Edge AI Technologies for Optimised Performance Embedded Processing

Informazioni relative al progetto

EdgeAI

ID dell’accordo di sovvenzione: 101097300

DOI

10.3030/101097300

Progetto chiuso

Data della firma CE 1 Dicembre 2022

Data di avvio 1 Dicembre 2022

Data di completamento 30 Giugno 2026

Finanziato da

• Digital, Industry and Space

Costo totale

€ 33 341 524,23

Contributo UE

€ 10 171 160,41

Coordinato da

SINTEF AS
Norway

CORDIS fornisce collegamenti ai risultati finali pubblici e alle pubblicazioni dei progetti ORIZZONTE.

I link ai risultati e alle pubblicazioni dei progetti del 7° PQ, così come i link ad alcuni tipi di risultati specifici come dataset e software, sono recuperati dinamicamente da .OpenAIRE .

Risultati finali

Documents, reports (16)

Intermediate Project Report 2

The report describes project progress during the period m14-m20.

Report on conceptual framework for edge AI requirements and specification

The report covers the results for defining a conceptual framework for defining requirements, other common aspects (terminology, relevant standards, etc.), and trends in edge AI research and innovation. It serves as a blueprint for applying these concepts in the various industries in D1.2-D1.6.

Initial standardization plan

The deliverable is dedicated to the detailed description and presentation of the EdgeAI activities towards the standardization activities.

Report on energy industry requirements and specification for edge AI

The report covers the implementation of the proposed requirements framework (D1.1) for the demonstrators in the energy industry value chain. It comprises (non-) functional requirements, terminology, and relevant standards.

Report on digital industry requirements and specification for edge AI

The report covers the implementation of the proposed requirements framework (D1.1) for the demonstrators in the digital industry value chain. It comprises (non-) functional requirements, terminology, and relevant standards.

Report on digital society requirements and specification for edge AI

The report covers the implementation of the proposed requirements framework (D1.1) for the demonstrators in the digital society value chain. It comprises (non-) functional requirements, terminology, and relevant standards.

Report on mobility industry requirements and specification for edge AI

The report covers the implementation of the proposed requirements framework (D1.1) for the demonstrators in the mobility industry value chain. It comprises (non-) functional requirements, terminology, and relevant standards.

Report on road-mapping for cross-industrial domains edge AI requirements and specification

The report covers a conclusion of cross-industrial requirements engineering in the area of edge AI. It presents a compiled analysis of communalities and provides a general roadmap for AI technologies at the edge during the project and open issues beyond the project lifetime.

Dissemination activities report RP1

The deliverable is dedicated to the detailed description, presentation and reporting of the Edge AI dissemination and communication activities during m01 – m13.

Risk Management Plan

The report covers the risk management plan identifying sources of risks, evaluating the probability and severity and controlling risks by implementing mitigation measures so no unwanted effects incur on project’s development and sustainability.

Project Handbook and Quality Assurance

The report covers the guidelines and rules related to the coordination and management of the project.

Report on agri-food and beverage industry requirements and specification for edge AI

The report covers the implementation of the proposed requirements framework (D1.1) for the demonstrators in the agri-food and beverage industry value chain. It comprises (non-) functional requirements, terminology, and relevant standards.

Dissemination activities report RP2

The deliverable is dedicated to the detailed description, presentation and reporting of the Edge AI dissemination and communication activities during m14 – m25.

Report on strategies for edge AI HW/SW verification and integration of enabling technologies

The report covers the definition of strategies for edge AI HW/SW verification and common integration principles of enabling technologies into applications. These strategies will be applied during the verification and integration implementation in the various industries in D5.2-D5.6.

Intermediate Project Report 1

The report describes project progress during the period m01-m07.

Plan for dissemination and exploitation including communication activities

The report covers the dissemination, communication and exploitation plan that will be followed by the EdgeAI consortium to realize all relevant activities.

Websites, patent fillings, videos etc. (2)

Public communication: social media, website

The report covers the design, deploy, development and release of the project user-friendly and interactive portal as well as the release of project social media (LinkedIn, Twitter, and YouTube Channel).

Network building and AI KDT JU community engagement workshop

This deliverable will describe in detail the activities carried out towards the project networking, and the organization of the AI related KDT JU community engagement workshop.

Data Management Plan (2)

First Updated Data Management Plan

The report covers the first revised DMP that describes how the project data/research outputs are implement according to FAIR principles.

Initial Data Management Plan

The report covers the DMP that describes how the project data/research outputs are findable, accessible, interoperable, and reusable (FAIR). The document will be revised towards the end of a project’s lifetime.

