Automatic Classification of UML Class Diagrams Using Deep Learning Technique: Convolutional Neural Network

Abstract

Unified Modeling Language (UML) includes various types of diagrams that help to study, analyze, document, design, or develop any software efficiently. Therefore, UML diagrams are of great advantage for researchers, software developers, and academicians. Class diagrams are the most widely used UML diagrams for this purpose. Despite its recognition as a standard modeling language for Object-Oriented software, it is difficult to learn. Although there exist repositories that aids the users with the collection of UML diagrams, there is still much more to explore and develop in this domain. The objective of our research was to develop a tool that can automatically classify the images as UML class diagrams and non-UML class diagrams. Earlier research used Machine Learning techniques for classifying class diagrams. Thus, they are required to identify image features and investigate the impact of these features on the UML class diagrams classification problem. We developed a new approach for automatically classifying class diagrams using the approach of Convolutional Neural Network under the domain of Deep Learning. We have applied the code on Convolutional Neural Networks with and without the Regularization technique. Our tool receives JPEG/PNG/GIF/TIFF images as input and predicts whether it is a UML class diagram image or not. There is no need to tag images of class diagrams as UML class diagrams in our dataset.

Design of a web-based information system for domestic sea transportation services for limited liability company goods

“…This research uses a design with the Unified Modeling Language (UML) and a waterfall model development method (Abdelnabi et al, 2021;Gosala et al, 2021). UML is an image-based language that visualizes, specifies, builds, and documents object-based software development systems (Khan et al, 2019).…”

NEURAL-UML: Intelligent Recognition System of Structural Elements in UML Class Diagram

“…The authors justify the poor performance of their system by the lack of training data. To overcome the lack of training data, Gosala et al [11] uses transfer learning and artificial data augmentation techniques. Although these recent techniques have been shown to be effective for class diagram classification, it remains to be proven for more complex tasks such as semantic analysis of a diagram.…”

“…In this case, a normalization step is applied to resize the images. In some works, as proposed by Gosala et al [11], the image sizing parameter plays a significant role in model performance. This step is empirical and computationally time-consuming.…”

Rancang Bangun Aplikasi Layanan Ujian Berbasis Komputer di Portal Akademik Perguruan Tinggi

“…Unified Modeling Language (UML) adalah bahasa pemodelan yang dikembangkan untuk menyederhanakan proses desain perangkat lunak [18]. UML mencakup beberapa jenis diagram seperti use case diagram dan activity diagram.…”