Spectrum-based fault localization (SBFL) generates a ranked list of suspicious elements by using the program execution spectrum, but the excessive number of elements ranked in parallel results in low localization accu...Spectrum-based fault localization (SBFL) generates a ranked list of suspicious elements by using the program execution spectrum, but the excessive number of elements ranked in parallel results in low localization accuracy. Most researchers consider intra-class dependencies to improve localization accuracy. However, some studies show that inter-class method call type faults account for more than 20%, which means such methods still have certain limitations. To solve the above problems, this paper proposes a two-phase software fault localization based on relational graph convolutional neural networks (Two-RGCNFL). Firstly, in Phase 1, the method call dependence graph (MCDG) of the program is constructed, the intra-class and inter-class dependencies in MCDG are extracted by using the relational graph convolutional neural network, and the classifier is used to identify the faulty methods. Then, the GraphSMOTE algorithm is improved to alleviate the impact of class imbalance on classification accuracy. Aiming at the problem of parallel ranking of element suspicious values in traditional SBFL technology, in Phase 2, Doc2Vec is used to learn static features, while spectrum information serves as dynamic features. A RankNet model based on siamese multi-layer perceptron is constructed to score and rank statements in the faulty method. This work conducts experiments on 5 real projects of Defects4J benchmark. Experimental results show that, compared with the traditional SBFL technique and two baseline methods, our approach improves the Top-1 accuracy by 262.86%, 29.59% and 53.01%, respectively, which verifies the effectiveness of Two-RGCNFL. Furthermore, this work verifies the importance of inter-class dependencies through ablation experiments.展开更多
Software debugging accounts for a vast majority of the financial and time costs in software developing and maintenance. Thus, approaches of software fault localization that can help automate the debugging process have...Software debugging accounts for a vast majority of the financial and time costs in software developing and maintenance. Thus, approaches of software fault localization that can help automate the debugging process have become a hot topic in the field of software engineering. Given the great demand for software fault localization, an approach based on the artificial bee colony （ABC） algorithm is proposed to be integrated with other related techniques. In this process, the source program is initially instrumented after analyzing the dependence information. The test case sets are then compiled and run on the instrumented program, and execution results are input to the ABC algorithm. The algorithm can determine the largest fitness value and best food source by calculating the average fitness of the employed bees in the iteralive process. The program unit with the highest suspicion score corresponding to the best test case set is regarded as the final fault localization. Experiments are conducted with the TCAS program in the Siemens suite. Results demonstrate that the proposed fault localization method is effective and efficient. The ABC algorithm can efficiently avoid the local optimum, and ensure the validity of the fault location to a larger extent.展开更多
The most resource-intensive and laborious part of debugging is finding the exact location of the fault from the more significant number of code snippets.Plenty of machine intelligence models has offered the effective ...The most resource-intensive and laborious part of debugging is finding the exact location of the fault from the more significant number of code snippets.Plenty of machine intelligence models has offered the effective localization of defects.Some models can precisely locate the faulty with more than 95%accuracy,resulting in demand for trustworthy models in fault localization.Confidence and trustworthiness within machine intelligencebased software models can only be achieved via explainable artificial intelligence in Fault Localization(XFL).The current study presents a model for generating counterfactual interpretations for the fault localization model’s decisions.Neural system approximations and disseminated presentation of input information may be achieved by building a nonlinear neural network model.That demonstrates a high level of proficiency in transfer learning,even with minimal training data.The proposed XFL would make the decisionmaking transparent simultaneously without impacting the model’s performance.The proposed XFL ranks the software program statements based on the possible vulnerability score approximated from the training data.The model’s performance is further evaluated using various metrics like the number of assessed statements,confidence level of fault localization,and TopN evaluation strategies.展开更多
