A Software Execution Data Component Identification Algorithm Based on Spectral Clustering

In order to understand the architecture of software system and facilitate the future maintenance of the software, we can reconstruct the software system as a component-based software system. To obtain the component information of the software, it is necessary to identify components based on the information contained in the software execution data. This paper presents a Software Execution data component identification algorithm based on Spectral Clustering (SESC). The input of the algorithm is the software execution event log, and the output is an evaluation report on the quality of the identified components, yielding the log of software execution events with component information. By using four software execution event logs, we compare the proposed SESC with five component identification algorithms based on the community detection algorithm. SESC takes the number of calls between classes into consideration, so it can identify components more accurately, and has certain advantages in time performance.