A two-layer scheme for membership and classification querying

ISSN： 0368-492X

Source： Kybernetes: The International Journal of Systems & Cybernetics, Vol.42, Iss.1, 2013-01, pp. : 82-93

Disclaimer: Any content in publications that violate the sovereignty, the constitution or regulations of the PRC is not accepted or approved by CNPIEC.

Previous Menu Next

Abstract

Purpose ‐ The purpose of this paper is to effectively deal with querying of classification with membership. Design/methodology/approach ‐ The authors propose a scheme comprising a layer of Bloom filter for membership checking and a second layer based on neural network for dealing with the classification requirement. Findings ‐ Not only could false positives be dramatically decreased, but also classification could be achieved with the proposed scheme. Research limitations/implications ‐ The experimental data were randomly generated instead of real-world ones. Practical implications ‐ It is difficult to implement this scheme in a real-world environment, such as the internet. Second, the neural network requires time to converge to a satisfactory level. Social implications ‐ Internet ethic might be compromised by hackers once they find a way around the filtering mechanism. Originality/value ‐ The neural network was moditified and utilized for the first time to be suitable for our purpose. Second, the two-layer design shows effectiveness.