Representation-based methods have found widespread applications in various classification tasks. However, these methods cannot deal effectively with imbalanced data scenarios. They tend to neglect the importance of minority samples, resulting in bias toward the majority class. To address this limitation, we propose a density-based discriminative nonnegative representation approach for imbalanced classification tasks. First, a new class-specific regularization term is incorporated into the framework of a nonnegative representation based classifier (NRC) to reduce the correlation between classes and improve the discrimination ability of the NRC. Second, a weight matrix is generated based on the hybrid density information of each sample’s neighbors and the decision boundary, which can assign larger weights to minority samples and thus reduce the preference for the majority class. Furthermore, the resulting model can be efficiently optimized through the alternating direction method of multipliers. Extensive experimental results demonstrate that our proposed method is superior to numerous state-of-the-art imbalanced learning methods.

Measurement of software trustworthiness is an important research field in the software engineering, which is very useful for analyzing the software quality. In this paper, we propose a mathematical programming approach to allocate the trustworthy degree to each sub-attribute of some software attribute appropriately and then to make the trustworthy degree of this attribute maximize under some constraint conditions. Some sufficient or necessary conditions for analyzing this mathematical programming problem are investigated. Moreover, a polynomial allocation algorithm is given for computing the optimal solution of this mathematical programming. Finally, an example is given in order to show the significance of this work. The results obtained here are useful for improving the software quality by adjusting the trustworthy degree of each sub-attribute under the same cost.

With the increasing number of software projects, within‐project defect prediction (WPDP) has already been unable to meet the demand, and cross‐project defect prediction (CPDP) is playing an increasingly significant role in the area of software engineering. The classic CPDP methods mainly concentrated on applying metric features to predict defects. However, these approaches failed to consider the rich semantic information, which usually contains the relationship between software defects and context. Since traditional methods are unable to exploit this characteristic, their performance is often unsatisfactory. In this paper, a transfer long short‐term memory (TLSTM) network model is first proposed. Transfer semantic features are extracted by adding a transfer learning algorithm to the long short‐term memory (LSTM) network. Then, the traditional metric features and semantic features are combined for CPDP. First, the abstract syntax trees (AST) are generated based on the source codes. Second, the AST node contents are converted into integer vectors as inputs to the TLSTM model. Then, the semantic features of the program can be extracted by TLSTM. On the other hand, transferable metric features are extracted by transfer component analysis (TCA). Finally, the semantic features and metric features are combined and input into the logical regression (LR) classifier for training. The presented TLSTM model performs better on the f ‐measure indicator than other machine and deep learning models, according to the outcomes of several open‐source projects of the PROMISE repository. The TLSTM model built with a single feature achieves 0.7% and 2.1% improvement on Log4j‐1.2 and Xalan‐2.7, respectively. When using combined features to train the prediction model, we call this model a transfer long short‐term memory for defect prediction (DPTLSTM). DPTLSTM achieves a 2.9% and 5% improvement on Synapse‐1.2 and Xerces‐1.4.4, respectively. Both prove the superiority of the proposed model on the CPDP task. This is because LSTM capture long‐term dependencies in sequence data and extract features that contain source code structure and context information. It can be concluded that: (1) the TLSTM model has the advantage of preserving information, which can better retain the semantic features related to software defects; (2) compared with the CPDP model trained with traditional metric features, the performance of the model can validly enhance by combining semantic features and metric features.

Software trustworthiness is an important research field in software engineering. In order to appropriately evaluate it, some different measurement approaches have been proposed, which have important guiding significance for improving software trustworthiness. Recently, we have investigated attributes-based approaches. That is, how to maximize trustworthy degree of some software satisfying a given threshold by adjusting every attribute value such that the cost is minimal, i.e., the sum of all attribute values is as small as possible. The work is helpful to improve the software quality under the same cost. This paper continues this work and considers a reallocation approach to dealing with the problem that the threshold and the minimal constraints of every attribute values dynamically increase. In this process, the costs of trustworthiness improvement should be ensured to be minimal. For this purpose, we firstly define a reallocation model by mathematical programming. Then we introduce the notion of growth function. Based on this, a polynomial reallocation algorithm is designed to solve the above reallocation model. Finally, we verify our work on spacecraft softwares and the results show that this work is valid.