Backed and advanced by EC techniques and AI applications, Edge Intelligence (EI) has been pushed to the horizon. The development of EC techniques, including powerful IoT data, edge devices, storage, wireless communication, and security and privacy make it possible to run AI algorithms on the edge. AI applications, such as connected vehicles, connected health, smart manufacturing and smart home are good examples of domain that could benefit from running analytics on the edge. In the EI scenario, advanced AI and machine learning algorithms will be optimized to run on the edge. The edge will be capable of dealing with video frames, natural speech information, time-series data and unstructured data generated by cameras, microphones, and other sensors without uploading data to the cloud and waiting for the response. Migrating the AI functions from the cloud to the edge is highly regarded by industry and academy. However, the edge capability depends on the application and how much intelligence one can practically place at the edge. This depends on several factors, such as memory availability, performance needs, cost, and energy consumption. This will determine how much inferencing and analysis can be done at the edge. It is not a straightforward decision of where AI algorithms should be located and they are often distributed, with some happening in the cloud and some in the edge device. Therefore, DAIS Distributed Artificial Intelligent System, a pan-European effort with 49 key partners from 11 countries (EU and Turkey), will provide intelligent, secure and trustworthy systems for industrial applications to provide comprehensive cost and energy-efficient solutions of intelligent, end-toend secure, trustworthy connectivity and interoperability to bring the Internet of Things and Artificial Intelligence together. DAIS aims at creating an intelligence centred heterogeneous distributed edge computing systems and solutions.

Research team