Heterogeneous defect prediction (HDP) predicts defects for the current project (target) using heterogeneous data from other projects (source), which can improve software quality effectively. The ability to reduce the distribution divergence between the source and target project is crucial to the performance of HDP. Existing HDP methods address this issue only by using feature adaptation techniques, i.e., feature matching and feature transformation. However, without considering instance adaptability differences, they cannot fully exploit the potential of instance adaptation and thus cannot make the source and target distribution completely matched. To address this problem, we propose a novel HDP approach called joint instance and feature adaptation (JIFA) combining both instance adaptation and feature adaptation to narrow the gap between projects. Making joint use of both adaptation techniques, JIFA not only further reduces the distribution discrepancy but also enhances its robustness to abnormal outliers. Besides, discriminant information is also preserved in JIFA so that a better classification boundary can be obtained. Particularly, JIFA applies to both heterogeneous and homogeneous cross-project defect prediction (CPDP) tasks. The experimental results from 22 projects indicate that JIFA outperforms a range of advanced heterogeneous and homogeneous CPDP approaches.

Context: Software defect number prediction (SDNP) helps allocate limited testing resources by ranking software modules according to the predicted defect numbers. However, the highly skewed distribution of defects greatly degrades the performance of SDNP models by preventing SDNP models from ranking software modules accurately. Objective: This paper introduces a novel subspace hybrid sampling ensemble (SHSE) method based on feature subspace construction, hybrid sampling , and ensemble learning for building high-performance SDNP models. Method: Specifically, we first construct a series of feature subspace to ensure the diversity of base learners. In each of feature subspace, we then use the proposed hybrid sampling method to balance the training subset without losing too much information and introducing lots of noisy data caused by only using undersampling or oversampling techniques. Finally, we train each base learner and combine them by using the proposed weighted ensemble strategy. Experiments are performed on 27 public defect datasets. We compare SHSE with five state-of-the-art resampling-based models and four zero-inflated/hurdle models in terms of the ranking performance measure fault-percentile-average (FPA). To demonstrate the effectiveness of SHSE, two statistical testing methods including Wilcoxon Signed-rank test and Scott–Knott Effect Size Difference test are utilized. Cliff’s δ is also computed for quantifying the difference when there is significant difference between SHSE and each baseline. Results: The experimental results show that SHSE significantly outperforms the baselines and improves the performance over each baseline with as least medium effect size on most datasets. On average, SHSE improves the performance over the resampling-based methods by 8.7% ∼ 14.4% and the zero-inflate/hurdle models by 10.3% ∼ 15.2%. Conclusion: It can be concluded that SHSE is a more promising alternative for software defect number prediction.

Abstract Cross‐project defect prediction (CPDP) is used to build defect prediction models when data from the target project are not enough. There has been several approaches to improve the performance of CPDP, such as feature transformation and instance selection methods. However, existing techniques are strongly dependent on the target data to reduce the distribution discrepancy between source and target projects. That is, the performance of these methods is determined by the effectiveness of feature transformation or the similarity between two projects. Additionally, when there is a large amount of source data that needs to be matched with target data, it will take much time and reduce the efficiency of model construction. Therefore, it is vital to explore a target project‐agnostic approach to build CPDP models. This paper presents a Weighted Isolation Forest with class Label information Filter (WIFLF) to relieve the issues above. Four groups of datasets from AEEEM, Relink and PROMISE Data Repository are used to conduct CPDP models. Besides, WIFLF is compared with 12 approaches. The experimental results indicate that WIFLF significantly outperforms all the baselines. Specifically, WIFLF with random forest significantly improves the performance over the baselines on average by at least 14.64% and 4.90% with respect to Skewed F‐Measure and G‐Measure, respectively.

Cross-project defect prediction (CPDP) refers to predicting defects in the target project lacking of defect data by using prediction models trained on the historical defect data of other projects (i.e., source data). However, CPDP requires the source and target projects have common metric set (CPDP-CM). Recently, heterogeneous defect prediction (HDP) has drawn the increasing attention, which predicts defects across projects having heterogeneous metric sets. However, building high-performance HDP methods remains a challenge owing to several serious challenges including class imbalance problem, nonlinear, and the distribution differences between source and target datasets. In this paper, we propose a novel kernel spectral embedding transfer ensemble (KSETE) approach for HDP. KSETE first addresses the class-imbalance problem of the source data and then tries to find the latent common feature space for the source and target datasets by combining kernel spectral embedding, transfer learning, and ensemble learning. Experiments are performed on 22 public projects in both HDP and CPDP-CM scenarios in terms of multiple well-known performance measures such as, AUC, G-Measure, and MCC. The experimental results show that (1) KSETE improves the performance over previous HDP methods by at least 22.7, 138.9, and 494.4 percent in terms of AUC, G-Measure, and MCC, respectively. (2) KSETE improves the performance over previous CPDP-CM methods by at least 4.5, 30.2, and 17.9 percent in AUC, G-Measure, and MCC, respectively. It can be concluded that the proposed KSETE is very effective in both the HDP scenario and the CPDP-CM scenario.

Adaptive testing (AT) is a software testing approach that uses a feedback mechanism to enhance test effectiveness. Its testing strategy can be adjusted online by using the testing data collected during the software testing process. However, it requires complex parameter estimation which results in excessive computational overhead that may hinder the applicability of AT. In this paper, we propose an approach called AT based on moment estimation (AT-ME) to address this problem. The proposed approach uses moment estimation to serve as the algorithm of parameter estimation, which reduces the complexity of AT-ME. In addition, a dynamic length for testing action is set to limit the number of decisions without influencing the test effectiveness. The proposed approach has been validated on the Siemens test suite, which includes seven real programs. The experiments show that AT-ME can reduce the computational overhead of AT without compromising overall testing efficiency. Results demonstrate that AT-ME is a feasible and effective AT strategy.

Abstract Residual defects at the time of delivery are an important concern for safety critical software systems. Suppliers and customers are urged to get evidence for what they can do to reduce residual defects. Thus, it is meaningful to learn from historical data concerning the kinds of defects that have escaped from the existing quality assurance approaches and the factors that lead to the residual defects. A total of 3747 defects from 70 software systems developed by 29 Chinese aviation organizations were collected from acceptance tests during the last 5 years. For all these organizations, 38 domain experts from the industry assessed the process consistency to the standard built in the framework of Capability Maturity Model (CMM). Results demonstrate that the process improvement in the range of high consistency is effective in reducing total defects, as well as the minor and severe defects. The high consistency adoption of the practices in CMM Level 1 to Level 3 is more effective in reducing minor defects than severe defects. Causal analysis was performed to investigate the underlying mechanisms. Results reveal that individual cognitive failures cause 87% of severe defects. More approaches to help software developers manage their interior cognitive process are needed for improving software quality in the future. Copyright © 2015 John Wiley & Sons, Ltd.