A software fault injection system SFIS is designed,which consists of the target system plus a fault injector,fault library,workload,data collector,and data analyzer. A serial communication mechanism is adopted to simu...A software fault injection system SFIS is designed,which consists of the target system plus a fault injector,fault library,workload,data collector,and data analyzer. A serial communication mechanism is adopted to simulate the factual work environment. Then a fault model is built for single particle event,which can be denoted as FM=(FL,FT). FL stands for fault location,and FT stands for fault type. The fault model supports three temporal faults: transient,intermittent,and permanent. During the experiments implemented by SFIS,the software interruption method is adopted to inject transient faults,and step trace method is adopted to inject permanent faults into the target system. The experiment results indicate that for the injected transient code segment faults,2.8 % of them do not affect the program output,80.1% of them are detected by the built-in error detection in the system,and 17.1% of them are not detected by fault detection mechanism. The experiment results verify the validity of the fault injection method.展开更多
In recent decades,many software reliability growth models（SRGMs） have been proposed for the engineers and testers in measuring the software reliability precisely.Most of them is established based on the non-homogene...In recent decades,many software reliability growth models（SRGMs） have been proposed for the engineers and testers in measuring the software reliability precisely.Most of them is established based on the non-homogeneous Poisson process（NHPP）,and it is proved that the prediction accuracy of such models could be improved by adding the describing of characterization of testing effort.However,some research work indicates that the fault detection rate（FDR） is another key factor affects final software quality.Most early NHPPbased models deal with the FDR as constant or piecewise function,which does not fit the different testing stages well.Thus,this paper first incorporates a multivariate function of FDR,which is bathtub-shaped,into the NHPP-based SRGMs considering testing effort in order to further improve performance.A new model framework is proposed,and a stepwise method is used to apply the framework with real data sets to find the optimal model.Experimental studies show that the obtained new model can provide better performance of fitting and prediction compared with other traditional SRGMs.展开更多
As requirements for system quality have increased, the need for high system reliability is also increasing. Soflnvare systems are extremely important, in terms of enhanced reliability and stability, for providing high...As requirements for system quality have increased, the need for high system reliability is also increasing. Soflnvare systems are extremely important, in terms of enhanced reliability and stability, for providing high quality services to customers. However, because of the complexity of software systems, soft-ware development can be time-consuming and expensive. Many statistical models have been developed in the past years to estimate soflnvare reliability. In this paper, we propose a new three-parameter fault-detection software reliability model with the uncertainty of operating environments. The explicit mean value function solution for the proposed model is presented. Examples are presented to illustrate the goodness-of-fit of the proposed model and several existing non-homogeneous Poisson process （NHPP） models based on three sets of failure data collected from software applications. The results show that the proposed model fits significantly better than other existing NHPP models based on three criteria such as mean squared error （MSE）, predictive ratio risk （PRR）, and predictive power （PP）.展开更多
基金funded by the Youth Fund of the National Natural Science Foundation of China(Grant No.42261070).
文摘Spectrum-based fault localization (SBFL) generates a ranked list of suspicious elements by using the program execution spectrum, but the excessive number of elements ranked in parallel results in low localization accuracy. Most researchers consider intra-class dependencies to improve localization accuracy. However, some studies show that inter-class method call type faults account for more than 20%, which means such methods still have certain limitations. To solve the above problems, this paper proposes a two-phase software fault localization based on relational graph convolutional neural networks (Two-RGCNFL). Firstly, in Phase 1, the method call dependence graph (MCDG) of the program is constructed, the intra-class and inter-class dependencies in MCDG are extracted by using the relational graph convolutional neural network, and the classifier is used to identify the faulty methods. Then, the GraphSMOTE algorithm is improved to alleviate the impact of class imbalance on classification accuracy. Aiming at the problem of parallel ranking of element suspicious values in traditional SBFL technology, in Phase 2, Doc2Vec is used to learn static features, while spectrum information serves as dynamic features. A RankNet model based on siamese multi-layer perceptron is constructed to score and rank statements in the faulty method. This work conducts experiments on 5 real projects of Defects4J benchmark. Experimental results show that, compared with the traditional SBFL technique and two baseline methods, our approach improves the Top-1 accuracy by 262.86%, 29.59% and 53.01%, respectively, which verifies the effectiveness of Two-RGCNFL. Furthermore, this work verifies the importance of inter-class dependencies through ablation experiments.
