To overcome the defect that K2 algorithm requires the suitable order of nodes in advance while dealing with the structure learning of Bayesian Network Classifier (BNC), the algorithm GA-K2 is proposed which introduces the integer coding genetic algorithm based on selective ensemble concept to K2. It provides the guarantee of getting the best order of nodes and the convergence of Bayesian network structure for K2 in global optimization.
By concretely integrating various algorithms and numerically testing to typic optimization problems sample, we see that being a class of valid integrated intelligent optimization algorithms, the IMHGNIOA can high efficiently get global optimization solutions and this integration method in the dissertation is accurate.
In the HGA+BP hybrid optimization strategy, BP operation is introduced into HGA algorithm. So it makes full use of the global optimization of GA to search the possible extremum area in a large scope and it uses BP to fast search near the extremum point. At the same time, the structure of network can be optimized because of hierarchical coding.
In the application,the global optimum solution can be obtained and the fine plant classification can be implemented without any prior information when the proposed algorithm is applied to the push-broom hyperspectral technique imager(PHI) data.
The support vector machines, which characterizes a simple model structure, good generalization, global optimal solution etc. , has been applied in the intelligent control. The current research includes SVMR modeling and prediction of nonlinear times serial, system identification, optimal control, learning control, predict control etc.
In order to enhance the global optimal search ability of AIA in solving multi-modal function optimization problem, based on mechanism of immune theory and genetic algorithm, a function "stretching" technique is introduced to obtain stretching immune genetic algorithm (SIGA).
Globally Optimal Weighted Measurement Fusion White Noise Deconvolution Estimator for Time-varying Systems
An optimization algorithm based on genetic algorithm for parameters of synergetic neural network was proposed, which searched the optimal solutions in the parameters space of synergetic neural network using the globally optimal searching ability of genetic algorithm.
Assuming that each sensor has the same measurenment matrix,compared with the centralized measurement fusion method,the weighted measurement fusion method not only it give the globally optimal estimation, but also it can obviously reduce the computational burden, so that it is suitable for real time applications.
Compared with the centralized measurement fusion method, by the weighted measurement fusion method, not only the globally optimal estimation can be obtained, but also the computational burden can obviously be reduced and it is suitable for real time applications.
Experimental results have shown that a global optimal solution can be quickly obtained using the proposed method and the precision requirement for target location is satisfied.
In addition, considering the non-convex and non-concave nature of the sub-problem of combinational optimization, the branch-and-bound technique was adopted to obtain or approximate a global optimal solution.
To speed up the search process and guarantee a global optimal result, the extended compact genetic algorithm (ECGA) is used to carry out the search process.
These schemes are based on a unified theoretical base-sufficient conditions for the global optimal known in optimal control theory.
2D and 3D ASMs are combined to obtain a "global optimal" segmentation of the 3D object embedded in the data set, rather than the "locally optimal" segmentation on separate slices.