Название: Cognitive Digital Twins for Smart Lifecycle Management of Built Environment and Infrastructure: Challenges, Opportunities
Автор: Ibrahim Yitmen
Издательство: CRC Press
Год: 2023
Страниц: 240
Язык: английский
Формат: pdf (true)
Размер: 12.2 MB

This book provides knowledge into Cognitive Digital Twins for smart lifecycle management of built environment and infrastructure focusing on challenges and opportunities. It focuses on the challenges and opportunities of data-driven cognitive systems by integrating the heterogeneous data from multiple resources that can easily be used in a Machine Learning model and adjust the algorithms. It comprises Digital Twins incorporating cognitive features that will enable sensing complex and unpredicted behavior and reason about dynamic strategies for process optimization to support decision-making in lifecycle management of the built environment and infrastructure. The book introduces the Knowledge Graph (KG)-centric framework for Cognitive Digital Twins involving process modeling and simulation, ontology-based Knowledge Graph, analytics for process optimizations, and interfaces for data operability. It offers contributions of Cognitive Digital Twins for the integration of IoT, Big Data, Artificial Intelligence, smart sensors, Machine Learning and communication technologies, all connected to a novel paradigm of self-learning hybrid models with proactive cognitive capabilities.

The book presents the topologies of models described for autonomous real time interpretation and decision-making support of complex system development based on Cognitive Digital Twins with applications in critical domains such as maintenance of complex engineering assets in built environment and infrastructure. It offers the essential material to enlighten pertinent research communities of the state-of-the-art research and the latest development in the area of Cognitive Digital Twins, as well as a valuable reference for planners, designers, developers, and ICT experts who are working towards the development and implementation of autonomous Cognitive IoT based on Big Data analytics and context–aware computing.

Digital transformation in the construction industry has gained momentum worldwide in the last decade. Construction projects across the world are increasingly adopting digital technologies for various functions and operations. The key drivers of Construction 4.0 are the various digital technologies and their interaction with each other. These technologies were augmented using Artificial Intelligence (AI), Machine Learning (ML), Semantic technologies, Big Data Analytics, Blockchain, the Internet of Things (IoT), Cloud Computing, and Cognitive computing. The research studies have demonstrated the usefulness and relevance of different technological advancements. The fundamental design principles of construction 4.0 are information transparency, decentralized decision making, seamless information flow, technical assistance through robotics and automation, and interconnectivity and interoperability among these applied technologies.

The Metaverse as a computer-generated universe has been defined through vastly diversified concepts, such as lifelogging, collective space in virtuality, embodied internet/spatial Internet, a mirror world, and an omniverse: a venue of simulation and collaboration. The Metaverse is one of the most concerned and promising smart applications (Extended Reality, User Interactivity (Human-Computer Interaction), Artificial Intelligence, Blockchain, Computer Vision, IoT and Robotics, Edge and Cloud computing) in the next generation of wireless network intelligent applications. At the core of the metaverse stands the vision of an immersive Internet as a gigantic, unified, persistent, and shared realm. This signifies that the Metaverse places higher demands on the current Edge AI architecture.

Convolutional neural networks (CNNs and also known as ConvNets) are deep neural networks influenced by biological neural networks. Conventional CNNs use a convolution kernel with a shared-weight design to create equivariant translation responses or feature maps. CNN includes convolution, pooling, and fully connected layers. CNN uses a technique known as weight sharing across neurons to achieve a large decrease in size. Consequently, CNNs have Supervised Learning algorithms that may be used in various Computer Vision applications, including augmented reality, image search, and face recognition.