Name
Abstract | ||
|---|---|---|
Since 1982, numerous Byzantine Agreement Protocols (BAPs) have been developed to solve arbitrary faults in the Byzantine Generals Problem (BGP). A novel BAP, using an artificial neural network (ANN), was proposed by Wang and Kao. It requires message exchange rounds similar to the traditional BAP and its suitability, in the context of network size, has not been investigated. In the present study, we propose to adopt Nguyen-Widrow initialization in ANN training, which modifies message communication and limits the message exchange rounds to three rounds. This modified approach is referred to as BAP-ANN. The BAP-ANN performs better than the traditional BAP, when the network size n is greater than nine. We also evaluate the message exchange matrix (MEM) constructed during the message exchange stage. For a fixed number of faulty nodes and remainder cases of (n mod 3), the study shows that the mean epoch for ANN training decreases as the network size increases, which indicates better fault tolerance. |
Year | DOI | Venue |
|---|---|---|
2007 | 10.1016/j.ins.2007.04.011 | Inf. Sci. |
Keywords | Field | DocType |
communication protocol,byzantine agreement,network size n,cryptology,message exchange matrix,message exchange stage,traditional bap,artificial neural network,performance study,network size increase,message communication,network size,artificial neural networks,byzantine agreement protocol,message exchange round,ann training,fault tolerance,fault tolerant | Computer science,Cryptography,Byzantine fault tolerance,Algorithm,Fault tolerance,Artificial intelligence,Initialization,Quantum Byzantine agreement,Artificial neural network,Exchange matrix,Machine learning,Communications protocol | Journal |
Volume | Issue | ISSN |
177 | 21 | 0020-0255 |
Citations | PageRank | References |
4 | 0.52 | 31 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Kok-Wah Lee | 1 | 4 | 0.52 |
| Hong-Tat Ewe | 2 | 28 | 6.12 |