Software Error Indication using Artificial Neural Network and Strong Back Propagation
N. Priya1, P. Nandhini2, D. Jeya Priya3, Nikita sharma4
1N. Priya, Department of CSE, Bharath Institute of Higher Education and Research, Chennai, Tamilnadu, India.
2P. Nandhini Department of CSE, Bharath Institute of Higher Education and Research, Chennai, Tamilnadu, India.
3D. Jeypriya, Department of CSE, Bharath Institute of Higher Education and Research, Chennai, Tamilnadu, India.
4Nikita Sharma, Student,Department of CSE, Bharath Institute of Higher Education and Research, Chennai, Tamilnadu, India.
Manuscript received on 05 July 2019 | Revised Manuscript received on 18 July 2019 | Manuscript Published on 23 August 2019 | PP: 875-878 | Volume-8 Issue-9S3 August 2019 | Retrieval Number: I31850789S319/2019©BEIESP | DOI: 10.35940/ijitee.K1133.09811S19
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© 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 designing field contains different methodologies identified with expectation, for example, test exertion forecast, redress cost expectation, blame expectation and so on. Among these product blame expectation is the most mainstream look into zone and numerous new tasks are begun around there. At the point when there is a mistake in the PC program, it delivers an invalid or false outcome. Henceforth expectation of inadequate modules is important to improve the product quality. Different techniques and metric sets are accessible to discover the false modules that are blunder inclined. In this, Artificial Neural Network based programming flaw forecast method is utilized. To discover assessed answers for improvement and inquiry issues this technique is utilized. Manufactured Neural Network is utilized for finding the flawed components and additionally to predict the mistaken modules
Keywords: ANN. Network, modelling
Scope of the Article: Network Architectures