期刊名称：International Journal of Universal Computer Sciences
印刷版ISSN：1737-9296
电子版ISSN：1737-930X
出版年度：2010
卷号：1
期号：1
页码：19-33
出版社：HyperSciences Publisher
摘要：In this article, an effective approach for measuring the usability of business network is introduced. The usability process for networking provides us with a flexible and a cost-effective way to assess the usability of a network and its products. In addition, the proposed approach can be used to certify network product usability in cycle development. Furthermore, it can be used to help in developing usable interfaces very early in the cycle and to give a way to measure, track, and improve usability. Moreover, a new approach for fast information processing over larger computer networks than those discussed in the previous work is presented. The work in literature have shown that focused time delay neural networks gives good results as well as reduces the amount of the required memory space for information processing. Here, such networks are accelerated to deal efficiently with real-time applications. The proposed fast focused time delay neural networks (FFTDNNs) relies on applying cross correlation in the frequency domain between the input data and the weights of the first layer. It is proved mathematically and practically that the number of computation steps required for the presented FFTDNNs is less than that needed by conventional time delay neural networks (CTDNNs) for information processing. Simulation results using MATLAB confirm the theoretical computations.
关键词：Usability Criteria; Large Computer Networks; FFTDNNs; Cross Correlation; Frequency Domain
