Abstract:
This paper presents the application of neural networks
in software maintainability estimation using objectoriented metrics. Maintenance effort can be measured as
the number of lines changed per class. In this paper, the
number of lines changed per class (modification volume)
is predicted using Ward neural network and General
Regression neural network (GRNN). Object-oriented
design metrics concerning with inheritance related
measures, complexity measures, cohesion measures,
coupling measures and size measures are applied in this
study. Principal components, which are derived from
these object-oriented metrics, are used as independent
variables.