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

Bethany Gosala,Sripriya Roy Chowdhuri,Alok Mishra,Manjari Gupta,Jyoti Singh

doi:10.3390/app11094267

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.

Highlights

Software development is done in a step-wise manner which can be understood as well-defined stages which we call as Software Development Life Cycle (SDLC)
RQ1: For our first RQ, we can answer in this way: Deep Learning methods allow us to have a greater number of features, filters, and parameters that can yield the best and most accurate results
By using Convolutional Neural Networks, we can have a variety of parameters that helps us to improve the accuracy, increasing the number of hidden layers, using different types of optimizers, and varying the learning rate all the factors contributes to the accuracy

Summary

Introduction

Software development is done in a step-wise manner which can be understood as well-defined stages which we call as Software Development Life Cycle (SDLC). A software cycle deals with various parts and phases from planning to testing and deploying software All these activities are carried out in different ways, as per the needs. Each way is known as a Software Development Life Cycle Model (SDLC) [1]. This helps the developer to manage and control the phases of development of a particular project. UML defines different types of diagrams in the form of graphs that represent objects, classes, states, etc., with various forms such as rectangle, ellipse, etc., and some defined notations They contain some texts, labeled arcs, and arrowheads. UML diagrams can model the different software engineering models such as structural, behavioral, or design models These models help the researchers or developers to understand the system properly. Simple drawing tools or fully developed computerassisted software engineering (CASE) tools can be used to produce UML diagrams, there are several means

Objectives

Methods

Results

Discussion

Conclusion