Guest Editors

Prof. Shi Dong, Zhoukou Normal University, China
Prof. Joarder Kamruzzaman, Federation University Australia, Australia
Sensor Engineer. Yongsheng Hao, Nanjing University of Information Science & Technology, China

Summary

Artificial intelligence and edge computing, as two epoch-making new technologies, are currently facing bottlenecks in their further development. On the one hand, for deep learning technology, due to its need for high-density computing, currently intelligent algorithms based on deep learning are usually run in cloud computing data centers with strong computing capabilities. To bring intelligence closer to users and enhance its integration into various aspects of life, it is essential to effectively deploy deep learning models on mobile terminal devices with limited resources, considering their current high popularity. On the other hand, for edge computing, with the sinking and decentralization of computing resources and services, edge computing nodes will be widely deployed in access points at the edge of the network (such as cellular base stations, gateways, wireless access points, etc.). Therefore, the concept of edge intelligence was proposed, which is the combination of artificial intelligence and edge computing. However, the research on edge intelligence is still in its infancy. Computer systems and artificial intelligence communities urgently need a special place to exchange the latest progress in edge intelligence. In essence, compared with traditional edge computing, it still needs to face several issues, including high latency, energy efficiency, privacy protection, bandwidth reduction, timeliness, and environmental sensitivity. To address the above issues, this special issue will serve as a forum to bring together active researchers all over the world to share their recent advances in edge intelligence. Our targets include (1) state-of-the-art theories and novel applications in edge intelligence; (2) novel edge intelligence framework; (3) edge intelligence methods in a specific environment (such as IoT or IoV environment); (4) resource management in edge intelligence (5) novel task offloading method for edge intelligence; (6) edge intelligence method based deep learning; (7) Security and privacy for edge intelligence and (8) survey articles reporting the recent progress in edge intelligence.

Keywords

Innovative edge intelligence models based on deep learning
Resource management in edge intelligence
Edge computing, communication, and caching driven by artificial intelligence
Energy-saving framework based on edge intelligence in an end-edge-cloud environment
Edge intelligence in 5G/6G
Big data analysis in edge computing
Network traffic prediction in edge intelligence
Hybrid/ Integrated deep learning model for efficient edge intelligence
Novel reinforcement learning method with edge intelligence