Cloud-assisted Industrial Systems and Applications

In recent years, cloud systems can provide flexible and onneed basis processing of vast amounts of data, as well as provisioning of other value-added services using Internet technologies. Cloud-based approaches will be applicable to all aspects of modern industrial systems, their applications and interactions in the large-scale systems. It is very necessary that more flexible infrastructure is designed to enhance performance, reliability and scalability in complex industrial systems. However, the majority of current cloud systems and the corresponding techniques primarily aim at the internet-based applications. The complex industrial systems give rise to some new issues and challenges to cloud computing since they are significantly different from those service-oriented and internet-based applications due to their inherent features (e.g., workload variations, process control, environment configurations, resource requirements, and life-cycle management, etc.). This special issue features six selected papers with high quality related to cloud-assisted industrial systems and applications. In the first article entitled BSmart Clothing: Connecting Human with Clouds and Big Data for Sustainable Health Monitoring^, Chen et al., investigate the novel sustainable health monitoring via smart clothing, one of development trends in healthcare industry. The innovative design of smart clothing facilitates unobtrusive collection of various physiological indicators of human body. In order to provide pervasive intelligence for smart clothing system, mobile healthcare cloud platform is constructed by the use of mobile internet, cloud computing and big data analytics. The authors introduce various design details, key technologies and practical implementation methods of smart clothing system. The paper also provides some novel applications powered by the proposed architecture, such as medical emergency response, emotion care, disease diagnosis and real-time tactile interaction. Especially, the ECG signals collected by smart clothing are used for mood monitoring and emotion detection. Finally, the authors highlight some of the design challenges and open issues that still need to be addressed to make smart clothing ubiquitous for a wide range of applications. External resource allocation is a very important issue in cloud-assisted industrial systems and applications because of that to solve the internal resource allocation problem, the user’s needs must first be ascertained to provide the required amount of resources. In previous work, the authors have proposed DEA to analyze the various parameters in the cloud resource allocation problem. However this method is too idealistic. In the paper entitled BLearning-based Data Envelopment Analysis for External Cloud Resource Allocation^, Cho et al. use Q-learning to train the input and output of DEA items so that DEA does not run the whole user’s data for a user every time. In this way, the authors proposed approach can provide an acceptable policy as well as much computation time can be reduced. * Jiafu Wan jiafuwan_76@163.com