
EdgeAI is as a key initiative for the European digital transition towards intelligent processing solutions at the edge. The project develops new electronic components and systems, processing architectures, connectivity, software, algorithms, and middleware through the combination of microelectronics, AI, embedded systems, and edge computing, covering key strategic application areas such as Digital Industry, Energy, Agri-food and Beverage, Mobility, and Digital Society.
These strategic areas are covered through so-called Value Chains (VC). Each value chain comprises of a set of demonstrators that provide the integration of the technologies developed by the project and are validated and tested in the industrial sector covered by the value chain. On demonstrator level the partners are working on different AI aspects related to the AI technology stack and their industry requirements.
EdgeAI will ensure that Europe has the necessary tools, skills, and technologies to enable edge AI as a viable alternative deployment option to legacy centralised solutions, unlocking the potential of ubiquitous AI deployment, with the long-term objective of Europe taking the lead of Intelligent Edge.
EdgeAI will contribute to the Green Deal twin transition with a systemic, cross-sectoral approach, and will deliver enhanced AI-based electronic components and systems, edge processing platforms, AI frameworks and middleware. It will develop methodologies to ease, advance and tailor the design of edge AI technologies by coordinating efforts across 48 of the brightest and best R&D organizations across Europe. It will demonstrate the applicability of the developed approaches across a variety of vertical solutions, considering security, trust, and energy efficiency demands inherent in each of these use cases.
EdgeAI will significantly contribute to the grand societal challenge to increase the intelligent processing capabilities at the edge
ITML’s role in the project
Within the EdgeAI project, ITML acts as the project’s dissemination, exploitation, and communication coordinator. ITML has also a key role in developing AI-based solutions, focusing on the design and implementation of anomaly detection algorithms, exploring federated learning (FL) approaches for data privacy, and integrating these AI solutions within the mobility sector. Specifically, ITML contributes to the development of prototypes for data preprocessing, model training, and evaluation for time series forecasting and anomaly detection for roadside perception units (RSPUs) connected with LoRa 2.4GHz Mesh network. This involves creating Python libraries and exploring model compression techniques. Furthermore, ITML is actively involved in designing and prototyping a time series anomaly detection model for RSPUs, utilizing federated learning for enhanced data privacy. Current efforts focus on finalizing model compression methods, refining FL pipelines, and evaluating model performance across various scenarios, ensuring the development of robust and efficient AI solutions for the EdgeAI ecosystem.
For more information, visit the official project website: https://edge-ai-tech.eu/
Acknowledgments
The project EdgeAI has received funding from the Chips Joint Undertaking (Chips JU) and its members (including top-up funding by the National Authority of Greece, General Secretariat for Research and Innovation – GSRI) under Grant Agreement No. 101097300. The action is also implemented within the framework of the National Recovery and Resilience Plan “Greece 2.0”, with funding from the European Union – NextGenerationEU.
