In this modification, for the first time, the probability of success of optimum production is defined by the user. These modifications magnify the small variations and produce a faster convergence while also giving the user the option to input the probability of success when compared to a Standard Genetic Algorithm.

It is well known that the biological function of a protein depends on its 3D structure. Therefore, solving the problem of protein structures is one of the most important works for studying proteins. However, protein structure prediction is a very challenging task because there is still no clear feature about how a protein folds to its 3D structure yet. In this thesis, we propose a genetic algorithm (GA) based on the lattice model to predict the 3D structure of an unknown protein, target protein, whose primary sequence and secondary structure elements (SSEs) are assumed known. Hydrophobic-hydrophilic model (HP model) is one of the most simplified and popular protein folding models. These models consider the hydrophobic-hydrophobic interactions of protein structures, but the results of prediction are still not encouraged enough. Therefore, we suggest that some other features should be considered, such as SSEs, charges, and disulfide bonds. That is, the fitness function of GA in our method considers not only how many hydrophobic-hydrophobic pairs there are, but also what kind of SSEs these amino acids belong to. The lattice model is in fact used to help us get a rough folding of the target protein, since we have no idea how they fold at the very beginning. We show that these additional features do improve the prediction accuracy by comparing our prediction results with their real structures with RMSD.

This thesis is based on the DSP to develop a facial expression recognition system. Most facial expression recognition systems suppose that human faces have been found, or the background colors are simple, or the facial feature points are extracted manually. Only few recognition systems are automatic and complete. This thesis is a complete facial expression system. Images are captured by CCD camera. DSP locates the human face, extracts the facial feature points and recognizes the facial expression automatically. The recognition system is divided into four sub-system: Image capture system, Genetic Algorithm human face location system, Facial feature points extraction system, Fuzzy logic facial expression recognition system. Image capture system is using CCD camera to capture the facial expression image which will be recognized in any background, and transmitting the image data to SRAM on DSP through the PPI interface on DSP. Human face location system is using genetic algorithm to find the human face¡¦s position in image by facial skin color and ellipse information, no matter what the size of the human face or the background is simple. Feature points extraction system is finding 16 facial feature points in located human face by many image process skills. Facial expression recognition system is analyzing facial action units by 16 feature points and making them fuzzily. Judging the four facial expression: happiness, anger, surprise and neutral, by fuzzy rule bases.. According to the results of the experiment. The facial expression system has nice performance on recognition rate and recognition speed.

DNA microarrays are widely used techniques in molecular biology and DNA computing area. Before performing the microarray experiment, a set of subsequences of DNA called probes which are complementary to the target genes of interest must be found. And its reliability seriously depends on the quality of the probe sequences. Therefore, one must carefully choose the probe set in target sequences. A new method for probe design strategy using multi-objective genetic algorithm is proposed. The proposed algorithm is able to find a set of suitable probes more efficient and uses a model based on suffix tree to speed up the specificity constraint checking. The dry dock experimental results show that the proposed algorithm finds several probes for DNA microarray that not only obey the design properties, but also have specificity.