Fault detection through sequential filtering of novelty patterns

John Cuzzola, Dragan Gašević, Ebrahim Bagheri

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

1 Citation (Scopus)


Multi-threaded applications are commonplace in today's software landscape. Pushing the boundaries of concurrency and parallelism, programmers are maximizing performance demanded by stakeholders. However, multi-threaded programs are challenging to test and debug. Prone to their own set of unique faults, such as race conditions, testers need to turn to automated validation tools for assistance. This paper's main contribution is a new algorithm called multi-stage novelty filtering (MSNF) that can aid in the discovery of software faults. MSNF stresses minimal configuration, no domain specific data preprocessing or software metrics. The MSNF approach is based on a multi-layered support vector machine scheme. After experimentation with the MSNF algorithm, we observed promising results in terms of precision. However, MSNF relies on multiple iterations (i.e., stages). Here, we propose four different strategies for estimating the number of the requested stages.

Original languageEnglish
Title of host publicationProceedings - 10th International Conference on Machine Learning and Applications, ICMLA 2011
Number of pages6
Publication statusPublished - 1 Dec 2011
Externally publishedYes
EventInternational Conference on Machine Learning and Applications 2011 - Honolulu, United States of America
Duration: 18 Dec 201121 Dec 2011
Conference number: 10th


ConferenceInternational Conference on Machine Learning and Applications 2011
Abbreviated titleICMLA 2011
Country/TerritoryUnited States of America
Internet address


  • back-box testing
  • fault detection
  • machine learning
  • software testing
  • unsupervised support vector machines

Cite this