Special Issue on Distributed Intelligence at the Edge for the Future Internet of Things Submission Date: 2021-05-31 Currently and even more in the future, business, industry, finance and retail, healthcare, media, entertainment and many others, are and will be completely managed, coordinated, and controlled using huge amounts of data. These operations are performed by the Internet of Things (IoT) system of connected computing, digital, and mechanical devices, all of them named using unique identifiers (UIDs) and able to transfer data over a network without human intervention.

To extract value from such massive data volumes, processing power offered by cloud computing is still utilized. However, streaming data to the cloud exposes some limitations related to the increased communication and data transfer, which introduces delays and consumes network bandwidth. Another limitation that cloud-based computing for IoT poses is limited network connectivity. Therefore, the adoption of cloud computing to process data generated by IoT devices may not be applicable at all to classes of applications such as those needed for real-time, low latency, and mobile applications. Therefore, it is beyond imagination to use cloud computing to collect data, store, and work out results. Therefore, there has been a move towards mobile communication and edge computing. Billions of devices have been connected to the Internet and created zettabytes of data items. The problem remains on how to extract information from collected data best.

The use of Artificial Intelligence, machine learning, neural network, and data analytic techniques in edge processing resulted in a new inter-disciplinary field that enables distributed intelligence with edge devices and is known as distributed edge AI or edge intelligence. However, research on edge AI and distributed edge AI is still relatively new, and thus models, techniques, and protocols supporting intelligent management, querying and mining of large-scale amounts of data produced at the edge are required. A lot of challenges related to providing edge intelligence include training edge devices, so they can become smarter and smarter. There is also a need of the presentation of the most recent outcome of research of distributed intelligence. This need could be illustrated by a smart city that contains for instance: garages, parkings, car washing systems, traffic unloading centrals etc. – usually belonging to different companies and running different protocols. A most likely scenario is that these devices could use different AI systems to support their activities. However, all of them are parts of one interconnected smart city; different AI systems must cooperate for common goal(s). Thus, we need distributed intelligence. Examples and different AI systems working for different edges could be multiplied; they support a variety of edges. All want to make money, kick competitors from the market out, and grab their systems. Furthermore, there is an emphasis on creating better software and algorithms that can run efficiently on resource-constrained devices. Moreover, purpose-built hardware at the edge is becoming increasingly important in the field of machine learning because companies can run software much more efficiently if they use specialized chips. Another key challenge of distributed edge AI will be the continued improvement of user interfaces that are used to communicate with other humans, including text, voice, vision, and different forms of body language.

These only are some of the challenges of edge intelligence. This field is expected to arise in the upcoming years and become an essential part of the next generation of the Internet of Things that expands its reach into almost every domain. Therefore, this Special Issue seeks to identify and provide high-quality research on recent advances on edge AI and distributed edge AI. We are interested in all aspects pertaining to this multidisciplinary paradigm. Topics of interest include, but are not limited to, the following:

· Distributed Intelligence at the Edge

· Modeling and Development of IoT applications using Edge AI

· Distributed AI with/for Secure Edge Networking

· Machine-Learning Algorithms for IoT Applications

· Optimization, Control, And Automation in Edge Computing for IoT

· Secure Intelligent IoT-Edge Systems

· Secure Intelligent Coordination and Networking Between IoT, Edge, and Cloud

· AI-Based Resource Allocation in IoT-Edge Systems

· Trust and Privacy Management in Intelligent IoT-Edge Systems

· Quality of Service and Energy Efficiency for Intelligent IoT-Edge Systems

· Data Mining and Big Data Analytics for Security and Resource Management in IoT-Edge Systems

· Distributed Ledger Technologies and Blockchain in IoT Environments

登录用户可以查看和发表评论, 请前往  登录 或  注册

SCHOLAT.com 学者网
免责声明 | 关于我们 | 用户反馈