• Journal of Internet Computing and Services
• /
• v.9 no.5
• /
• pp.85-97
• /
• 2008

Recently, service-oriented systems have been issued by their properties of reducing software development time and effort by reusing functional service units. The reusability of services can effectively promote through loose coupling between services and loose coupling between services depends on component-based system. That is, the component-based system is designed by grouping the tightly coupled classes of the object-oriented system and the service-oriented system is designed by the component-based system. Therefore, to design the component-based system and service-oriented system efficiently, a metric to measure the coupling between classes accurately needs. In this paper, we propose a coupling metric between classes applying a structural property, a dynamic property, and the normalized value by 0-1. We prove the theoretical soundness of the proposed metric by the axioms of briand et al, and suggest the accuracy and practicality through a case study. We suggest the evaluation results of the proposed metric through a comparison with the conventional metrics.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.10
• /
• pp.651-660
• /
• 2013

Object oriented design brought up improvement of productivity and software quality by adopting some concepts such as inheritance and encapsulation. However, both the number of software's classes and object couplings are increasing as the software volume is becoming larger. The object coupling between classes is closely related with software complexity, and high complexity causes decreasing software quality. In order to solve the object coupling issue, IT-field researchers adopt a component based development and software quality metrics. The component based development requires explicit representation of dependencies between classes and the software quality metrics evaluates quality of software. As part of the research, we intend to gain a basic data that will be used on decomposing software. We focused on properties of the linkage between classes rather than previous studies evaluated and accumulated the qualities of individual classes. Our method exploits machine learning technique to analyze the properties of linkage and predict the strength of dependency between classes, as a new perspective on analyzing software property.