File(s) not publicly available
A neural system for digital data processing
journal contributionposted on 06.12.2017, 00:00 by Wanwu Guo, A Watson
In data processing it is common to have many data files resulted from using various operations on a given original data file for different purposes. Since each operation has its own algorithm and is designed for carrying out a specific task, each resultant data file will need an independent presentation. If we need to present the features processed by multiple operations into one presentation so that the relationships among the processed features in different files can be revealed, a new system that is capable of not only managing all the resultant data files, but also carrying out some manipulations on these data files is required. In this paper, we propose a neural network-based system that can not only coordinate all the results from traditional processing, but also integrate different data files into one presentation. The general structure of this neural system is described firstly, and then three examples are used to test the usefulness of this system. The results show that this neural system is adaptive and meets the needs of managing and manipulating digital data for different purposes.