International Journal of Software Engineering and Knowledge Engineering

Significant effort is being put into developing industrial applications for artificial intelligence (AI), especially those using machine learning (ML) techniques. Despite the intensive support for building ML applications, there are still challenges when it comes to evaluating, assuring, and improving the quality or dependability. The difficulty stems from the unique nature of ML, namely, system behavior is derived from training data not from logical design by human engineers. This leads to black-box and intrinsically imperfect implementations that invalidate many principles and techniques in traditional software engineering. In light of this situation, the Japanese industry has jointly worked on a set of guidelines for the quality assurance of AI systems (in the Consortium of Quality Assurance for AI-based Products and Services) from the viewpoint of traditional quality-assurance engineers and test engineers. We report on the second version of these guidelines, which cover a list of quality evaluation aspects, catalogue of current state-of-the-art techniques, and domain-specific discussions in five representative domains. The guidelines provide significant insights for engineers in terms of methodologies and designs for tests driven by application-specific requirements.

Software effort estimation models are typically developed based on an underlying assumption that all data points are equally relevant to the prediction of effort for future projects. The dynamic nature of several aspects of the software engineering process could mean that this assumption does not hold in at least some cases. This study employs three kernel estimator functions to test the stationarity assumption in five software engineering datasets that have been used in the construction of software effort estimation models. The kernel estimators are used in the generation of nonuniform weights which are subsequently employed in weighted linear regression modeling. In each model, older projects are assigned smaller weights while the more recently completed projects are assigned larger weights, to reflect their potentially greater relevance to present or future projects that need to be estimated. Prediction errors are compared to those obtained from uniform models. Our results indicate that, for the datasets that exhibit underlying nonstationary processes, uniform models are more accurate than the nonuniform models; that is, models based on kernel estimator functions are worse than the models where no weighting was applied. In contrast, the accuracies of uniform and nonuniform models for datasets that exhibited stationary processes were essentially equivalent. Our analysis indicates that as the heterogeneity of a dataset increases, the effect of stationarity is overridden. The results of our study also confirm prior findings that the accuracy of effort estimation models is independent of the type of kernel estimator function used in model development.

Modern compilers provide a huge number of optional compilation optimization options. It is necessary to select the appropriate compilation optimization options for different programs or applications. To mitigate this problem, machine learning is widely used as an efficient technology. How to ensure the integrity and effectiveness of program information is the key to problem mitigation. In addition, when selecting the best compilation optimization option, the optimization goals are often execution speed, code size, and CPU consumption. There is not much research on program reliability. This paper proposes a Gate Graph Attention Neural Network (GGANN)-based compilation optimization option selection model. The data flow and function-call information are integrated into the abstract syntax tree as the program graph-based features. We extend the deep neural network based on GGANN and build a learning model that learns the heuristics method for program reliability. The experiment is performed under the Clang compiler framework. Compared with the traditional machine learning method, our model improves the average accuracy by 5–11% in the optimization option selection for program reliability. At the same time, experiments show that our model has strong scalability.

Software dynamic birthmark techniques construct birthmarks using the captured execution traces from running the programs, which serve as one of the most promising methods for obfuscation-resilient software plagiarism detection. However, due to the perturbation caused by non-deterministic thread scheduling in multi-threaded programs, such dynamic approaches optimized for sequential programs may suffer from the randomness in multi-threaded program plagiarism detection. In this paper, we propose a new dynamic thread-aware birthmark FPBirth to facilitate multi-threaded program plagiarism detection. We first explore dynamic monitoring to capture multiple execution traces with respect to system calls for each multi-threaded program under a specified input, and then leverage the Apriori algorithm to mine frequent patterns to formulate our dynamic birthmark, which can not only depict the program’s behavioral semantics, but also resist the changes and perturbations over execution traces caused by the thread scheduling in multi-threaded programs. Using FPBirth, we design a multi-threaded program plagiarism detection system. The experimental results based on a public software plagiarism sample set demonstrate that the developed system integrating our proposed birthmark FPBirth copes better with multi-threaded plagiarism detection than alternative approaches. Compared against the dynamic birthmark System Call Short Sequence Birthmark (SCSSB), FPBirth achieves 12.4%, 4.1% and 7.9% performance improvements with respect to union of resilience and credibility (URC), F-Measure and matthews correlation coefficient (MCC) metric, respectively.

The activeness of regional business entities, like restaurants, cinemas and shopping malls, represents the evolvement of their corresponding commercial districts, whose prediction helps practitioners grasp the trend of commercial development and provides support for urban layout. On the other hand, online social network services, such as Yelp, are generating massive online reviews toward business entities every day, which provide a solid data source for the prediction of regional commercial activeness and entity condition through big data technology rather than applying business data with limited access and poor time efficiency. Inspired by the outstanding performance of deep learning in the field of image and video processing, this paper proposes a deep spatio-temporal residual network (DSTRN) model for regional commercial activeness prediction using online reviews and check-in records of commercial entities. Furthermore, aiming at predicting business trend of entities, we also propose a novel multi-view entity condition prediction model (SBCE) based on online views, along with business attributes and regional commercial activeness. The experiments on the public Yelp datasets demonstrate that both DSTRN and SBCE outperform the compared approaches.

Stack Overflow is the most popular programming question and answer community that continuously receives a large number of questions every day. To ensure the quality of questions, the community grants privileges for the moderators and a group of experienced users to review the quality of questions and close the low-quality ones (e.g. duplicate or irrelevant questions). The review process is a typical crowdsourcing job that relies on users’ volunteer participation, and the current practices of closing questions in Stack Overflow face two aspects of challenges: (1) an obvious increase in both the absolute number and the percentage of “closed” questions; (2) a considerable decrease in participation willingness of experienced users to close questions. In order to solve the problem, we present a novel model of user willingness for reviewing and voting questions by incorporating four types of user activity history, including questions, answers, comments and votes of closing questions. Then we propose an automatic recommendation method based on the model to assign experienced users proper questions, to utilize the forces of them to close questions. The evaluation shows that the successful recommendation probability in the top 5, top 10, top 20, top 30, top 40, top 50 users are 48.23%, 58.93%, 68.83%, 74.27%, 78.13% and 81%, respectively.

