Automated Software Design Reusability using a Unique Machine Learning Technique
P. Mangayarkarasi
Dr. P. Mangayarkarasi, Associate Professor, Department of Information Science and Engineering, New Horizon College of Engineering, Bangalore, India.
Manuscript received on February 10, 2020. | Revised Manuscript received on February 24, 2020. | Manuscript published on March 10, 2020. | PP: 1825-1828 | Volume-9 Issue-5, March 2020. | Retrieval Number: E3010039520/2020©BEIESP | DOI: 10.35940/ijitee.E3010.039520
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: The era of machine learning (ML) has brought significant advancement into the traditional approaches of software development and services. Software reusability and design automation is a key requirement that can be handled through the integration of artificial intelligence (AI) capabilities with the traditional approach of software development lifecycle (SDLC) practices. The study introduces a novel approach of ML, which can assist inappropriate selection of reusable software components, which in the long run, can optimize the operational cost in the context of development practices and also speed up the service delivery performance of software engineering activities. The proposed model is validated through a numerical analysis that shows the effectiveness of the system in terms of both classification accuracy and computational efficiency.
Keywords: Machine Learning, Software Reusability, Supervised Learning Model, Computational Complexity.
Scope of the Article: Machine Learning