Papers by Keyword: BPN

Abstract: Modern encryption algorithms will focus on transforming rendered text block into a non-rendered block of symbols. The objective is to make the cipher block more non-interpretable. Distinguisher attack algorithm is used to distinguish cipher text from random permutation and other related algorithms. Currently, a cipher has been design to concentrate on distinguisher attack. In this research work, we have attempted to distinguish the cipher blocks of AES-128 (Advanced Encryption Standard) and AES-256 symmetric block cipher algorithms using an artificial neural network based classifier.

Abstract: In this paper, aim to salt and pepper noise, a new detect algorithm is proposed. GA-BPN algorithm uses Genetic Algorithm (GA) to decide weights in a Back Propagation neural Network (BPN)(GA-BPN).In this paper, we used Genetic Algorithm Back Propagation neural Network GA-BPN to do image noise detect work. Firstly, this paper uses training samples to train a GA-BPN as noise detector. Then, we utilize the well-trained GA-BPN to recognize noise pixels in target image. Experiment data shows that this algorithm has good performance.

Abstract: This study adopts popular back-propagation neural network to make one-period-ahead prediction of the stock price. A model based on Taylor series by using both fundamental and technical indicators EPS and MACD as input data is built for an empirical study. Leading Taiwanese companies in non-hi-tech industry such as Formosa Plastics, Yieh Phui Steel, Evergreen Marine, and Chang Hwa Bank are picked as targets to analyze their reasonable prices and moving trends. The performance of this model shows remarkable return and high accuracy in making long/short strategies.

Abstract: Artificial neural networks (ANNs) are one of the most recently explored advanced technologies which show promise in the factory monitoring area. This paper focuses on two particular network models, back-propagation network (BPN) and general regression neural network (GRNN). The prediction accuracy of these two models is evaluated using a practical application situation in a monitor factory. GRNN emerged as a variant of the artificial neural network. Its principal advantages are that it can quickly learn and rapidly converge to the optimal regression surface with large number of data sets. According the simulation results we can show that GRNN is an effective way to considerably improve the predictive ability of BPN.

Abstract: In this study, the back-propagation neural network technology (BPN) is utilized to identify the shape of the defective solder ball of ball grid array (BGA) so as to promote the accuracy of the optical inspection and measurement. The two dimensional BGA optical inspecting system is implemented by Visual Basic as the developing tool incorporated with the Halcon’s function which is the database of the image processing on Windows operation system. For the development of the processing procedure of the automatic optical inspecting system, the precise geometrical information of the solder ball is evaluated by the sub-pixel method to identify the shape of solder ball and its location which are acquired to classify the defects of solder ball including the ball offset, the ball over scale, the ball absence, and the ball shape under the BGA board is offset and rotated at any angle. From the experimental results, the back-propagation neural network technology is proved to properly identify and classify the shape defects, especially for the ball deformation and the ball bridging of the solder ball which can achieve and contribute the requirements for the automatic inspection and the high identification efficiency.