Please use this identifier to cite or link to this item:
|Title:||Inferring class level specifications for distributed systems||Authors:||Kumar, S.
|Issue Date:||2012||Citation:||Kumar, S.,Khoo, S.-C.,Roychoudhury, A.,Lo, D. (2012). Inferring class level specifications for distributed systems. Proceedings - International Conference on Software Engineering : 914-924. ScholarBank@NUS Repository. https://doi.org/10.1109/ICSE.2012.6227128||Abstract:||Distributed systems often contain many behaviorally similar processes, which are conveniently grouped into classes. In system modeling, it is common to specify such systems by describing the class level behavior, instead of object level behavior. While there have been techniques that mine specifications of such distributed systems from their execution traces, these methods only mine object-level specifications involving concrete process objects. This leads to specifications which are large, hard to comprehend, and sensitive to simple changes in the system (such as the number of objects). In this paper, we develop a class level specification mining framework for distributed systems. A specification that describes interaction snippets between various processes in a distributed system forms a natural and intuitive way to document their behavior. Our mining method groups together such interactions between behaviorally similar processes, and presents a mined specification involving "symbolic" Message Sequence Charts. Our experiments indicate that our mined symbolic specifications are significantly smaller than mined concrete specifications, while at the same time achieving better precision and recall. © 2012 IEEE.||Source Title:||Proceedings - International Conference on Software Engineering||URI:||http://scholarbank.nus.edu.sg/handle/10635/41462||ISBN:||9781467310673||ISSN:||02705257||DOI:||10.1109/ICSE.2012.6227128|
|Appears in Collections:||Staff Publications|
Show full item record
Files in This Item:
There are no files associated with this item.
checked on Feb 15, 2020
checked on Feb 19, 2020
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.