Название: Convergence of Deep Learning and Internet of Things: Computing and Technology
Автор: T. Kavitha, G. Senbagavalli, Deepika Koundal
Издательство: IGI Global
Год: 2023
Страниц: 376
Язык: английский
Формат: epub (true)
Размер: 25.0 MB

Digital technology has enabled a number of internet-enabled devices that generate huge volumes of data from different systems. This large amount of heterogeneous data requires efficient data collection, processing, and analytical methods. Deep Learning (DL) is one of the latest efficient and feasible solutions that enable smart devices to function independently with a decision-making support system. Convergence of Deep Learning and Internet of Things: Computing and Technology contributes to technology and methodology perspectives in the incorporation of Deep Learning approaches in solving a wide range of issues in the IoT domain to identify, optimize, predict, forecast, and control emerging IoT systems. Covering topics such as data quality, edge computing, and attach detection and prediction, this premier reference source is a comprehensive resource for electricians, communications specialists, mechanical engineers, civil engineers, computer scientists, students and educators of higher education, librarians, researchers, and academicians.

The Internet of Things (IoT) is multidisciplinary, and it integrates a variety of domain technologies with electronics, communications, Mechanical, Civil, and computer technology. Evaluation of digital technology has enabled the number of Internet-enabled devices that generate a huge volume of data from different systems. This large amount of heterogeneous data requires efficient data collection, processing, and analytical methods. Technological advances and evaluation in the field of Deep Learning and the Internet of Things (IoT) have attracted greater research on the use of Deep Learning in the Internet of Things. The amalgamation of deep learning and IoT gives the inherent opportunity for a wide range of emerging applications with diverse devices that are beyond our imagination, which has been discussed in recent literature surveys.

Each chapter of the book will contribute to technology and methodology perspectives in the incorporation of DL approaches in solving the wide range of issues in the IoT domain. Altogether, this book is expected to be the collection of academic and industrial researchers’ contributions in DL algorithms for Edge Computing in the Internet of Things, Intelligent Internet of Things, and conceptual structures of Deep Learning concepts on IoT infrastructure. Deep Learning for the Internet of Things, there are a lot of scopes that need further investigation to embed the intelligence in the Internet of Things for accuracy and speed-up the decision. The audience who are interested in designing and building intelligent Internet of Things is in need of strong technical information; this book addresses the emerging technologies and applications of both Deep Learning and the Internet of Things that is the need of the audience. Moreover, this book is a collective effort of the contributors to highlight and promote the value of deep learning in the field of the Internet of Things.

The heart of Industry 4.0 is established by a new technology called the Internet of Things (IoT). Through the Internet, the IoT makes it possible for machines and gadgets to share signals. Using Artificial Intelligence (AI) approaches to manage and regulate the communications between various equipment based on intelligent decisions is made possible by the Internet of Things (IoT) technology. Data collection devices can be fundamentally altered to “lock in” to the best sensing data with regard to a user-defined cost function or design constraint by utilizing inverse design and machine learning techniques. By allowing low-cost and small sensor implementations developed through iterative analysis of data-driven sensing outcomes, a new generation of intelligence sensing systems reduces the data load while significantly enhancing sensing capabilities. Machine learning-enabled computational sensors can encourage the development of widely distributed applications that leverage the Internet of Things to build robust sensing networks that have an influence across a variety of industries.