Pubblicazioni

Conference proceedings (15)

TinyLid: a RISC-V accelerated Neural Network For LiDAR Contaminant Classification in Autonomous Vehicle

Autori: Grafika Jati, Martin Molan, Francesco Barchi, Andrea Bartolini, Andrea Acquaviva
Pubblicato in: Proceedings of the 21st ACM International Conference on Computing Frontiers, 2025
Editore: ACM
DOI: 10.1145/3649153.3649201

VFM-UDA++: Improving Network Architectures and Data Strategies for Unsupervised Domain Adaptive Semantic Segmentation

Autori: Brunó B. Englert, Gijs Dubbelman
Pubblicato in: 2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), 2026
Editore: IEEE
DOI: 10.1109/ICCVW69036.2025.11495570

PCB-SAID: A Low-Cost Camera-Based Dataset for Few-Shot SMD Assembly Inspection

Autori: Raffaele Mineo, Amelia Sorrenti, Robin Faro, Gabriele Mineo, Francesco Cancelliere, Alberto Faro
Pubblicato in: 2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), 2026
Editore: IEEE
DOI: 10.1109/ICCVW69036.2025.00145

What is the Added Value of UDA in the VFM Era?

Autori: Brunó B. Englert, Tommie Kerssies, Gijs Dubbelman
Pubblicato in: 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2025
Editore: IEEE
DOI: 10.1109/CVPRW67362.2025.00238

Bio-Inspired Drone Control: A Reinforcement Learning-Trained Spiking Neural Networks for Agile Navigation in Dynamic Environment

Autori: Yin-Ching Lee, Sebastiano Mengozzi, Luca Zanatta, Andrea Bartolini, Andrea Acquaviva, Francesco Barchi
Pubblicato in: 2025 IEEE International Conference on Omni-layer Intelligent Systems (COINS), 2025
Editore: IEEE
DOI: 10.1109/COINS65080.2025.11125776

Scaling Up Quantization-Aware Neural Architecture Search for Efficient Deep Learning on the Edge

Autori: Yao Lu, Hiram Rayo Torres Rodriguez, Sebastian Vogel, Nick van de Waterlaat, Pavol Jancura
Pubblicato in: 2024
Editore: Zenodo
DOI: 10.48550/ARXIV.2401.12350

On the Trustworthiness of Spiking Neural Networks and Neuromorphic Systems

Autori: Theofilos Spyrou; Haralampos-G. Stratigopoulos; Ihsen Alouani; Said Hamdioui; Anteneh Gebregiorgis
Pubblicato in: 2025
Editore: IEEE
DOI: 10.1109/ETS63895.2025.11049613

VidEoMT: Your ViT is Secretly Also a Video Segmentation Model

Autori: Narges Norouzi, Idil Esen Zulfikar, Niccolò Cavagnero, Tommie Kerssies, Bastian Leibe, Gijs Dubbelman, Daan de Geus
Pubblicato in: 2026
Editore: arxiv.org
DOI: 10.48550/ARXIV.2602.17807

Depth Map Reconstruction from Low-altitude UAV

Autori: S. Hamed Javadi, Hichem Sahli, André Bourdoux
Pubblicato in: 2025 22nd European Radar Conference (EuRAD), 2025
Editore: IEEE
DOI: 10.23919/EURAD65285.2025.11234265

Trusted Execution, Updating of AI/ML Models and Sensor Data through Isolation on IoT Devices

Autori: George Kornaros, Stavros Martini, Nicolas Spyridakis, Alexandra Polixronidou
Pubblicato in: 2025 IEEE Annual Congress on Artificial Intelligence of Things (AIoT), 2026
Editore: IEEE
DOI: 10.1109/AIOT66900.2025.00139

Your ViT is Secretly an Image Segmentation Model

Autori: Tommie Kerssies, Niccolò Cavagnero, Alexander Hermans, Narges Norouzi, Giuseppe Averta, Bastian Leibe, Gijs Dubbelman, Daan de Geus
Pubblicato in: 2025
DOI: 10.48550/ARXIV.2503.19108

Compact MEOL OxRAM with 14 Conductance Levels for Dense Embedded Inference Computing

Autori: J. Minguet Lopez, S. Barraud, M. Dampfhoffer, A. Souhaité, T. Dubreuil, J.-M. Pedini, C. Comboroure, A. Gharbi, F. Boulard, C. Castan, A. Lambert, F. Andrieu
Pubblicato in: 2025 IEEE International Reliability Physics Symposium (IRPS), 2025
Editore: IEEE
DOI: 10.1109/IRPS48204.2025.10983457

