Research Papers - Dept of Software Engineering

Permanent URI for this collectionhttps://rda.sliit.lk/handle/123456789/1022

Browse

Filters

2015 - 20172

Advanced Search

Filter by

Settings

Subject: search.filters.subject.complexity measure

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    PublicationEmbargo
    Limitations of an object-oriented metric: Weighted complexity measure
    (IEEE, 2015-09-23) De Silva, D. I; Kodagoda, N; Kodituwakku, S. R; Pinidiyaarachchi, A. J
    Many computer science practitioners and software developers believes that the complexity of a program could be controlled more effectively by using object-oriented programming concepts. In addition to controlling complexity, the object-oriented approach allows faster development, reduction in costs, higher quality, easier maintenance, increased scalability, better information structures, and increased adaptability. As such, more and more programs are written using the object-oriented programming approach rather than using the traditional functional approach. This demand has spurred the provision for a number of object-oriented metrics. Out of them, Chidamber and Kemerers' metrics suite is one of the most prominent object-oriented metrics that has been proposed. It has been widely validated and has been accepted as a useful predictor of object-oriented design complexity. But it does not consider the complexities that occur due to factors such as the nesting level and type of control structures, and the size of the program. Thus, Chhillar and Bhasins' introduced the weighted complexity measure to address these issues. It is the only metric which considers the complexities that occur due to inheritance level of statements, nesting level and type of control structures, and the size of the program. However, weighted complexity measure also has some limitations. This paper attempts to draw the readers' attention to those limitations, with the hope that it will be further improved by addressing them.
  • Thumbnail Image
    PublicationEmbargo
    Analysis and enhancements of a cognitive based complexity measure
    (IEEE, 2017-06-25) De Silva, D. I; Kodagoda, N; Kodituwakku, S. R; Pinidiyaarachchi, A. J
    As stated by Tom DeMacro, something that cannot be measured is uncontrollable. Thus, a number of metrics have been developed to measure the complexity associated with software by considering various aspects such as size, control flow and data flow between modules, cognitive informatics etc. Amongst these aspects, cognitive informatics is recognized as a promising aspect in measuring software complexity. Thus, majority of the complexity metrics that were proposed after the introduction of cognitive informatics have been proposed mainly based on the cognitive aspect. Amongst them, Chhillar and Bhasins' weighted composite complexity measure is one of the few metrics that had attempted to measure the complexity of a program by considering more than three or more complexity factors. After a thorough analysis, in a previous study, the authors identified that the weighted composite complexity measure could be further improved by considering more complexity factors. This paper extends the previous study to identify the most appropriate factors that could be considered by the weighted composite complexity measure. Using the opinions of the industry experts, the authors were able to discover that compound conditional statements, threads and recursion could also be considered by the weighted composite complexity measure. Accordingly, the weighted composite complexity measure was enhanced to capture the complexities that arise due to those factors. The paper also includes a demonstration of the complexity calculation method of the improved weighted composite complexity measure with the use of three sample java programs, which were written by incorporating the above mentioned factors. In addition, an application of the weighted composite complexity measure to the same programs are also given in the paper, to illustrate the changes in complexity values of the two measures.