In recent years, the amount of user check-in data has significantly increased on social network platforms. Such data is an ideal source for characterizing user behaviors and identifying similar users, contributing to many research areas (e.g. user-based collaborative filtering). However, existing trajectory-based user similarity analysis approaches do not distinguish the effects of geographical factors at a fine-grained level, and thus are not able to unleash the full power of semantic information that is hidden in the trajectory. In this paper, we have proposed an effective graph embedding approach to identify similar users based on their check-in data. Specifically, we firstly identify meaningful concepts of user check-in data, based on which we design two metagraphs for representing features of similar user behaviors. Then we characterize each user with a sequence of nodes that are derived through a metagraph-guided random walk strategy. Such sequences are embedded to generate meaningful user vectors for measuring user similarity and eventually identifying similar users. We have evaluated our proposal on three public datasets, the results of which show that our approach is 4% higher than the best existing approach in terms of F1-measure.

With the development of Web 2.0, social media such as Twitter and Sina Weibo have become an essential platform for disseminating hot events. Simultaneously, due to the free policy of microblogging services, users can post user-generated content freely on microblogging platforms. Accordingly, more and more hot events on microblogging platforms have been labeled as spammers. Spammers will not only hurt the healthy development of social media but also introduce many economic and social problems. Therefore, the government and enterprises must distinguish whether a hot event on microblogging platforms is a spammer or is a naturally-developing event. In this paper, we focus on the hot event list on Sina Weibo and collect the relevant microblogs of each hot event to study the detecting methods of spammers. Notably, we develop an integral feature set consisting of user profile, user behavior, and user relationships to reflect various factors affecting the detection of spammers. Then, we employ typical machine learning methods to conduct extensive experiments on detecting spammers. We use a real data set crawled from the most prominent Chinese microblogging platform, Sina Weibo, and evaluate the performance of 10 machine learning models with five sampling methods. The results in terms of various metrics show that the Random Forest model and the over-sampling method achieve the best accuracy in detecting spammers and non-spammers.

Both complexity of code change for bug fixing and bug severity play an important role in release planning when considering which bugs should be fixed in a specific release under certain constraints. This work investigates whether there are significant differences between bugs of different severity levels regarding the complexity of code change for fixing the bugs. Code change complexity is measured by the number of modified lines of code, source files, and packages, as well as the entropy of code change. We performed a case study on 20 Apache open source software (OSS) projects using commit records and bug reports. The study results show that (1) for bugs of high severity levels (i.e. Blocker, Critical and Major in JIRA), there is no significant difference on the complexity of code change for fixing bugs of different severity levels for most projects, while (2) for bugs of low severity levels (i.e. Major, Minor and Trivial in JIRA), fixing bugs of a higher severity level needs significantly more complex code change than fixing bugs of a lower severity level for most projects. These findings provide useful and practical insights for effort estimation and release planning of OSS development.

Spiking Neuron Network (SNN) uses spike sequence for data processing, so it has an excellent characteristic of low power consumption. However, due to the immaturity of learning algorithm, the multiplayer network training has difficulty in convergence. Utilizing the mature learning algorithm and fast training speed of the back-propagation network, this paper proposes a method to converse the Convolutional Neural Network (CNN) to the SNN. First, the adjustment strategy for CNN is introduced. Then after training, the weight parameters in the model are extracted, which is the corresponding synaptic weight in the layer of the SNN. Finally, a new threshold-setting algorithm based on feedback is proposed to solve the critical problem of the threshold setting of neurons in the SNN. We evaluate our method on the CIFAR-10 datasets released by Hinton’s team. The experimental results show that the image classification accuracy of the SNN is more than 98% of that of CNN, and the theoretical value of power consumption per second is 3.9mW.

Selecting a framework and documenting the rationale for choosing it is an essential task for system architects. Different framework selection approaches have been proposed in the literature. However, none of these connect frameworks to qualities based on their implemented patterns and tactics. In this paper, we propose a way to semi-automatically compare the quality attributes of frameworks by extracting the patterns and tactics from a framework’s source code and documenting them to connect frameworks to requirements upon which a selection can be made. We use a tool called Archie (a tool used to extract tactics from a Java-based system’s code) to extract the patterns/tactics from the implementation code of frameworks. We then document and model these patterns/tactics and their impact on qualities using the Goal-oriented Requirements Language (GRL). After that, we reuse these models of patterns and tactics to model frameworks in terms of their implemented patterns and tactics. The satisfaction level of the quality requirements integrated with other criteria such as the preferences of an architect provide architects with a tool for comparing different frameworks and documenting their rationale for choosing a framework. As a validation of the approach, we apply it to three realistic case studies with promising results.

The distributed multiple autonomous network has become the main trend of modern information systems, such as Cloud, Service-Oriented Architecture (SOA) and Internet of Things (IoT). Access control in such a heterogeneous and dynamic system has become a major information security challenge, which hinders the sharing of resources and information. In this work, we present an Attribute-Based Access Control (ABAC) model for cross-domain access control. The proposed access control model comprises a boundary control server designed to provide cross-domain access control capability. An eXtensible Access Control Markup Language (XACML) policy model-based implementation is introduced. Process and implementation show the proposed model alleviates the security risk on the domain boundary during the cross-domain access control process.