TD-Magic: From Pictures of Timing Diagrams To Formal Specifications

Autori: Jie He, Dejan Nickovic, Ezio Bartocci, Radu Grosu
Pubblicato in: 2023, ISBN 979-8-3503-2349-8
Editore: IEEE
DOI: 10.1109/DAC56929.2023.10247685

Experimental Software and Hardware Evaluation of Ad-Hoc Constant Division Routines

Autori: Frédéric Pétrot
Pubblicato in: 2025 IEEE 32nd Symposium on Computer Arithmetic (ARITH), 2025
Editore: IEEE
DOI: 10.1109/ARITH64983.2025.00020

Exploring Superposition and Interference in State-of-the-Art Low-Parameter Vision Models

Autori: Lilian Hollard, Lucas Mohimont, Nathalie Gaveau, Luiz-Angelo Steffenel
Pubblicato in: 2025
Editore: arxiv.org
DOI: 10.48550/ARXIV.2507.15798

Peer reviewed articles (6)

Rethinking 1T1R architecture and OxRAM stack for memristive neural network inference in-memory

Autori: Joel Minguet Lopez, Sylvain Barraud, David Cooper, Audrey Jannaud, Adeline Grenier, Aurelie Souhaité, Jean-Michel Pedini, Corinne Comboroure, Ahmed Gharbi, François Boulard, Clément Castan, Amélie Lambert, François Andrieu
Pubblicato in: Frontiers in Nanotechnology, Numero 7, 2025, ISSN 2673-3013
Editore: Frontiers Media SA
DOI: 10.3389/FNANO.2025.1549547

LoRaWAN-Based Emergency Framework for Vehicular Networks

Autori: Dimitrios Georgiadis, Konstantina Karathanasopoulou, Eirini Liotou, George Dimitrakopoulos
Pubblicato in: IEEE Networking Letters, Numero 7, 2025, ISSN 2576-3156
Editore: Institute of Electrical and Electronics Engineers (IEEE)
DOI: 10.1109/LNET.2025.3583492

LIDAROC: Realistic LiDAR Cover Contamination Dataset for Enhancing Autonomous Vehicle Perception Reliability

Autori: Grafika Jati, Martin Molan, Francesco Barchi, Andrea Bartolini, Giuseppe Mercurio, Andrea Acquaviva
Pubblicato in: IEEE Sensors Letters, Numero 8, 2024, ISSN 2475-1472
Editore: Institute of Electrical and Electronics Engineers (IEEE)
DOI: 10.1109/LSENS.2024.3434624

Increasing the Accessibility of Causal Domain Knowledge via Causal Information Extraction Methods: A Case Study in the Semiconductor Manufacturing Industry

Autori: Houssam Razouk, Leonie Benischke, Daniel Gärber, Roman Kern
Pubblicato in: Applied Sciences, Numero 15, 2025, ISSN 2076-3417
Editore: MDPI AG
DOI: 10.3390/APP15052573

Intelligent Traction Inverter in Next Generation Electric Vehicles: The Health Monitoring of Silicon-Carbide Power Modules

Autori: Carmelo Pino, Alessandro Sitta, Giulia Castagnolo, Angelo A. Messina, Salvatore Coffa, Michele Calabretta, Fabio Scotti, Angelo Genovese, Vincenzo Piuri, Concetto Spampinato, Francesco Rundo
Pubblicato in: IEEE Transactions on Intelligent Vehicles, Numero 8, 2024, ISSN 2379-8904
Editore: Institute of Electrical and Electronics Engineers (IEEE)
DOI: 10.1109/TIV.2023.3294726

ANZIL: Attention-based network for zero-risk inspection of LiDAR point cloud in self-driving cars

Autori: Grafika Jati, Martin Molan, Francesco Barchi, Andrea Bartolini, Giuseppe Mercurio, Andrea Acquaviva
Pubblicato in: Expert Systems with Applications, Numero 292, 2025, ISSN 0957-4174
Editore: Elsevier BV
DOI: 10.1016/J.ESWA.2025.128412

Book chapters (2)

DT-Anon: Decision Tree Target-Driven Anonymization

Autori: Sabrina De Capitani di Vimercati, Sara Foresti, Valerio Ghirimoldi, Pierangela Samarati
Pubblicato in: Lecture Notes in Computer Science, Data and Applications Security and Privacy XXXVIII, 2024
Editore: Springer Nature Switzerland
DOI: 10.1007/978-3-031-65172-4_8

Query Integrity in Smart Environments

Autori: Sabrina De Capitani di Vimercati, Sara Foresti, Pierangela Samarati
Pubblicato in: Lecture Notes in Computer Science, Security and Privacy in Smart Environments, 2024
Editore: Springer Nature Switzerland
DOI: 10.1007/978-3-031-66708-4_2