A self-processing network model for relational databases

Eldad De-Medonsa, Sarit Kraus, Yosi Shiftan

Research output: Contribution to journalArticlepeer-review

1 Scopus citations


In this paper, a model which combines relational databases with self-processing networks is proposed in order to improve the performance of very large databases. The proposed model uses an approach which is radically different from all other distributed database models, where each computer processes a portion of the database. In the self-processing network model, the network structure which consists of nodes and connections, captures the data and the relationships by assigning them unique, connected control, and data nodes. The network activity is the mechanism that performs the relational algebra operations. No data transmission is needed, and since data nodes are common to all the relations, integrity and elimination of data redundancy are achieved. An extension of the model, by interconnecting the data nodes via weighted links, provides us with properties that are embedded in neural networks, such as fuzziness and learning.

Original languageEnglish
Pages (from-to)198-225
Number of pages28
JournalIEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Issue number2
StatePublished - 1999


  • Relational databases
  • Self-processing network


Dive into the research topics of 'A self-processing network model for relational databases'. Together they form a unique fingerprint.

Cite this