Charting the Intelligence Frontiers – Edge AI Systems Nexus

Ovidiu Vermesan, Alain Pagani, Paolo Meloni

• Publisher: River Publishers
• eBook ISBN:
  9788743808886
• Year: 2026

We are witnessing a fundamental shift in the computing landscape, a paradigm shift where intelligence is rapidly migrating to the very edges of the network. This is the era of edge AI, which embeds decision-making, perception, and control directly into devices that shape our physical world.

This book is a selected collection of the presented work from the European Conference on EDGE AI Technologies and Applications (EEAI) held on 21–23 October 2024 in Cagliari, Sardinia, Italy.

The conference is part of a series of annual conferences that delve into the expanding continuum of micro-, deep-, and meta-edge architectures, which form the backbone of emerging intelligent autonomous systems across numerous sectors. From the complexities of advanced algorithms and the design of novel edge AI hardware accelerators to the architecture of next-generation communication networks, AI frameworks and software systems, the EEAI fosters a vibrant exchange of ideas that are following the future and actively defining it.

From industrial automation to environmental monitoring, from manufacturing to smart mobility, the expansion of micro-, deep-, and meta-edge AI processing is propelling a new class of autonomous systems. These systems thrive on distributed intelligence, leveraging advancements in edge AI hardware architectures, accelerators, performant algorithms, and advanced software frameworks.

The chapters in this volume celebrate this paradigm shift and offer a glimpse into the vibrant ecosystem shaping the future of edge AI technologies and applications. The numerous chapters describe novel solutions and rigorous investigations spanning verification and validation, federated learning, neuromorphic design, scalable architectures, sensor fusion, and human–machine collaboration, each chapter demonstrating the innovation wave fuelling Europe's edge AI landscape.

Together, these twenty chapters provide a rich, multi-layered, and deeply insightful perspective on the state of edge AI. Each chapter documents the achievements made and highlights the path forward, offering a compelling vision of a future where intelligence is seamlessly and securely integrated into the fabric of the real world.

This book is an essential guide for navigating, understanding, and contributing to the dynamic and rapidly evolving field of edge AI.

The real value of this book lies in its innovative, forward-looking perspective, offering a guided exploration of the latest scientific breakthroughs and practical advancements shaping intelligent systems at the edge.

For researchers, students, practitioners, and visionaries, this book provides a comprehensive roadmap for the next stage in the evolution of intelligent, connected systems at the edge.

Table of contents

• Cover Page
• Half Title page
• Series page
• Title Page
• Copyright Page
• Dedication
• Acknowledgement
• Contents
• Preface
• List of Figures
• List of Tables
• List of Contributors
• List of Abbreviations
• 1 Edge AI Systems Verification and Validation
• 2 Pioneering the Hybridization of Federated Learning in Human Activity Recognition
• 3 Edge Intelligence Architecture for Distributed and Federated Learning Systems
• 4 Challenges and Performance of SLAM Algorithms on Resource-constrained Devices
• 5 Designing Accelerated Edge AI Systems with Model Based Methodology
• 6 Edge AI Acceleration for Critical Systems: from FPGA Hardware to CGRA Technology
• 7 Model Selection and Prompting Strategies in Resource Constrained Environments for LLM-based Robotic System
• 8 Optimising ViT for Edge Deployment: Hybrid Token Reduction for Efficient Semantic Segmentation
• 9 Recent Trends in Edge AI: Efficient Design, Training and Deployment of Machine Learning Models
• 10 Scalable Sensor Fusion for Motion Localization in Large RF Sensing Networks
• 11 Multi-Step Object Re-Identification on Edge Devices: A Pipeline for Vehicle Re-Identification
• 12 A TinyMLOps Framework for Real-world Applications
• 13 Transfer and Self-learning in Probabilistic Models
• 14 A Novel Hierarchical Approach to Perform On-device Energy Efficient Fault Classification
• 15 Discovering and Classifying Digital and Industries Products' Defects at the Edge by a Yolo/ResNet-based Approach and Beyond
• 16 Conscious Agents Interaction Framework for Industrial Automation
• 17 Neuromorphic IoT Architecture for Efficient Water Management
• 18 Online AI Benchmarking on Remote Board Farms
• 19 Optimising Neural Networks for Water Stress Prediction in Europe: A Sustainable Approach
• 20 The Accountability Strikes Back: Decentralizing the Key Generation in CL-PKC with Traceable Ring Signatures
• Index
• About the Editors