Svs: Prediction Framework for Software Quality Enhancement through Data Mining Techniques
A.R.Visagan1, M.Sumathi2, G.Sujatha3
1A.R.Visagan*, Department of Computer Science, Madurai Kamraj Universty College, Madurai, India.
2Dr.M.Sumathi, Department of Computer Science, Sri Meenakshi Government Arts College for Women, Madurai, India.
3Dr, G,Sujatha, Department of Computer Science, Sri Meenakshi Government Arts College for Women, Madurai, India.
Manuscript received on November 25, 2019. | Revised Manuscript received on December 22, 2019. | Manuscript published on December 30, 2019. | PP:284-291 | Volume-9 Issue-2, December, 2019. | Retrieval Number: B3008129219/2019©BEIESP | DOI: 10.35940/ijeat.B3008.129219
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: Software Engineering has its origins in tackling the issue of development and maintenance of quality software. Software Quality has been defined in multiple ways but the broadest definition is that quality is the extent to which the customer is satisfied with the developed software. Data mining has the prospects of being applied to multiple domains and addressing the long standing issues faced by them. It has been successfully applied to uncover solutions to complex problems that have long confronted these domains. The proposed research is a step in the direction. It will attempt to apply existing data mining algorithms to data accumulated by software organizations in an attempt to extract useful patterns that can go a long way in addressing the issue of software quality. This work proposed Spacious Virtue Suggestion (SVS) Model for analyzing code based quality in software quality model. The first layer of this model is Extraction Layer that extracts the various attributes of software code used. After the extraction of the metrics attributes are constructed as a vector is considered as the feature vector for the second layer of the SVS Model. The second layer of the SVS model is Selection Layer which employs feature selection strategy to obtain significant metrics attributes for the software quality prediction by reducing the overlapping metrics attributes from the vector… The third layer of SVS Model is Prediction Layer which predict the good class from the training set and result shows the high accuracy in the proposed system.
Keywords: Software Engineering, Software Quality Evaluation, Software Code Metrics, Spacious Virtue Suggestion, SVS Model, Artificial Intelligence, Metrics Selection, Machine Learning.