Retracted: Scientific programming using optimized machine learning techniques for software fault prediction to improve software quality

Shafiq, M. Zubair; Alghamedy, Fatemah; Jamal, Nasir; Kamal, Tahir; Daradkeh, Yousef Ibrahim; Shabaz, Mohammad

doi:10.1049/sfw2.12091

Cited by 15 publications

(9 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this paper, other classifiers are used to show the effectiveness of our proposed method. These classifiers are the K‐Nearest neighbor (KNN) [50], the probabilistic neural network (PNN) [51], and the Naïve Bayes (NB) [52] and the acquired results are shown in Tables 16 and 17. As can be seen from Table 16, our proposed method has better results than other classifiers.…”

Section: Results Of the Identification Of The Harmonic Sourcementioning

confidence: 99%

Multiple harmonic sources identification including inverter‐based distributed generations using empirical Fourier decomposition

Motlagh

Foroud

2023

IET Generation Trans & Dist

View full text Add to dashboard Cite

This paper proposes an intelligent approach based on the empirical Fourier decomposition (EFD) to identify harmonic sources at the point of common coupling (PCC) when different inverter-based distributed generations (DGs) like microturbine (MT), battery energy storage system (BESS), photovoltaic (PV), superconducting magnetic energy storage (SMES), wind turbine with a permanent magnet synchronous generator (PMSG), and doubly-fed induction generator (DFIG) wind turbine are presented. In order to decrease memory storage and computational burden, strife feature selection is used. Applying just voltage signals consumes less processing time and decreases measurement devices. Moreover, the whale optimization algorithm (WOA) as the optimizer of the parameters of the support vector machine (SVM) classifier is used. Consequently, the results from the proposed method can be helpful for both engineers and researchers to plan and develop a better strategy to mitigate harmonic distortion.

show abstract

Section: Results Of the Identification Of The Harmonic Sourcementioning

confidence: 99%

Multiple harmonic sources identification including inverter‐based distributed generations using empirical Fourier decomposition

Motlagh

Foroud

2023

IET Generation Trans & Dist

View full text Add to dashboard Cite

show abstract

“…Table 1 encapsulates a summary of previous research endeavors pertaining to SDP applied in open-source projects. [5] introduced the ACO-SVM model, which amalgamates the Ant Colony Optimization (ACO) technique with the Support Vector Machine (SVM) model. ACO serves as an optimization technique for feature selection.…”

Section: Software Defect Prediction Applied In Open-source Projectsmentioning

confidence: 99%

“…Quality management and testing expenditures aimed at guaranteeing reliability constitute a substantial portion of overall software development costs. The expense is escalating exponentially to rectify software defects in the later stages of development [5]. Hence, utilizing available resources and minimize defects at the initial phase of a software development are crucial to obtaining high-quality outcomes [6].…”

Section: Introductionmentioning

confidence: 99%

ML Based Software Defect Prediction in Embedded Software for Telecommunication Systems(Focusing on the Case of SAMSUNG ELECTRONICS)

Kang,

2024

Preprint

View full text Add to dashboard Cite

Software stands as one of the most rapidly evolving technologies in the present era, characterized by its swift expansion in both scale and complexity which leads to challenges in quality assurance. Software Defect Prediction (SDP) emerges as a methodology crafted to anticipate undiscovered defects, leveraging known defect data from existing codes. This methodology serves to facilitate software quality management, thereby ensuring overall product quality. Machine Learning (ML) and Deep Learning (DL) methodologies exhibit superior accuracy and adaptability compared to traditional statistical approaches catalyzing active researches in this domain. However, it makes us hard to generalize not only because of the disparity between open-source project and commercial project but also the difference on each industrial sectors. Consequently, further research utilizing datasets sourced from diverse real-world sectors becomes imperative to bolster the applicability of these findings. In this study, we utilized embedded software for telecommunication systems of SAMSUNG ELECTRONICS, supplemented by the introduction of nine novel features to train the model, and subsequent analysis of results ensued. Experimental outcomes revealed that the F-measurement metric has been enhanced from 0.58 to 0.63 upon integration of the new features, thereby signifying a performance augmentation of 8.62%. This case study is anticipated to contribute to bolster the application of SDP methodologies within analogous industrial sectors.

show abstract

“…In addition, to validate the efficacy of their proposed algorithm, they compared it against eight distinct public data sets, in which the results showed that their suggested work handles the multi-objective undersampling SDD problem more effectively. Shafiq et al [28] developed an approach for SDD using ML to enhance software quality. They used PC1 data set as input data.…”

Section: Literature Reviewmentioning

confidence: 99%

Automatic Detection of Software Defects based on Machine Learning

Elshamy¹,

AbouElenen²,

Elmougy³

2023

IJACSA

View full text Add to dashboard Cite

Defects in software are one of the critical problems in software engineering community because they provide inaccurate results and negatively affect the quality and reliability of the software. These defects must be detected in the early stages of software development. Researchers had used Software Defect Detection (SDD) techniques to allow predicting module faultproneness. By implementing the hyperparameter optimization techniques and exploiting data imbalances in predicting defects, this paper proposes and develops an SDD model with high performance and generalization capability. To classify defects in software modules, machine learning algorithms and ensemble learning techniques are used on the balanced datasets. The balanced datasets are obtained through using a hybrid of synthetic minority oversample (SMOTE) and Support Vector Machine (SVM). To obtain the optimal hyperparameters needed for the used classifiers and for the dataset balanced algorithms, Non-dominated Sorting Genetic Algorithm II (NDSGA-II) is used. To reduce the time and save other used resources, Hyperband technique, which is a multi-fidelity optimization, is used in NDSGA-II. A 10-fold Cross Validation (CV) is applied to overcome the overfitting and underfitting problems. The accuracy, recall, F-measure, and ROC AUC metrics are used to evaluate the SDD model. The results show that the proposed model predicts defects more accurately than the compared studies.

show abstract

Retracted: Scientific programming using optimized machine learning techniques for software fault prediction to improve software quality

Cited by 15 publications

References 33 publications

Multiple harmonic sources identification including inverter‐based distributed generations using empirical Fourier decomposition

Multiple harmonic sources identification including inverter‐based distributed generations using empirical Fourier decomposition

ML Based Software Defect Prediction in Embedded Software for Telecommunication Systems(Focusing on the Case of SAMSUNG ELECTRONICS)

Automatic Detection of Software Defects based on Machine Learning

Contact Info

Product

Resources

About