Title :
Bayesian Network Based Software Diagnosis Expert System
Author_Institution :
Sch. of Reliability & Syst. Eng., Beihang Univ., Beijing, China
Abstract :
Through the demonstrated external phenomenon or some input data, most software failures can be analyzed to help the in-depth understanding and backtracking the root source of the fault. Base on bayesian network, we designed a fault analysis expert system, which can realize the collection of fault case, strcture learning and parameter learning of the diagnosis network. This diagnosis expert system can analysis the possible fault cause and fault module, and output the dynamic diagnosis strategy given the inputs of fault phenomenon. And finally it can be achieved the multi-perspective shallow reasoning, deep-level reasoning and dynamic fault reasoning.
Keywords :
belief networks; expert systems; fault diagnosis; program diagnostics; Bayesian network based software diagnosis expert system; deep level reasoning; dynamic fault reasoning; fault analysis expert system; input data; multiperspective shallow reasoning; network diagnosis; parameter learning; software failures; Bayesian methods; Engines; Expert systems; Fault diagnosis; Knowledge engineering; Libraries; Software; Bayesian network; expert system; fault diagnosis;
Conference_Titel :
Intelligent System Design and Engineering Application (ISDEA), 2012 Second International Conference on
Conference_Location :
Sanya, Hainan
Print_ISBN :
978-1-4577-2120-5
DOI :
10.1109/ISdea.2012.533