The aim of this special issue is to facilitate a forum to a wide variety of researchers who can exploit state-of-the-art research in the field of soft computational (SC) approaches in relation to software engineering (SE) and its applications. This special issue is envisioned to outline the benefits by applying soft computing methods to software engineering tasks that are used to predict or estimate the following: (i) software quality, (ii) software size, (iii) software reliability, (iv) software reusability, (v) software defect, (vi) software cost, (vii) software effort, and so on. During the past decade, the use of soft computational approaches has been extended to a variety of software engineering applications. Software engineering approaches, from soft computational methods such as fuzzy systems, neural networks, evolutionary algorithms, and statistical model algorithms, are currently attractive topics in extensive software engineering research areas. This special issue provides a platform for dissemination of knowledge on both empirical and applied research in the field of software computing and software engineering.

Probabilistic and prediction models have gained momentum in software quality and software defect prediction and prevention techniques. Now these techniques have been applied to a variety of applications including Healthcare, Cloud Computing, and Big Data Analytics.

We invite researchers to submit and explore works on novel contribution and bridge the gaps in applying soft computational approaches in software engineering applications. Paper acceptance and publication will be reviewed on the basis of quality, relevance to the special issue, clarity of presentation, originality, and accuracy of results and proposed solutions.

Potential topics include, but are not limited to:

• Multicriteria decision making approaches
• Fuzzy logic techniques and algorithm for global software engineering
• Fuzzy and evolutionary computation
• Intuitionistic fuzzy information and group decision making for software industry
• Neural networks and genetic algorithm for software methods and practices
• Fuzzy neural systems for prediction and estimation of software engineering principles
• Hybrid machine intelligence techniques for global software development issues
• Hybrid fuzzy systems (fuzzy-neuro-evolutionary-rough) for software deployment
• Hybrid architectures for software systems
• Soft computing and quality management
• Artificial intelligence and software design and its applications
• Neural computing for software reliability, reusability, effort, and defect prediction
• Evolutionary computing and optimization methods for empirical software engineering
• Empirical studies of knowledge management, software development, and computational intelligence
• Predictive and probabilistic models including Bayesian networks and chaotic theories