Abstract
In this paper, we propose a method to design of a neural network (NN) by using a genetic algorithm (GA) and simulated annealing (SA). And also, in order to demonstrate the effectiveness of the proposed scheme, we apply the proposed scheme to a coin recognition example.
In general, as a problem becomes complex and large-scale, the number of operations increase and hardware implementation to real systems (coin recognition machines) using NNs becomes difficult. Therefore, we propose the method which makes a small-sized NN system to achieve a cost reduction and to simplify hardware implementation to the real machines.
The coin images used in this paper were taken by a relatively cheap scanner (scanning 12mm in width). Then they are not complete, but a part of the coin image could be used in computer simulations. This is the reason why the width of coin images is limited. If the conventional scheme was used for this image, it would have low recognition accuracy. Therefore, in order to obtain high recognition accuracy, we propose a new scheme.
Input signals, which are Fourier spectra, are learned by a three-layered NN. The inputs to NN are selected by using GA with SA to make a small-sized NN. Simulation results show that the proposed scheme is effective to find a small number of input signals for coin recognition.
