Software defect prediction using stacked denoising autoencoders and two-stage ensemble learning

Tong, Haonan; Liu, Bin; Wang, Shihai

doi:10.1016/j.infsof.2017.11.008

Cited by 173 publications

(115 citation statements)

References 62 publications

Supporting

Mentioning

115

Contrasting

Order By: Relevance

“…, xN] = [X1, X2, X3] i.e. P CX where Xi is the submatrix containing the coding coefficients of Pi over C, and xn is the representation coefficients of representing pn with C. the objective function of SDL can be defined as (1) Where r(P, C, X) is a semi-supervised discriminative fidelity term, is the sparsity constraint, and the balance factor is λ. The semisupervised discriminative fidelity term can be defined as For a query module an in P3 , its label can be predicted using equation 3.…”

Section: Proposed Methodologymentioning

confidence: 99%

“…computer code defect prediction (SDP) technique was planned to designate testing assets sanely, decide the testing want of assorted modules of the computer code, and improve programming quality. By utilizing the implications of SDP, programming specialists will profitably pass judgment on it that computer code modules square measure absolute to be blemished, the conceivable range of imperfections in an exceedingly module or different knowledge known with computer code defects before testing the computer code [1]. Existing SDP studies may be divided into four types: (1) Classification, (2) Regression, (3) Mining association rules, (4) Ranking.…”

Section: Introductionmentioning

confidence: 99%

“…

Existing sdp studies may be divided into four types: (1) classification, (2) regression, (3) mining association rules, (4) ranking.

…”

mentioning

confidence: 99%

See 2 more Smart Citations

“Analyzing the Effect with Integrated Technique for Feature Selection and Software Defect Prediction”

Singh¹,

Thankachan²

2019

IJRTE

View full text Add to dashboard Cite

software defect prediction (sdp) technique was projected to designate testing assets sanely, decide the testing want of assorted modules of the software system, and improve programming quality. By utilizing the implications of sdp, programming specialists will fruitfully pass judgment on it that software system modules area unit sure to be blemished, the conceivable range of imperfections in a very module or different information known with software system defects before testing the software system [1]. streamlining the performance of ranking, i.e., faults share average (fpa) as indicated by existing studies of sdp [8]. Existing sdp studies may be divided into four types: (1) classification, (2) regression, (3) mining association rules, (4) ranking. The primary aim of the primary class is to classification of the software system entities like functions, classes, files, etc into completely different levels of severity with the assistance of various applied math techniques like supply regression [2] and discriminant analysis [3] and techniques of machine learning like svm [4] and ann [5]. The second kind aims to assess the amount of imperfections within the components of the software system by victimisation completely different ways, for instance, genetic programming, and support vector regression [6]. The third category utilizes association rule mining approaches, for instance, relative affiliation rule [7], and also the cba2 algorithmic rule, to mine the affiliation between the errors of programming components and programming measurements. The fourth category contemplates to rank the product of the software system as per the amount of errors in components or specifically Sdp distinguishes the modules that area unit imperfect and it needs a large scope of testing. Early recognizable proof of a blunder prompts viable allotment of assets, decreases the time and value of developing software system of high-quality. Hence, associate degree sdp model assumes a vital job in comprehending, assessing and rising the character of a product framework. Consequently, predicting deformity is incredibly basic within the field of reliableness and quality of software system. Predicting the defects is almost a unique analysis space of programming quality planning. By covering key indicators, forms of info to be assembled and also the role of sdp in software system quality, the connection among predictor and defect may be established. Keywords: faults percentage average (fpa) sdp, cba2 algorithm etc.I.

show abstract

Section: Proposed Methodologymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…

Existing sdp studies may be divided into four types: (1) classification, (2) regression, (3) mining association rules, (4) ranking.

…”

mentioning

confidence: 99%

See 1 more Smart Citation

“Analyzing the Effect with Integrated Technique for Feature Selection and Software Defect Prediction”

Singh¹,

Thankachan²

2019

IJRTE

View full text Add to dashboard Cite

show abstract

“…Mahmood et al, conducted a study of replicability as well as reproducibility of defect prediction in research areas to show the importance of any topic behind the replicability [12]. Tong et al worked on SDP using dual-stage ensembles and encoders [16]. Multi objective effort aware SDP model called as Just in Time(JIT) software defect predictor has been proposed by Chen et al They have used logistic regression to build this JIT software defect predictor [15].…”

Section: Literature Surveymentioning

confidence: 99%

Software Defect Prediction u sing Support Vectorised Data and Intelligent Techniques

Kumar*,

Prasad

2020

IJITEE

View full text Add to dashboard Cite

Software enhances the working capability of any business. Developing such a software entrusts the developing organization to build defect free software. In this context we have used PC1 dataset(NASA dataset) which has sufficient parameters for analysis. Intelligent techniques using different methodologies have been applied exhaustively on the PC1 data to find out the best intelligent technique for software defect. As the PC1 data is highly imbalanced data, there was biasness in the prediction of the intelligent techniques. Hence, to overcome this issue, in this paper we tried to propose best balancing method along with the intelligent technique to predict the software defect accurately.

show abstract

“…There are other measures (e.g., AUC and G-measure) that can be used for performance evaluation of dichotomous classifiers. In fact, the F-measure as a comprehensive measurement is a commonly-used evaluation metric in SDP tasks [21,25,26,[35][36][37].…”

Section: The F-measure Might Not Be the Only Appropriate Measuresmentioning

confidence: 99%

Transfer Convolutional Neural Network for Cross-Project Defect Prediction

Qiu

Deng

et al. 2019

Applied Sciences

View full text Add to dashboard Cite

Cross-project defect prediction (CPDP) is a practical solution that allows software defect prediction (SDP) to be used earlier in the software lifecycle. With the CPDP technique, the software defect predictor trained by labeled data of mature projects can be applied for the prediction task of a new project. Most previous CPDP approaches ignored the semantic information in the source code, and existing semantic-feature-based SDP methods do not take into account the data distribution divergence between projects. These limitations may weaken defect prediction performance. To solve these problems, we propose a novel approach, the transfer convolutional neural network (TCNN), to mine the transferable semantic (deep-learning (DL)-generated) features for CPDP tasks. Specifically, our approach first parses the source file into integer vectors as the network inputs. Next, to obtain the TCNN model, a matching layer is added into convolutional neural network where the hidden representations of the source and target project-specific data are embedded into a reproducing kernel Hilbert space for distribution matching. By simultaneously minimizing classification error and distribution divergence between projects, the constructed TCNN could extract the transferable DL-generated features. Finally, without losing the information contained in handcrafted features, we combine them with transferable DL-generated features to form the joint features for CPDP performing. Experiments based on 10 benchmark projects (with 90 pairs of CPDP tasks) showed that the proposed TCNN method is superior to the reference methods.

show abstract

Software defect prediction using stacked denoising autoencoders and two-stage ensemble learning

Cited by 173 publications

References 62 publications

“Analyzing the Effect with Integrated Technique for Feature Selection and Software Defect Prediction”

“Analyzing the Effect with Integrated Technique for Feature Selection and Software Defect Prediction”

Software Defect Prediction u sing Support Vectorised Data and Intelligent Techniques

Transfer Convolutional Neural Network for Cross-Project Defect Prediction

Contact Info

Product

Resources

About