2016 International Conference on Advanced Materials and Energy Sustainability [AMES2016] was held in Wuhan, Hubei, China during May 27-29, 2016. AMES2016 aims to bring together researchers, engineers, and students to participate in the discussion of Advanced Materials and Energy Sustainability. AMES2016 features unique mixed topics of Advanced Materials and Related Technology, Energy Management and Renewable Energy and Environmental Engineering and Sustainable Development.The conference program committee is greatly honoured to have three renowned experts for taking time off to present their keynotes to the conference. In addition, we have put together five invited sessions. There are a total of 260 submissions from various parts of the world. Among them, 87 articles are compiled into this proceedings, covering Polymers, Composites and Mesoporous Materials; Applications of Micro- and Nano-Technology and Materials; Processing Technologies and Computational Methods in Area of Materials Science; Smart Grid, Micro-Grid Concepts; Fuels, Combustion and Materials Handling; Advanced and Renewable Energy Systems; Sustainable Management of Environment; Sustainable Cities and Communities, Transportation and Wind Energy Systems and Technologies.

This book provides theoretical background and state-of-the-art findings in artificial intelligence and cybersecurity for industry 4.0 and helps in implementing AI-based cybersecurity applications. Machine learning-based security approaches are vulnerable to poison datasets which can be caused by a legitimate defender's misclassification or attackers aiming to evade detection by contaminating the training data set. There also exist gaps between the test environment and the real world. Therefore, it is critical to check the potentials and limitations of AI-based security technologies in terms of metrics such as security, performance, cost, time, and consider how to incorporate them into the real world by addressing the gaps appropriately. This book focuses on state-of-the-art findings from both academia and industry in big data security relevant sciences, technologies, and applications. ​

This book provides a collection of the state-of-the-art research attempts to tackle the challenges in image and signal processing from various novel and potential research perspectives. The book investigates feature extraction techniques, image enhancement methods, reconstruction models, object detection methods, recommendation models, deep and temporal feature analysis, intelligent decision support systems, and autonomous image detection models. In addition to this, the book also looks into the potential opportunities to monitor and control the global pandemic situations. Image processing technology has progressed significantly in recent years, and it has been commercialized worldwide to provide superior performance with enhanced computer/machine vision, video processing, and pattern recognition capabilities. Meanwhile, machine learning systems like CNN and CapsNet get popular to provide better model hierarchical relationships and attempts to more closely mimic biological neural organization. As machine learning systems prosper, image processing and machine learning techniques will be tightly intertwined and continuously promote each other in real-world settings. Adopting this trend, however, the image processing researchers are faced with few image reconstruction, analysis, and segmentation challenges. On the application side, the orientation of the image features and noise removal has become a huge burden.