文摘Software debugging accounts for a vast majority of the financial and time costs in software developing and maintenance. Thus, approaches of software fault localization that can help automate the debugging process have become a hot topic in the field of software engineering. Given the great demand for software fault localization, an approach based on the artificial bee colony （ABC） algorithm is proposed to be integrated with other related techniques. In this process, the source program is initially instrumented after analyzing the dependence information. The test case sets are then compiled and run on the instrumented program, and execution results are input to the ABC algorithm. The algorithm can determine the largest fitness value and best food source by calculating the average fitness of the employed bees in the iteralive process. The program unit with the highest suspicion score corresponding to the best test case set is regarded as the final fault localization. Experiments are conducted with the TCAS program in the Siemens suite. Results demonstrate that the proposed fault localization method is effective and efficient. The ABC algorithm can efficiently avoid the local optimum, and ensure the validity of the fault location to a larger extent.
文摘The most resource-intensive and laborious part of debugging is finding the exact location of the fault from the more significant number of code snippets.Plenty of machine intelligence models has offered the effective localization of defects.Some models can precisely locate the faulty with more than 95%accuracy,resulting in demand for trustworthy models in fault localization.Confidence and trustworthiness within machine intelligencebased software models can only be achieved via explainable artificial intelligence in Fault Localization(XFL).The current study presents a model for generating counterfactual interpretations for the fault localization model’s decisions.Neural system approximations and disseminated presentation of input information may be achieved by building a nonlinear neural network model.That demonstrates a high level of proficiency in transfer learning,even with minimal training data.The proposed XFL would make the decisionmaking transparent simultaneously without impacting the model’s performance.The proposed XFL ranks the software program statements based on the possible vulnerability score approximated from the training data.The model’s performance is further evaluated using various metrics like the number of assessed statements,confidence level of fault localization,and TopN evaluation strategies.
基金National Defense Scientific Work Committee Foundation of China (Grant No.16.6.2.7).
文摘A software fault injection system SFIS is designed,which consists of the target system plus a fault injector,fault library,workload,data collector,and data analyzer. A serial communication mechanism is adopted to simulate the factual work environment. Then a fault model is built for single particle event,which can be denoted as FM=(FL,FT). FL stands for fault location,and FT stands for fault type. The fault model supports three temporal faults: transient,intermittent,and permanent. During the experiments implemented by SFIS,the software interruption method is adopted to inject transient faults,and step trace method is adopted to inject permanent faults into the target system. The experiment results indicate that for the injected transient code segment faults,2.8 % of them do not affect the program output,80.1% of them are detected by the built-in error detection in the system,and 17.1% of them are not detected by fault detection mechanism. The experiment results verify the validity of the fault injection method.
基金supported by the National Natural Science Foundation of China(61070220)the Anhui Provincial Natural Science Foundation(1408085MKL79)
文摘In recent decades,many software reliability growth models（SRGMs） have been proposed for the engineers and testers in measuring the software reliability precisely.Most of them is established based on the non-homogeneous Poisson process（NHPP）,and it is proved that the prediction accuracy of such models could be improved by adding the describing of characterization of testing effort.However,some research work indicates that the fault detection rate（FDR） is another key factor affects final software quality.Most early NHPPbased models deal with the FDR as constant or piecewise function,which does not fit the different testing stages well.Thus,this paper first incorporates a multivariate function of FDR,which is bathtub-shaped,into the NHPP-based SRGMs considering testing effort in order to further improve performance.A new model framework is proposed,and a stepwise method is used to apply the framework with real data sets to find the optimal model.Experimental studies show that the obtained new model can provide better performance of fitting and prediction compared with other traditional SRGMs.
文摘As requirements for system quality have increased, the need for high system reliability is also increasing. Soflnvare systems are extremely important, in terms of enhanced reliability and stability, for providing high quality services to customers. However, because of the complexity of software systems, soft-ware development can be time-consuming and expensive. Many statistical models have been developed in the past years to estimate soflnvare reliability. In this paper, we propose a new three-parameter fault-detection software reliability model with the uncertainty of operating environments. The explicit mean value function solution for the proposed model is presented. Examples are presented to illustrate the goodness-of-fit of the proposed model and several existing non-homogeneous Poisson process （NHPP） models based on three sets of failure data collected from software applications. The results show that the proposed model fits significantly better than other existing NHPP models based on three criteria such as mean squared error （MSE）, predictive ratio risk （PRR）, and predictive power （PP）.
