Software maintainability prediction using hybrid neural network and fuzzy logic approach with parallel computing concept

Kumar, Lov; Rath, Santanu Kumar

doi:10.1007/s13198-017-0618-4

Cited by 27 publications

(10 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…a function of change was considered as a dependent variable. The Change was counted by comparing two consecutive versions of software whereas addition and deletion of code were counted as one changFe while updating of code was counted as two changes [3]. The proposed formula is defined in equation ( 1) and ( 2) whereas in equation ( 2) combination of static and dynamic metrics were used i.e.…”

Section: A Proposed Formulamentioning

confidence: 99%

“…Therefore, the neural network (NN) [2] approach provides adaptive learning capabilities to predict software maintainability, whereas fuzzy logic can generalize rules. To take advantage of both, we have proposed a neuro-fuzzy (NF) approach [3] to determine a class's maintainability effectively. Further, the authors also compared the proposed NN and NF model with four existing machine learning algorithms as described below.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Hybrid Maintainability Prediction using Soft Computing Techniques

Duhan¹,

Bhatia²

2021

IJC

View full text Add to dashboard Cite

Effective software maintenance is a crucial factor to measure that can be achieved with the help of software metrics. In this paper, authors derived a new approach for measuring the maintainability of software based on hybrid metrics that takes advantages of both i.e. static metrics and dynamic metrics in an object-oriented environment whereas, dynamic metrics capture the run time features of object-oriented languages i.e. run time polymorphism, dynamic binding etc. which is not covered by static metrics. To achieve this, the authors proposed a model based on static and hybrid metrics to measure maintainability factor by using soft computing techniques and it is found that the proposed neuro-fuzzy model was trained well and predict adequate results with MAE 0.003 and RMSE 0.009 based on hybrid metrics. Additionally, the proposed model was validated on two test datasets and it is concluded that the proposed model performed well, based on hybrid metrics.

show abstract

Section: A Proposed Formulamentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Hybrid Maintainability Prediction using Soft Computing Techniques

Duhan¹,

Bhatia²

2021

IJC

View full text Add to dashboard Cite

show abstract

“…Kumar and Rath [26] suggested an estimation model utilizing parallel computing and neuro-fuzzy approach. For verification the model gets implemented on 10 defined static codes revealing that the combination of both the approaches works well.…”

Section: Related Workmentioning

confidence: 99%

Mobile Phone Maintainability Prediction using MCDM Methodology

2019

IJRTE

View full text Add to dashboard Cite

For software engineering it is essential to build a software that is qualitative from every perspective. As the interest of the clients in mobile applications getting higher and higher day by day, the quality turns out to be a major concern. Ample number of researches shows issues with the maintenance of the applications once they are public. Different studies showed various evaluation methods for estimating maintainability but only few were defined for mobile applications. Also, none of the approaches propounded gives a specified way for evaluating maintainability of these portable applications. The present research work, examines the key idea of maintenance of apps considering 9 vital factors for the estimation of maintainability utilizing an MCDM approach to evaluate the identified factors.

show abstract

“…A number of studies have employed individual machine learning models to predict software maintainability based on historical data of OO systems on the QUES dataset specifically: Bayesian network [1]; Multivariate adaptive regression splines [2]; TreeNet [3]; Mamdani-based model [4]; Group Method of Data Handling model [5]; Artificial neural network and genetic algorithm [6]; Neuro-Genetic algorithm [7]; Hybrid neural network and fuzzy logic approach [8]. Furthermore, two research studies have investigated the application of ensemble models in software maintainability: Aljamaan et al [15] developed a heterogeneous ensemble model by selecting the best base model in training; and Elish et al [17] evolved their work by generalizing a heterogeneous ensemble to include averaging, weighted averaging and best base in training as well.…”

Section: Related Workmentioning

confidence: 99%

“…Utilization of individual machine learning models has been investigated in several studies to predict software maintainability [1][2][3][4][5][6][7][8]. Recently, ensemble models have been applied across a wide range of software engineering problem domains, such as fault prediction, to increase accuracy prediction over individual models [9].…”

Section: Introductionmentioning

confidence: 99%

Predicting Software Maintainability in Object-Oriented Systems Using Ensemble Techniques

Alsolai

2018

2018 IEEE International Conference on Software Maintenance and Evolution (ICSME)

View full text Add to dashboard Cite

Prediction of the maintainability of classes in object-oriented systems is a significant factor for software success, however it is a challenging task to achieve. To date, several machine learning models have been applied with variable results and no clear indication of which techniques are more appropriate. With the goal of achieving more consistent results, this paper presents the first set of results in an extensive empirical study designed to evaluate the capability of bagging models to increase accuracy prediction over individual models. The study compares two major machine learning based approaches for predicting software maintainability: individual models (regression tree, multilayer perceptron, knearest neighbors and m5rules), and an ensemble model (bagging) that are applied to the QUES data set. The results obtained from this study indicate that k-nearest neighbors model outperformed all other individual models. The bagging ensemble model improved accuracy prediction significantly over almost all individual models, and the bagging ensemble models with k-nearest neighbors as a base model achieved superior accurate prediction in both datasets. This paper also provides a description of the planned programme of research which aims to investigate the performance over various datasets of advanced (ensemble-based) machine learning models. Keywords-individual models, bagging ensemble model, software maintainability, prediction, Object-oriented systems.Fig. 1. Pred (.25) for each models apply on QUES dataset. Fig. 2. Box plot of MRE for models in QUES dataset.

show abstract

Software maintainability prediction using hybrid neural network and fuzzy logic approach with parallel computing concept

Cited by 27 publications

References 36 publications

Hybrid Maintainability Prediction using Soft Computing Techniques

Hybrid Maintainability Prediction using Soft Computing Techniques

Mobile Phone Maintainability Prediction using MCDM Methodology

Predicting Software Maintainability in Object-Oriented Systems Using Ensemble Techniques

Contact Info

Product

Resources

About