Impact of Parameter Tuning for Optimizing Deep Neural Network Models for Predicting Software Faults

Mansi Gupta; Kumar Rajnish; Vandana Bhattacharjee

doi:10.1155/2021/6662932

journal article Open Access Jun 11, 2021

Impact of Parameter Tuning for Optimizing Deep Neural Network Models for Predicting Software Faults

Mansi Gupta

Kumar Rajnish

Vandana Bhattacharjee

Scientific Programming Vol. 2021 pp. 1-17 · Wiley

View at Publisher Save 10.1155/2021/6662932

Abstract

Deep neural network models built by the appropriate design decisions are crucial to obtain the desired classifier performance. This is especially desired when predicting fault proneness of software modules. When correctly identified, this could help in reducing the testing cost by directing the efforts more towards the modules identified to be fault prone. To be able to build an efficient deep neural network model, it is important that the parameters such as number of hidden layers, number of nodes in each layer, and training details such as learning rate and regularization methods be investigated in detail. The objective of this paper is to show the importance of hyperparameter tuning in developing efficient deep neural network models for predicting fault proneness of software modules and to compare the results with other machine learning algorithms. It is shown that the proposed model outperforms the other algorithms in most cases.

Topics

No keywords indexed for this article. Browse by subject →

References

43

[1]

X.-Y. Jing "Dictionary learning based software defect prediction"

[2]

M. Tan "Online defect prediction for imbalanced data"

[3]

A. G. Liu "Progressive reliability forecasting of service-oriented software"

[4]

S. S. Rathore "A decision tree logic based recommendation system to select software fault prediction techniques" Computing (2016) 10.1007/s00607-016-0489-6

[5]

10.3745/jips.2012.8.2.241

[6]

P. He "An empirical study on software defect prediction with a simplified metric set" Information and Software Technology (2015) 10.1016/j.infsof.2014.11.006

[7]

10.1016/j.advengsoft.2011.06.001

[8]

10.1142/s0219622011004282

[9]

10.1016/j.asoc.2014.11.023

[10]

10.5120/525-685

[11]

10.1109/tse.2012.20

[12]

J. Cahill "predicting fault-prone software modules with rank sum classification" 10.1109/aswec.2013.33

[13]

10.1016/j.asoc.2015.04.045

[14]

L. Kumar "Effective Fault Prediction model developed using least square Support vector machine (LSSVM)" Journal of Systems and Software (2018) 10.1016/j.jss.2017.04.016

[15]

10.14429/dsj.61.1088

[16]

10.1016/j.infsof.2017.11.005

[17]

S. Wang "Automatically learning semantic features for defect prediction" 10.1145/2884781.2884804

[18]

10.1016/j.asoc.2016.08.025

[19]

10.1016/j.ins.2018.02.027

[20]

M. Samir "Investigating the use of deep neural networks for software defect prediction" 10.1109/aiccsa47632.2019.9035240

[21]

10.1016/j.eswa.2018.12.033

[22]

J. Li "Software defect prediction via convolutional neural network"

[23]

10.1016/j.jestch.2019.10.005

[24]

10.3233/jifs-179677

[25]

10.3233/jifs-179619

[26]

10.1109/access.2019.2945858

[27]

10.1109/access.2017.2785445

[28]

10.1109/tkde.2011.163

[29]

10.1016/j.eswa.2019.113085

[30]

Applications of machine learning to machine fault diagnosis: A review and roadmap

Yaguo Lei, Bin Yang, Xinwei Jiang et al.

Mechanical Systems and Signal Processing 10.1016/j.ymssp.2019.106587

[31]

10.1049/cje.2020.05.016

[32]

10.1016/j.scient.2011.08.031

[33]

10.1016/j.ijleo.2018.07.044

[34]

On hyperparameter optimization of machine learning algorithms: Theory and practice

Li Yang, Abdallah Shami

Neurocomputing 2020 10.1016/j.neucom.2020.07.061

[35]

10.1109/access.2020.2981072

[36]

10.1007/978-1-4842-4240-7_5

[37]

10.3233/jifs-190033

[38]

10.1109/tr.2020.2996261

[39]

C. Manjula "Software defect prediction using deep belief network with L1-regularization based optimization" International Journal of Advanced Research in Computer Science (2018) 10.26483/ijarcs.v9i1.5476

[40]

Y. Qu "Impact of hyper parameter optimization for cross-project software defect prediction" International Journal of Performability Engineering (2018)

[41]

P. K. Kudjo "The significant effect of parameter tuning on software vulnerability prediction models"

[42]

A. Ng (2019)

[43]

Metrics

16

Citations

43

References

Details

Published: Jun 11, 2021
Vol/Issue: 2021
Pages: 1-17
License: View

Authors

M

Mansi Gupta

Department of Computer Science and Engineering, BIT Mesra, Ranchi, India

K

Kumar Rajnish

Department of Computer Science and Engineering, BIT Mesra, Ranchi, India

V

Vandana Bhattacharjee

Department of Computer Science and Engineering, BIT Mesra, Ranchi, India

Cite This Article

Mansi Gupta, Kumar Rajnish, Vandana Bhattacharjee (2021). Impact of Parameter Tuning for Optimizing Deep Neural Network Models for Predicting Software Faults. Scientific Programming, 2021, 1-17. https://doi.org/10.1155/2021/6662932

Impact of Parameter Tuning for Optimizing Deep Neural Network Models for Predicting Software Faults

You May Also Like