|Title:||Real-coded genetic algorithm based variable feed-forward neural networks and their applications|
|Subject:||Hong Kong Polytechnic University -- Dissertations.|
Neural networks (Computer science)
Evolutionary programming (Computer science)
|Department:||Department of Electronic and Information Engineering|
|Pages:||xxxiii, 261 leaves : ill. ; 31 cm.|
|Abstract:||This thesis focuses on the real-coded genetic algorithm and different topologies of feed-forward neural networks. Results in the following areas will be reported: (1) a real-coded genetic algorithm with new crossover and mutation operations, and its applications; (2) three different topologies of variable feed-forward neural networks, and their applications to short-term electric load forecasting in Hong Kong and hand-written graffiti recognition. The real-coded genetic algorithm (RCGA) is one evolutionary computation technique that can tackle complex optimization problems. In this thesis, RCGA with new genetic operations called the average-bound crossover (ABX) and wavelet mutation (WM) will be presented. On realizing the ABX operation, the offspring spreads over the domain so that a higher chance of reaching the global optimum can be obtained. Taking advantage of the wavelet theory, the performance of the mutation operation in terms of the cost function value, solution stability (standard deviation of solutions) and convergence rate is improved. A suite of benchmark test functions are used to evaluate the performance of the proposed algorithm. Also, the sensitivity of the parameters in WM and the sensitivity of the genes' initial range to the searching performance of the proposed RCGA will be discussed. Application examples on economic load dispatch and tuning the parameters of neural networks are used to show the merits of the proposed RCGA. The three proposed topologies of variable feed-forward network networks are: (1) the variable-structure neural network (VSNN), (2) the variable-parameter neural network (VPNN), and (3) the variable-node-to-node-link neural network (VN2NN). By taking advantage of these networks' structures, the learning and generalization abilities of the networks can be increased. All the network parameters are tuned by the proposed RCGA with ABX and WM. The proposed VSNN consists of a neural network with link switches (NNLS) and a network switch controller (NSC). In the NNLS, switches are introduced in the links between the hidden and output layers. By using the NSC to control the on-off states of the switches in the NNLS, the proposed neural network can model different input patterns with different network structures. In other words, it operates with a variable structure to handle different sets of input patterns. Consequently, the VSNN offers better results and an enhanced learning ability. In the proposed VPNN, the parameters will adaptively tackle different sets of input data sparsely located in a large domain. Each input data set is effectively handled by its corresponding set of network parameters. The network operates as if there is a corresponding neural network for each set of input data. This makes the VPNN exhibit a better learning and generalization ability than the traditional neural networks. In the proposed VN2NN, the parameters of the activation functions in the hidden layer change with respect to the network inputs. Node-to-node links are introduced in the hidden layer and the forms of the links are tuned by the RCGA. The introduction of the node-to-node links increases the degree of freedom of the network's modelling ability, enabling the network to provide better learning and generalization abilities. Application examples on short-term electric load forecasting and hand-written graffiti recognition are given to illustrate the merits of the proposed neural networks. Short-term electric load forecasting is important to power systems for their economic, reliable and secure operation. The nonlinearities and large-scale characteristics of the problem require a well-designed neural network to tackle it. Hand-written graffiti recognition is another problem demanding the superior learning and generalization abilities of the proposed neural networks to do classifications with respect to a large number of input data sets. Based on the results from the two application examples, the performance characteristics of the three proposed networks will be investigated and explained. Comparisons among the networks will be conducted in order to let the user have an idea on how to choose which network to use for different kinds of problems.|
|Rights:||All rights reserved|
Files in This Item:
|b20938822.pdf||For All Users||28.76 MB||Adobe PDF||View/Open|
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
- I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.
Please use this identifier to cite or link to this item: