Search

Summary: Although cross‐project defect prediction (CPDP) techniques that use traditional manual features to build defect prediction model have been well‐developed, they usually ignore the semantic and structural information inside the program and fail to capture the hidden features that are critical for program category prediction, resulting in poor defect prediction results. Researchers have proposed using deep learning to automatically extract the semantic features of programs and fuse them with traditional features as training data. However, in practice, it is important to explore the effective representation of the semantic features in the programs and how the fusion of a reasonable ratio between the two types of features can maximize the effectiveness of the model. In this paper, we propose a semantic feature enhancement‐based defect prediction framework (SFE‐DP), which augments the semantic feature set extracted from the program code with data. We also introduce a layer of self‐attentive mechanism and a matching layer to filter low‐efficiency and non‐critical semantic features in the model structure. Finally, we combine the idea of hybrid loss function to iteratively optimize the model parameters. Extensive experiments validate that SFE‐DP can outperform the baseline approaches on 90 pairs of CPDP tasks formed by 10 open‐source projects. [ABSTRACT FROM AUTHOR]

Cross-project defect prediction (CPDP) plays an essential role in identifying potential defects in target projects, especially those with limited historical data, using relevant information from similar source projects. The current studies focused on three main types of software metrics for CPDP: static metrics, code-change metrics, and semantic features. However, these existing CPDP studies encounter two primary challenges: class overlap due to reduced feature dimensions and multicollinearity from integrating various software metrics. To address these challenges, we propose a CPDP model based on both reduction and hybridization techniques (RH-CPDP). The proposed model uses hybrid deep neural networks as a hybridization technique to combine the essential metrics from all metric categories, addressing the issue of class overlap to enhance prediction model efficiency. Principal component analysis (PCA) was used as a reduction method to keep the number of metrics used small, focusing on influential relationships among metrics and fault proneness and avoiding the multicollinearity problem. The experimental analysis conducted using nine open-source projects from the PROMISE dataset demonstrates that RH-CPDP surpasses current CPDP methods (TCSBoost, TPTL, DA-KTSVMO, DBN, and 3SW-MSTL) regarding area under the curve (AUC) and F1-measure. These findings highlight the effectiveness of RH-CPDP in improving the performance of CPDP techniques.

Context: Cross-project defect prediction (CPDP), due to the potential of adaption by industry in realistic scenarios, had gained significant attention from the research community. Currently, existing CPDP studies use static statistical features designed by experts, which might not capture the semantic and structural aspects of software, resulting in low accuracy in defect prediction. Meanwhile, they tend to overlook the valuable iterative information brought about by version updates in mature software projects. Objective: This paper introduces DETECTOR, a novel CPDP approach based on coDE semanTic and cross-vErsion struCTural infORmation to leverage cross-versions features of the software and improve the performance of CPDP. Methods: DETECTOR parses source code to exploit Abstract Syntax Trees (ASTs) and cross-version software network (Cross-SN) that consists of internal class dependency network and cross-version class dependency edges. It utilizes Attention-based Bi-LSTM and simplified graph convolutional neural networks to automatically extract software features from ASTs and Cross-SN. The extracted features are fused using gate(⋅) to generate more effective cross-version features. Finally the source project is selected to carry out the data used to train the classifier to predict the defects. Results: Empirical studies on seven open-source Java projects, the experiment results show that: (1) DETECTOR outperforms the state-of-the-art models in CPDP; (2) our proposed cross-version dependent edges positively contribute to DETECTOR performance; (3) gate(⋅) outperforms existing strategies in fusion features; (4) more multi-versions information enhance DETECTOR's performance. Conclusion: DETECTOR can predict more defects in CPDP and improve the accuracy and effectiveness of prediction. [ABSTRACT FROM AUTHOR]

The Software Defect Prediction (SDP) process provides reliable software by identifying defect-prone modules before the testing stage. It efficiently and effectively utilizes quality assurance resources. Most predictive models are trained on historical data which belong to the same project or comparable project. These models show satisfactory performance as they utilize similar settings to the considered projects. But the limitation of these models is that they are effective only if there are adequate historical data to train a predictive model. In reality, however, such historical data are minimal for some projects and absent for new projects. The defect prediction in such projects which lack historical data can be accomplished by training prediction models on different project data. This process is known as Cross-Project Defect Prediction (CPDP). Software defect datasets also suffered from class imbalance issues which further degrades the model's performance. In this research work, the authors have proposed a Multi-Objective Random Forest (MO-RF) algorithm with a data resampling technique to minimize the probability of false alarms, to maximize the probability of detection and to overcome the class imbalance problem. The study also evaluates the performance of other prediction models. The proposed method has shown percentage improvement (in terms of AUC) of 2.78 and 3.46 over MONB and MONBNN, respectively. [ABSTRACT FROM AUTHOR]

Software cross-project defect prediction (CPDP) makes use of cross-project (CP) data to overcome the lack of data necessary to train well-performing software defect prediction (SDP) classifiers in the early stage of new software projects. Since the CP data (known as the source) may be different from the new project's data (known as the target), this makes it difficult for CPDP classifiers to perform well. In particular, it is a mismatch of data distributions between source and target that creates this difficulty. Transfer learning-based CPDP classifiers are designed to minimize these distribution differences. The first Transfer learning-based CPDP classifiers treated these differences equally, thereby degrading prediction performance. To this end, recent research has the Weighted Balanced Distribution Adaptation (W-BDA) method to leverage the importance of both distribution differences to improve classification performance. Although W-BDA has been shown to improve model performance in CPDP and tackle the class imbalance by balancing the class proportion of each domain, research to date has failed to consider model performance in light of increasing target data. We provide the first investigation studying the effects of increasing the target data when leveraging the importance of both distribution differences. We extend the initial W-BDA method and call this extension the W-BDA + method. To evaluate the effectiveness of W-BDA + for improving CPDP performance, we conduct eight experiments on 18 projects from four datasets, where data sampling was performed with different sampling methods. Data sampling was only performed on the baseline methods and not on our proposed W-BDA + and the original W-BDA because data sampling issues do not exist for these two methods. We evaluate our method using four complementary indicators (i.e., Balanced Accuracy, AUC, F-measure and G-Measure). Our findings reveal an average improvement of 6%, 7.5%, 10% and 12% for these four indicators when W-BDA + is compared to the original W-BDA and five other baseline methods (for all four of the sampling methods used). Also, as the target to source ratio is increased with different sampling methods, we observe a decrease in performance for the original W-BDA, with our W-BDA + approach outperforming the original W-BDA in most cases. Our results highlight the importance of having an awareness of the effect of the increasing availability of target data in CPDP scenarios when using a method that can handle the class imbalance problem. [ABSTRACT FROM AUTHOR]

Software defect prediction involves predicting which components in a software program, like classes or functions, are likely to have defects, based on metrics that describe those components. Cross-project defect prediction is a type of defect prediction where, due to not enough labeled defect data for the target project, the model is trained on data from other projects to predict defects in the target project. Within cross-project defect prediction, several transfer learning techniques have been proposed, whose goal is to transfer knowledge from a source to a target domain. Although there is a collection of comprehensive surveys on cross-project defect prediction, no study surveyed the cross-project defect prediction approaches through the lens of a transfer learning algorithm design framework. The contribution of this survey is twofold: it establishes a taxonomy for transfer learning approaches and surveys 44 cross-project defect prediction methods, analyzing and organizing each paper according to those categories. Ultimately, this survey provides a new perspective on how transfer learning approaches are employed in cross-project defect prediction and opens new research directions for the application of transfer learning for cross-project defect prediction.

Software defect prediction models enable test managers to predict defect-prone modules and assist with delivering quality products. A test manager would be willing to identify the attributes that can influence defect prediction and should be able to trust the model outcomes. The objective of this research is to create software defect prediction models with a focus on interpretability. Additionally, it aims to investigate the impact of size, complexity, and other source code metrics on the prediction of software defects. This research also assesses the reliability of cross-project defect prediction. Well-known machine learning techniques, such as support vector machines, k-nearest neighbors, random forest classifiers, and artificial neural networks, were applied to publicly available PROMISE datasets. The interpretability of this approach was demonstrated by SHapley Additive exPlanations (SHAP) and local interpretable model-agnostic explanations (LIME) techniques. The developed interpretable software defect prediction models showed reliability on independent and cross-project data. Finally, the results demonstrate that static code metrics can contribute to the defect prediction models, and the inclusion of explainability assists in establishing trust in the developed models. [ABSTRACT FROM AUTHOR]

Cross-project software defect prediction (CPDP) aims to enhance defect prediction in target projects with limited or no historical data by leveraging information from related source projects. The existing CPDP approaches rely on static metrics or dynamic syntactic features, which have shown limited effectiveness in CPDP due to their inability to capture higher-level system properties, such as complex design patterns, relationships between multiple functions, and dependencies in different software projects, that are important for CPDP. This paper introduces a novel approach, a graph-based feature learning model for CPDP (GB-CPDP), that utilizes NetworkX to extract features and learn representations of program entities from control flow graphs (CFGs) and data dependency graphs (DDGs). These graphs capture the structural and data dependencies within the source code. The proposed approach employs Node2Vec to transform CFGs and DDGs into numerical vectors and leverages Long Short-Term Memory (LSTM) networks to learn predictive models. The process involves graph construction, feature learning through graph embedding and LSTM, and defect prediction. Experimental evaluation using nine open-source Java projects from the PROMISE dataset demonstrates that GB-CPDP outperforms state-of-the-art CPDP methods in terms of F1-measure and Area Under the Curve (AUC). The results showcase the effectiveness of GB-CPDP in improving the performance of cross-project defect prediction. [ABSTRACT FROM AUTHOR]

The software defect prediction approaches are evaluated, in within-project context only, with only a few other approaches, according to distinct scenarios and performance indicators. So, we conduct various experiments to evaluate well-known defect prediction approaches using different performance indicators. The evaluations are performed in the scenario of ranking the entities — with and without considering the effort to review the entities and classifying entities in within-project as well as cross-project contexts. The effect of imbalanced datasets on the ranking of the approaches is also evaluated. Our results indicate that in within-project as well as cross-project context, process metrics, the churn of source code, and entropy of source code perform significantly better under the context of classification and ranking — with and without effort consideration. The previous defect metrics and other single metric approaches (like lines of code) perform worst. The ranking of the approaches is not changed by imbalanced datasets. We suggest using the process metrics, the churn of source code, and entropy of source code metrics as predictors in future defect prediction studies and taking care while using the single metric approaches as predictors. Moreover, different evaluation scenarios generate different ordering of approaches in within-project and cross-project contexts. Therefore, we conclude that each problem context has distinct characteristics, and conclusions of within-project studies should not be generalized to cross-project context and vice versa. [ABSTRACT FROM AUTHOR]

A deep learning system (DLS) developed based on one software project for defect prediction may well be applied to the related code on the same project but is usually difficult to be applied to new or unknown software projects. To address this problem, we propose a Transferable Graph Convolutional Neural Network (TGCNN) that can learn defects from the lightweight semantic graphs of code and transfer the learned knowledge from the source project to the target project. We discuss how the semantic graph is constructed from code; how the TGCNN can learn from the graph; and how the learned knowledge can be transferred to a new or unknown project. We also conduct a controlled experiment to evaluate our method. The result shows that despite some limitations, our method performs considerably better than existing methods. [ABSTRACT FROM AUTHOR]

Heterogeneous defect prediction (HDP) is a significant research topic in cross-project defect prediction (CPDP), due to the inconsistency of metrics used between source and target projects. While most HDP methods aim to improve the performance of models trained on data from one source project, few studies have investigated how the number of source projects affects predictive performance. In this paper, we propose a new multi-source heterogeneous kernel mapping (MSHKM) algorithm to analyze the effects of different numbers of source projects on prediction results. First, we introduce two strategies based on MSHKM for multi-source HDP. To determine the impact of the number of source projects on the predictive performance of the model, we regularly vary the number of source projects in each strategy. Then, we compare the proposed MSHKM with state-of-the-art HDP methods and within-project defect prediction (WPDP) methods, in terms of three common performance measures, using 28 data sets from five widely used projects. Our results demonstrate that, (1) in the multi-source HDP scenario, strategy 2 outperforms strategy 1; (2) for MSHKM, a lower number of source projects leads to better results and performance under strategy 1, while n = 4 is the optimal number under strategy 2; (3) MSHKM performs better than related state-of-the-art HDP methods; and (4) MSHKM outperforms WPDP. In summary, our proposed MSHKM algorithm provides a promising solution for heterogeneous cross-project defect prediction, and our findings suggest that the number of source projects should be carefully selected to achieve optimal predictive performance. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Cross-project defect prediction (CPDP) involves the use of other projects (aka source projects) for training and persuasive model building for a particular project (aka target project). However, the distribution dissimilarity between the two different project data often limits the CPDP model's capability. Several CPDP approaches have been proposed in the literature to combat this distribution gap through instance selection by transferring the knowledge learned from the source to the target project. However, very few have explored transferring knowledge through feature selection (FS). A novel CPDP approach has been proposed consisting of two distinct FS strategies (one non-iterative and one iterative) having a trade-off between the cost and the performance respectively. The first strategy MIC_SM_FS is a non-iterative strategy that selects features that are important and have similar distribution with the corresponding target feature. The feature importance is measured using maximal information coefficient and the feature distribution similarity is calculated using 10 statistical measures. On the other hand, the second strategy BPSO_FS is an iterative strategy that works on optimizing the performance, utilizing the powerful binary particle swarm optimization algorithm for selecting the representative features for CPDP. Both of the proposed strategies have been tested on 26 cross-project experiments based on 8 software projects. From the two proposed strategies, a CPDP model built utilizing BPSO_FS showed better results. Further, to assess its performance, comparison is done with two baseline approaches viz. ALL and ManualDown, within-project defect prediction, and a state-of-the-art CPDP technique TCA+. Statistical results showed the potential of the proposed CPDP approach over the compared approaches. [ABSTRACT FROM AUTHOR]

Software defect prediction models enable test managers to predict defect-prone modules and assist with delivering quality products. A test manager would be willing to identify the attributes that can influence defect prediction and should be able to trust the model outcomes. The objective of this research is to create software defect prediction models with a focus on interpretability. Additionally, it aims to investigate the impact of size, complexity, and other source code metrics on the prediction of software defects. This research also assesses the reliability of cross-project defect prediction. Well-known machine learning techniques, such as support vector machines, k-nearest neighbors, random forest classifiers, and artificial neural networks, were applied to publicly available PROMISE datasets. The interpretability of this approach was demonstrated by SHapley Additive exPlanations (SHAP) and local interpretable model-agnostic explanations (LIME) techniques. The developed interpretable software defect prediction models showed reliability on independent and cross-project data. Finally, the results demonstrate that static code metrics can contribute to the defect prediction models, and the inclusion of explainability assists in establishing trust in the developed models.

Cross-project defect prediction (CPDP) is a practical approach for finding software defects in projects which have incomplete or fewer data. Improvements to the defect prediction accuracy of CPDP—such as the PROMISE repository, the correct classification of the source data, removing the noise, reducing the distribution gap, and balancing the output classes—are an ongoing challenge, as is the selection of an optimal feature set. This research paper aims to achieve a higher defect prediction accuracy for multi-class CPDP by selecting an optimal feature set through XGBoost combined with an automatic feature extraction using a convolutional neural network (CNN). This research type is explanatory, and this research method is controlled experimentation, for which the independent variable prediction accuracy was dependent upon two variables, XGBoost and CNN. The Softmax layer was added to the output layers of the CNN classifier to classify the output into multiple classes. In our experimentation with CPDP, we selected all 28 versions of the multi-class, in which 11 versions were selected as the source projects, against which we predicted 28 target versions with an average AUC of 75.57%. We validated this research paper's results through the Wilcoxon test. Therefore, after removing the noise, class imbalances, and the data distribution gap, and treating the PROMISE dataset as multi-class, the optimal features selected through XGBoost and classified through the CNN can substantially increase the prediction accuracy in CPDP as evident from our exploratory data analysis (EDA). [ABSTRACT FROM AUTHOR]

Cross-project software defect prediction (CPSDP) uses data from other projects to train the defect prediction model and is often used for new projects for which previous versions of the software are not available. Most of the latest CPSDP models are based on machine learning (ML), and ML algorithms use code quality metrics of the project as input. Existing ML-based CPSDP models use trivial count-based code quality metrics of the code's object-oriented features, which can hardly capture the structural characteristics of the code and are insufficient to develop a good CPSDP model. So, this research article proposes an improved ML-based CPSDP model that uses new structural code metrics as input features. Proposed source code metrics capture the structural characteristics of the code, such as complexity of the class, coupling, lack of cohesion, abstraction, inheritance coupling, and polymorphism, in a better way than existing source code metrics. Datasets of selected projects are prepared based on the proposed structural code metrics, and a new t-test-based procedure for project selection to prepare training datasets for ML algorithms is proposed. Finally, the most appropriate ML algorithm, extreme gradient boost, is selected for our proposed CPSDP model based on three performance metrics: AUC, accuracy, and balance between AUC and accuracy (BBAA). The balance between AUC and accuracy (BBAA) is proposed in this article. The proposed CPSDP model is compared with six existing models, and results show a significant improvement in the performance. • An improved cross-project software defect prediction model is developed. • Six new structural code metrics are proposed based on object-oriented design. • A new project selection method is proposed based on T-test. • XGBOOST is identified empirically as the best classifier for defect prediction. • The proposed model gives 7 % better AUC than selected existing studies. [ABSTRACT FROM AUTHOR]

Cross-project defect prediction (CPDP) trains the prediction models with existing data from other projects (the source projects) and uses the trained model to predict the target projects. To solve two major problems in CPDP, namely, variability in data distribution and class imbalance, in this paper we raise a CPDP model combining feature transfer and ensemble learning, with two stages of feature transfer and the classification. The feature transfer method is based on Pearson correlation coefficient, which reduces the dimension of feature space and the difference of feature distribution between items. The class imbalance is solved by SMOTE and Voting on both algorithm and data levels. The experimental results on 20 source-target projects show that our method can yield significant improvement on CPDP.

Background: Software defect prediction models aim at identifying the potential faulty modules of a software project based on historical data collected from previous versions of the same project. Due to the lack of availability of software engineering data from the same project, the researchers proposed cross-project defect prediction (CPDP) models where the data collected from one or more projects are used to predict faults in other project. There are a number of approaches proposed with different levels of success and very limited repeatability. Goals: The purpose of this paper is to investigate the existing studies of cross-project models for defect prediction. It synthesizes the literature focusing on characteristics such as project type, software metrics, data preprocessing techniques, features selection approaches, classifiers, and performance measures used. Method: This paper follows the well-known Systematic Literature Review (SLR) approach proposed by Barbara Kitchenham in 2007. Results: Our finding shows that most of the article was published between 2015 and 2021. Moreover, the studies are mostly based on open-source datasets and the software metrics used to create the models are mainly product metrics. We also found out that most studies attempted to improve their models improving data preprocessing and feature selection approaches. Furthermore, logistic regression followed by naive bayes and random forest are the most adopted classifier techniques in such models. Finally, the f-measure followed by recall and AUC are the most preferred evaluation measure used to evaluate the performance of the models. Conclusions: This study provides an overview of the different approaches used to improve the CPDP models analyzing the different techniques used for data preprocessing, feature selection, and the selection of the classifiers. Moreover, we identified some aspects that need further investigation.

Software defect prediction (SDP) plays an important role in allocating testing resources and improving testing efficiency. Multi-source cross-project defect prediction (MSCPDP) based on transfer learning refers to transferring defect knowledge from multiple source projects to the target project. MSCPDP has drawn increasing attention from academic and industry communities, and some MSCPDP methods have been proposed. However, most existing MSCPDP models are not open-source. MSCPDPLab replicates nine state-of-the-art MSCPDP models with unified interface and integrates the processes of data loading, model training and testing, and performance evaluation (including 13 performance measures). This paper describes the toolbox’s functionalities and presents its ease of use.

• To create your highlights, please type over the instructions in the template box below: • Pre-processing and feature extraction techniques from NLP domain to CPDP domain. • The feature extractor combines BLSTM with an attention mechanism to enhance the effect. • An adversarial structure is used to solve the distribution differences problem. Cross-project defect prediction (CPDP) is currently a hot research direction in the field of software reliability. Traditional CPDP methods cannot capture the semantic and contextual information of programs by handcrafted features, which affects the prediction performance. In this paper, we apply technology in the NLP domain to solve it. We first extract token vectors from the abstract syntax tree (AST) of source and target code files, and then convert them into numerical vectors by the word embedding algorithm of continuous bag-of-word model (CBOW) as the input of the proposed deep learning model named Generative Adversarial Long-Short Term Memory Neural Networks (G-LSTM). The model integrates generative adversarial network (GAN) and bidirectional long-short term memory networks (BiLSTM) with attention mechanism to automatically learn semantic and contextual features of programs. Specifically, GAN is used to eliminate the differences in data distribution between source and target projects, and BiLSTM is the feature extraction encoder. We compose five projects of the PROMISE dataset into 20 source-target project pairs and conduct comparison experiments on them. The experimental results demonstrate that our method outperforms some traditional and state-of-the-art CPDP methods in terms of the evaluation metrics of AUC and Acc. To create your abstract, type over the instructions in the template box below. Fonts or abstract dimensions should not be changed or altered. [Display omitted] [ABSTRACT FROM AUTHOR]

Data available in software engineering for many applications contains variability and it is not possible to say which variable helps in the process of the prediction. Most of the work present in software defect prediction is focused on the selection of best prediction techniques. For this purpose, deep learning and ensemble models have shown promising results. In contrast, there are very few researches that deals with cleaning the training data and selection of best parameter values from the data. Sometimes data available for training the models have high variability and this variability may cause a decrease in model accuracy. To deal with this problem we used the Akaike information criterion (AIC) and the Bayesian information criterion (BIC) for selection of the best variables to train the model. A simple ANN model with one input, one output and two hidden layers was used for the training instead of a very deep and complex model. AIC and BIC values are calculated and combination for minimum AIC and BIC values to be selected for the best model. At first, variables were narrowed down to a smaller number using correlation values. Then subsets for all the possible variable combinations were formed. In the end, an artificial neural network (ANN) model was trained for each subset and the best model was selected on the basis of the smallest AIC and BIC value. It was found that combination of only two variables' ns and entropy are best for software defect prediction as it gives minimum AIC and BIC values. While, nm and npt is the worst combination and gives maximum AIC and BIC values. [ABSTRACT FROM AUTHOR]

Software fault prediction (SFP) refers to the process of identifying (or predicting) faulty modules based on its characteristics/software metrics. SFP can be done either using the same project data in both the training and testing phase i.e. within project defect prediction or using a different one, as done in cross-project defect prediction (CPDP). Previous works show that contemporary research in this field is progressing towards CPDP. To present the current state of progress and the future prospects of CPDP, this article presents a comprehensive survey of CPDP considering the latest work along with its SWOT analysis. This survey is targeted to present the novice researchers, academicians, and practitioners with the alphas and omegas of this contemporary challenging field. We have also carried a qualitative and quantitative evaluation of CPDP w.r.t some of the targeted research questions. A total of 34 significant primary CPDP studies published from 2008 to 2019 were selected. Both qualitative and quantitative data are extracted from each study. The collected data is then consolidated and analyzed to present a comprehensive report showing the current state of the art, along with the answers to the targeted research questions and finally the CPDP SWOT analysis. We observed that there exists a big scope for performance improvement in CPDP. Integration of feature engineering, exploration with different process metrics, hyperparameter tuning, class imbalance handling in CPDP setting are some of the ways identified for bringing enhancement in CPDP performance. Apart from this, we would like to conclude that there is a strong need to investigate Precision over the Recall and model's validity in terms of effort/cost-effectiveness. [ABSTRACT FROM AUTHOR]

Heterogeneous defect prediction (HDP) is a significant research topic in cross-project defect prediction (CPDP), due to the inconsistency of metrics used between source and target projects. While most HDP methods aim to improve the performance of models trained on data from one source project, few studies have investigated how the number of source projects affects predictive performance. In this paper, we propose a new multi-source heterogeneous kernel mapping (MSHKM) algorithm to analyze the effects of different numbers of source projects on prediction results. First, we introduce two strategies based on MSHKM for multi-source HDP. To determine the impact of the number of source projects on the predictive performance of the model, we regularly vary the number of source projects in each strategy. Then, we compare the proposed MSHKM with state-of-the-art HDP methods and within-project defect prediction (WPDP) methods, in terms of three common performance measures, using 28 data sets from five widely used projects. Our results demonstrate that, (1) in the multi-source HDP scenario, strategy 2 outperforms strategy 1; (2) for MSHKM, a lower number of source projects leads to better results and performance under strategy 1, while n = 4 is the optimal number under strategy 2; (3) MSHKM performs better than related state-of-the-art HDP methods; and (4) MSHKM outperforms WPDP. In summary, our proposed MSHKM algorithm provides a promising solution for heterogeneous cross-project defect prediction, and our findings suggest that the number of source projects should be carefully selected to achieve optimal predictive performance.

Software effort estimation (SEE) models have been studied for decades. One of serious but typical situations for data-oriented models is the availability of datasets for training models. Cross-company software effort estimation (CCSEE) is a research topic to utilize project data outside an organization. The same problem was identified in software defect prediction research, and Cross-project defect prediction (CPDP) has been studied. CPDP and CCSEE shared the motivation and developed approaches for the same problem. A question arisen that CPDP approaches were applicable to CCSEE. This study explored this question with a survey and an empirical study focusing on homogeneous approaches. We first examined 24 homogeneous CPDP approach implementations provided in a CPDP framework and found more than half of the approaches were applicable. Next, we used the results of two past studies to check whether the applicable CPDP approaches covered strategies taken in past CPDP studies. The empirical experiment was then conducted to evaluate the estimation performance of the applicable CPDP approaches. CPDP approaches were configured with some machine learning techniques if available, and ten CCSEE dataset configurations were supplied for evaluation. The result was also compared with the results of those two past studies to find the commonalities and the differences between CPDP and CCSEE. The answers to the research questions revealed the our CPDP selection covered the strategies that CPDP approaches had taken. The empirical results supported the simple merge with no instance weighting, no feature selection, no data transformation, nor the simple voting. It was not necessarily surprising according CPDP and CCSEE studies, but had not been explored with CPDP approaches under CCSEE situation. A practical implication is: Combine cross-company data to make effort estimates. [ABSTRACT FROM AUTHOR]

The selection of relevant training data significantly improves the quality of cross-project defect prediction (CPDP) process. We propose a training data selection approach and compare its performance against the Burak filter and the Peter filter over Bug Prediction Dataset. In our approach (BurakMHD), firstly a data transformation is applied to the datasets. Then, individual instances of the target project adds k-instances at a minimum Hamming distance each from the transformed multi-source defective and non-defective data instances to the filtered training dataset (filtered TDS). Compared to using all the cross-project data, the false positive rate decreases by 10.6% associated with a 2.6% decrease in defect detection rate. The overall performance nMCC, Balance, G-measure increase by 2.9%, 5.7%, 6.6%, respectively. Compared to Burak filter and Peter filter, defect detection rate increases by 1.5% and 1.8%, respectively, and the false positive rate decreases by 6.4%. The overall performance nMCC, Balance, G-measure increase by 3%, 5.3%, 6.8% and by 3.2%, 5.5%, 7.1% compared to Burak and Peter filter, respectively. Compared to within-project predictions, the overall performance nMCC, Balance, G-measure increase by 1.1%, 3.4%, 4%, respectively, and the defect detection rate and false positive rate decrease by 9.2% and 13.1%, respectively. In general, our approach improved the performance significantly, compared to the Burak filter, Peter filter, cross-project prediction, and within-project prediction. Therefore, we conclude, applying data transformation and filtering training data separately from the defective and non-defective instances of cross-project data is helpful to select the relevant data for CPDP. [ABSTRACT FROM AUTHOR]

Featured Application: DePaaS has the potential to be used as a global, shared platform for availing software defects prediction services by choosing appropriate base project, defect prediction model and prediction granularity. Over time, DePaaS can potentially become a rich source of defects metadata and provide deep insights into developing efficient software defects prediction models. It can promote inter-agency collaboration, data sharing, continuous improvement, and further research into application of artificial intelligence, genetic programming, and other techniques for solving key problems of software engineering. Using artificial intelligence (AI) based software defect prediction (SDP) techniques in the software development process helps isolate defective software modules, count the number of software defects, and identify risky code changes. However, software development teams are unaware of SDP and do not have easy access to relevant models and techniques. The major reason for this problem seems to be the fragmentation of SDP research and SDP practice. To unify SDP research and practice this article introduces a cloud-based, global, unified AI framework for SDP called DePaaS—Defects Prediction as a Service. The article describes the usage context, use cases and detailed architecture of DePaaS and presents the first response of the industry practitioners to DePaaS. In a first of its kind survey, the article captures practitioner's belief into SDP and ability of DePaaS to solve some of the known challenges of the field of software defect prediction. This article also provides a novel process for SDP, detailed description of the structure and behaviour of DePaaS architecture components, six best SDP models offered by DePaaS, a description of algorithms that recommend SDP models, feature sets and tunable parameters, and a rich set of challenges to build, use and sustain DePaaS. With the contributions of this article, SDP research and practice could be unified enabling building and using more pragmatic defect prediction models leading to increase in the efficiency of software testing. [ABSTRACT FROM AUTHOR]

Cross-project defect prediction (CPDP) aims to build a prediction model on existing source projects and predict the labels of target project. The data distribution difference between different projects makes CPDP very challenging. Besides, most existing CPDP methods usually require sufficient and labeled data. However, acquiring lots of labeled data for a new project is difficult while obtaining the unlabeled data is relatively easy. A desirable approach is building a prediction model on unlabeled data and labeled data. CPDP in this scenario is called cross-project semi-supervised defect prediction (CSDP). Recently, generative adversarial networks have achieved impressive results with these strong ability of learning data distribution and discriminative representation. For effectively learning the discriminative features of data from different projects, we propose a Discriminative Adversarial Feature Learning (DAFL) approach for CSDP. DAFL consists of feature transformer and project discriminator, which compete with each other. A feature transformer tries to generate feature representation, which learns the discriminant information and preserves intrinsic structure inferred from both labeled and unlabeled data. A project discriminator tries to discriminate source and target instances on the generated representation. Experiments on 16 projects show that DAFL performs significantly better than baselines.

Cross-project defect prediction (CPDP) is a promising approach to help to allocate testing efforts efficiently and guarantee software reliability in the early software lifecycle. A CPDP method usually trains a software defect classifier based on labeled data sets. Then the trained classifier can predict new projects without labeled data. Most previous CPDP techniques focused on manually designing handcrafted features. However, these handcrafted features ignore the programs' semantic information. Moreover, some other existing defect prediction approaches learned semantic features from source code to build classifiers directly. However, they did not consider the distribution divergence between source and target projects. To address these limitations, we put forward a new method called Adversarial Discriminative Convolutional Neural Network (ADCNN). It can extract the transferable semantic features from source code for CPDP tasks. Specifically, we first parse source files into token vectors and then map them to integer vectors via word embedding. Second, we combine adversarial learning with discriminative feature learning to train the ADCNN model. The key of the ADCNN model is to learn the discriminative mapping of the target project to the source feature space by deceiving a domain discriminator. A domain discriminator tries to distinguish the target project files from the source project files. Finally, we use the extracted transferable semantic features to build a classifier for CPDP tasks. We evaluate our method on ten benchmark projects in terms of F-measure, AUC, and PofB20 (an effort-aware evaluation metric). The experimental results demonstrate that our ADCNN method performs better compared with other related CPDP methods.

Cross-project defect prediction (CPDP) methods can be used when the target project is a new project or lacks enough labeled program modules. In these new target projects, we can easily extract and then measure these modules with software measurement tools. However, labeling these program modules is time-consuming, error-prone and requires professional domain knowledge. Moreover, directly using labeled modules in the other projects (i.e., the source projects) can not achieve satisfactory performance due to the large data distribution difference in most cases. In this article, to our best knowledge, we are the first to propose a novel method ALTRA, which can utilize both active learning and TrAdaBoost to alleviate this issue. In particular, we firstly use Burak filter to select similar labeled modules from the source project after analyzing the unlabeled modules in the target project. Then we use active learning to choose representative unlabeled modules from the target project and ask experts to label the type (i.e., defective or non-defective) of these modules. Later, we use TrAdaBoost to determine the weights of labeled modules in the source project and the target project, and then construct the model via weighted support vector machine. After selecting a small number of modules (i.e., only 5% modules) in the target project, we terminate the method ALTRA and return the final constructed model. To show the effectiveness of our proposed method ALTRA, we choose 10 large-scale open-source projects from different application domains. In terms of both F1 and AUC performance indicators, we find ALTRA can perform significantly better than seven state-of-the-art CPDP baselines. Moreover, we also show that the usage of Burak filter, the uncertainty active learning strategy, the class imbalanced learning method and TrAdaBoost are competitive in our proposed method ALTRA.

Cross-project defect prediction (CPDP) is a feasible way to perform software defect prediction (SDP) when lacking historical data. Recent CPDP approaches have employed deep learning techniques to better exploit the information from the program's abstract syntax trees (ASTs). However, the granularity of the AST nodes and the data distribution difference between projects may have negative impacts on the prediction performance, which many CPDP studies didn't take into consideration. To handle these issues, this paper explores a better AST node granularity and proposes a CPDP framework based on multi-kernel transfer convolutional neural networks. Specifically, for AST node granularity, we explore the difference of three AST node granularities and then compare the prediction performance of each granularity on several prediction models. For the CPDP framework, we first parse the program source code into ASTs and then encode the AST nodes into numerical vectors using the embedding technique. Secondly, to mine transferable semantic features, the encoded ASTs are fed into a convolutional neural network, in which a multi-kernel matching layer is added to minimize the data distribution divergence between the source and target project. Finally, to make use of the information from the handcrafted features, the semantic features mined from the AST are joint with handcrafted features to form the joint features for CPDP. We evaluate our approach on 110 CPDP tasks formed by 11 open-source projects and results show that the proposed CPDP method outperforms most deep learning-based approaches.

Defect prediction is a technique introduced to optimize the testing phase of the software development pipeline by predicting which components in the software may contain defects. Its methodology trains a classifier with data regarding a set of features measured on each component from the target software project to predict whether the component may be defective or not. However, suppose the defective information is not available in the training set. In that case, we need to rely on an alternate approach that uses the training set of external projects to train the classifier. This approached is called cross-project defect prediction. Bad code smells are a category of features that have been previously explored in defect prediction and have been shown to be a good predictor of defects. Code smells are patterns of poor development in the code and indicate flaws in its design and implementation. Although they have been previously studied in the context of defect prediction, they have not been studied as features for cross-project defect prediction. In our experiment, we train defect prediction models for 100 projects to evaluate the predictive performance of the bad code smells. We implemented four cross-project approaches known in the literature and compared the performance of 37 smells with 56 code metrics, commonly used for defect prediction. The results show that the cross-project defect prediction models trained with code smells significantly improved 6.50 % on the ROC AUC compared against the code metrics. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Prediction approaches used for cross-project defect prediction (CPDP) are usually impractical because of high false alarms, or low detection rate. Instance based data filter techniques that improve the CPDP performance are time-consuming and each time a new test set arrives for prediction the entire filter procedure is repeated. We propose to use local modeling approach for the utilization of ever-increasing cross-project data for CPDP. We cluster the cross-project data, train per cluster prediction models and predict the target test instances using corresponding cluster models. Over 7 NASA Data sets performance comparison using statistical methods between within-project, cross-project, and our local modeling approach were performed. Compared to within-project prediction the cross-project prediction increased the probability of detection (PD) associated with an increase in the probability of false alarm (PF) and decreased overall performance Balance. The application of local modeling decreased the (PF) associated with a decrease in (PD) and an overall performance improvement in terms of Balance. Moreover, compared to one state of the art filter technique – Burak filter, our approach is simple, fast, performance comparable, and opens a new perspective for the utilization of ever-increasing cross-project data for defect prediction. Therefore, when insufficient within-project data is available we recommend training local cluster models than training a single global model on cross-project datasets. [ABSTRACT FROM AUTHOR]

Cross-project defect prediction (CPDP) aims to predict the defects on target project by using a prediction model built on source projects. The main problemin CPDP is the huge distribution gap between the source project and the target project, which prevents the prediction model from performing well. Most existing methods overlook the class discrimination of the learned features. Seeking an effective transferable model from the source project to the target project for CPDP is challenging. In this paper, we propose an unsupervised domain adaptation based on the discriminative subspace learning (DSL) approach for CPDP. DSL treats the data from two projects as being from two domains and maps the data into a common feature space. It employs crossdomain alignment with discriminative information from different projects to reduce the distribution difference of the data between different projects and incorporates the class discriminative information. Specifically, DSL first utilizes subspace learning based domain adaptation to reduce the distribution gap of data between different projects. Then, itmakes full use of the class label information of the source project and transfers the discrimination ability of the source project to the target project in the common space. Comprehensive experiments on five projects verify that DSL can build an effective prediction model and improve the performance over the related competing methods by at least 7.10% and 11.08% in terms of G-measure and AUC. [ABSTRACT FROM AUTHOR]

Cross-project defect prediction (CPDP) is a practical approach for finding software defects in projects which have incomplete or fewer data. Improvements to the defect prediction accuracy of CPDP—such as the PROMISE repository, the correct classification of the source data, removing the noise, reducing the distribution gap, and balancing the output classes—are an ongoing challenge, as is the selection of an optimal feature set. This research paper aims to achieve a higher defect prediction accuracy for multi-class CPDP by selecting an optimal feature set through XGBoost combined with an automatic feature extraction using a convolutional neural network (CNN). This research type is explanatory, and this research method is controlled experimentation, for which the independent variable prediction accuracy was dependent upon two variables, XGBoost and CNN. The Softmax layer was added to the output layers of the CNN classifier to classify the output into multiple classes. In our experimentation with CPDP, we selected all 28 versions of the multi-class, in which 11 versions were selected as the source projects, against which we predicted 28 target versions with an average AUC of 75.57%. We validated this research paper’s results through the Wilcoxon test. Therefore, after removing the noise, class imbalances, and the data distribution gap, and treating the PROMISE dataset as multi-class, the optimal features selected through XGBoost and classified through the CNN can substantially increase the prediction accuracy in CPDP as evident from our exploratory data analysis (EDA).

Software defect prediction has attracted much attention of researchers in software engineering. At present, feature selection approaches have been introduced into software defect prediction, which can improve the performance of traditional defect prediction (known as within-project defect prediction, WPDP) effectively. However, the studies on feature selection are not sufficient for cross-project defect prediction (CPDP). In this paper, we use the feature subset selection and feature ranking approaches to explore the effectiveness of feature selection for CPDP. An empirical study is conducted on NASA and PROMISE datasets. The results show that both the feature subset selection and feature ranking approaches can improve the performance of CPDP. Therefore, we should select the representative feature subset or set a reasonable proportion of selected features to improve the performance of CPDP in future studies.

Cross-project defect prediction (CPDP) is an active research topic in the domain of software defect prediction, since CPDP can be applied to the following scenarios: the target project for software defect prediction is a new project or the target project does not have enough labeled modules. Most of the previous work tried to utilize the labeled dataset gathered from other projects (i.e., the source projects) and then proposed transfer learning based methods to reduce the data distribution difference between different projects. In this article, we propose a deep learning based CPDP method DeepCPDP. For this method, we represent source code of each extracted program module by using simplified abstract syntax tree (SimAST). For a node of SimAST, we only keep its node type, since this is project-independent, while we ignore the name of method and variable, since these information are project-specific. Therefore, SimAST is project-independent and especially suitable for the task of CPDP. Then, we extract the token vector from each module after it is modeled via SimAST. Moreover, we design a new unsupervised based embedding method SimASTToken2Vec to learn meaningful representation for these extracted token vectors. Later, we employ Bi-directional Long Short-Term Memory (BiLSTM) neural network to automatically learn semantic features from embedded token vectors. In addition, we use attention mechanism over the BiLSTM layer to learn the weight of the vectors from the learned semantic features. Finally, we construct CPDP models via Logistic regression classifier. To show the effectiveness of DeepCPDP, ten large-scale projects from different application domains are used and AUC measure is used to measure the prediction performance of trained models. By using Scott-Knott test, we can find DeepCPDP can significantly outperform eight state-of-the-art baselines. Moreover, we also verify that the usage of SimASTToken2Vec, BiLSTM and attention mechanism is competitive in our proposed method.

Over the last decade, researchers have investigated to what extent cross-project defect prediction (CPDP) shows advantages over traditional defect prediction settings. These works do not take the training and testing data of defect prediction from the same project; instead, dissimilar projects are employed. Selecting the proper training data plays an important role in terms of the success of CPDP. In this study, a novel clustering method called complexFuzzy is presented for selecting the training data of CPDP. The method reveals the most defective instances that the experimental predictors exploit in order to complete the training. To that end, a fuzzy-based membership is constructed on the data sets. Hence, overfitting (which is a crucial problem in CPDP training) is alleviated. The performance of complexFuzzy is compared to its 5 counterparts on 29 data sets by utilizing 4 classifiers. According to the obtained results, complexFuzzy is superior to other clustering methods in CPDP performance. [ABSTRACT FROM AUTHOR]

Cross‐project defect prediction (CPDP) technology refers to the constructing prediction model to predict the instance label of the target project by utilising labelled data from an external project. The challenge of CPDP methods is the distribution difference between the data from different projects. Transfer learning can transfer the knowledge from the source domain to the target domain with the aim to minimise the domain difference between different domains. However, most existing methods reduce the distribution discrepancy in the original feature space, where the features are high‐dimensional and non‐linear, which makes it hard to reduce the distribution distance between different projects. Moreover, previous works mainly consider marginal distribution or conditional distribution difference. In this study, the authors proposed a manifold embedded distribution adaptation (MDA) approach to narrow the distribution gap in manifold feature subspace. MDA maps source and target project data to manifold subspace and then joint distribution adaptation of conditional and marginal distributions is performed on manifold subspace. To evaluate the effectiveness of MDA, the authors perform extensive experiments on 20 public projects with three indicators. The experiment results show that MDA improves the average performance, but the improvement is not statistically significant in comparison to HYDRA (one of the baselines). [ABSTRACT FROM AUTHOR]

Software testing is the main method for finding software defects at present, and symmetric testing and other methods have been widely used, but these testing methods will cause a lot of waste of resources. Software defect prediction methods can reasonably allocate testing resources by predicting the defect tendency of software modules. Cross-project defect prediction methods have huge advantages when faced with missing datasets. However, most cross-project defect prediction methods are designed based on the settings of a single source project and a single target project. As the number of public datasets continues to grow, the number of source projects and defect information is increasing. Therefore, in the case of multi-source projects, this paper explores the problems existing when using multi-source projects for defect prediction. There are two problems. First, in practice, it is not possible to know in advance which source project is used to build the model to obtain the best prediction performance. Second, if an inappropriate source project is used in the experiment to build the model, it can lead to lower performance issues. According to the problems found in the experiment, the paper proposed a multi-source-based cross-project defect prediction method MSCPDP. Experimental results on the AEEEM dataset and PROMISE dataset show that the proposed MSCPDP method effectively solves the above two problems and outperforms most of the current state-of-art cross-project defect prediction methods on F1 and AUC. Compared with the six cross-project defect prediction methods, the F1 median is improved by 3.51%, 3.92%, 36.06%, 0.49%, 17.05%, and 9.49%, and the ACU median is improved by −3.42%, 8.78%, 0.96%, −2.21%, −7.94%, and 5.13%.