Detecting the Most Important Classes from Software Systems with Self Organizing Maps

Detecting the Most Important Classes from Software Systems with Self Organizing Maps

Self Organizing Maps (SOM) are unsupervised neural networks suited for visualisation purposes and clustering analysis. This study uses SOM to solve a software engineering problem: detecting the most important (key) classes from software projects. Key classes are meant to link the most valuable conc...

Full description

Bibliographic Details
Main Author: Elena-Manuela MANOLE
Format: Article
Language:English
Published: Babes-Bolyai University, Cluj-Napoca 2021-07-01
Series:Studia Universitatis Babes-Bolyai: Series Informatica
Subjects:
self organizing maps, artificial neural networks, machine learning, classification algorithms, search based software engineering, software visualisation, key class detection, condensing class diagrams
Online Access:http://193.231.18.162/index.php/subbinformatica/article/view/1173

Similar Items

Similar Items