Abstract Event prediction is essential in social network (SN) analysis to study the SN's evolutionary patterns (communities). Machine learning (ML) models are often used to predict events in SN communities. The ML algorithms manifest the results with biasness for the same dataset. Hence, the performance of an ML model requires validation for the unseen data to avoid biasness in learning. Generally, researchers use the generative adversarial network (GAN) model for generating realistic sample data to enhance the prediction of events. It is challenging for the discriminator to learn features using a single layer with similar weights in a conventional GAN technique. Therefore, this article proposes an improved version of the GAN model named generative adversarial network classifier (GAN‐C). The proposed GAN‐C model contains an additional layer, called classifier, that generates different feature maps. Wherein weights are adjusted dynamically based on the conditions to predict the events. To be precise, conditioning the weights in a classifier layer using entropy values of the features is a simple and effective way to minimize the classifier loss function (categorical cross‐entropy). GAN‐C model results in 16% loss up to 10 batches, and after that, the loss becomes negligible and can generate non‐overlapping events. The gaps between such non‐overlapping events are analyzed using the Jensen–Shannon divergence technique. The experimental results show that the existing single‐GAN and multi‐GAN methods predict events with 79.34% and 82.17% accuracy, respectively. While the proposed GAN‐C comparatively predicts events with improved accuracy of 88.56% on the same dataset. The data generated by the GAN‐C model are also approximately 55.85% and 80.59% more realistic than multi‐GAN and single‐GAN, respectively, based on root mean square error and inception score comparisons. GAN‐C is also approximately 68.01% faster than other GAN models. Thus, this article's theoretical and experimental analysis justifies that GAN‐C works suitably for predicting events in a massive dataset.

In this paper, three meta-heuristic techniques are studied and their results are compared for pairwise testing by generating the test cases. The aim of this paper is to minimize the number of test cases that are needed to be checked for pairwise testing. The techniques studied are Genetic Algorithm (GA), Particle Swarm Optimization (PSO), and Elephant Herding Optimization (EHO). The test cases thus generated check the software for each pair of input parameters. The results generated using pairwise testing show that PSO and EHO perform slightly better than GA for most of the input configurations.

Summary Software testers always face the dilemma of whether to retest the software with all the test cases or select a few of them on the basis of their fault detection ability. This paper introduces a novel approach to minimizing the test suite as an integer linear programming problem with optimal results. The minimization method uses the cohesion values of the program parts affected by the changes made to the program. The hypothesis is that the program parts with low cohesion values are more prone to errors. This assumption is validated on the mutation fault detection ability of the test cases. The experimental study carried out on 30 programs evaluates the effectiveness and usefulness of the proposed framework. The experimental results show that the minimized test suite can efficiently reveal the errors and ensure acceptable software quality. Copyright © 2017 John Wiley & Sons, Ltd.

Program slicing has numerous applications in software engineering activities like debugging, testing, maintenance, model checking etc. The main objective of this paper is to automate the generation of System Dependency Graphs (SDG) for aspect-oriented programs to efficiently compute accurate slices. The construction of SDG is automated by analysing the byte code of aspect-oriented programs that incorporates the representation of aspect-oriented features. After constructing the SDG, we propose a slicing algorithm that uses the intermediate graph and computes slices for a given AOP. To implement our proposed slicing technique, we have developed a prototype tool that takes an AOP as input and compute its slices using our proposed slicing algorithm. To evaluate our proposed technique, we have considered some case studies by taking open source projects. The comparative study of our proposed slicing algorithm with some existing algorithms show that our approach is an efficient and scalable approach of slicing for different applications with respect to aspect-oriented programs.