Artificial Intelligence of Things (AIoT): Bringing Intelligence into the Physical World
Date and time: 29 August 2024, 13:00-14:00 CEST (UTC +2), coffee is served from 12:30
Speaker: Ivana Podnar Žarko, University of Zagreb, Croatia
Title: Artificial Intelligence of Things (AIoT): Bringing Intelligence into the Physical World
Where: KTH Visualization Studio, Lindstedtsvägen 5, 4451, 114 28 Stockholm
Direction: https://maps.app.goo.gl/HEMWXQoGU1JvB3km7
OR
Zoom: https://kth-se.zoom.us/j/64305333712
Download presentation: AIoT-orchestration-KTH-talk
Abstract: The true potential of the Internet of Things (IoT) lies in its convergence with artificial intelligence (AI), giving rise to the concept of Artificial Intelligence of Things (AIoT) which integrates AI models and concepts into the IoT-edge-cloud continuum. AIoT environments can learn, reason, and make autonomous decisions based on the data continuously generated by many IoT devices, and they can operate devices autonomously at the edge of the network. AIoT brings AI into our physical environment and removes the boundaries between the physical and digital worlds, opening up new possibilities for device intelligence and autonomy in the physical environment.
In this talk, I will introduce the concept of AIoT as a continuous processing cycle consisting of four steps (1. sensing, 2. learning, 3. decision-making and 4. acting) and illustrate it with concrete real-world use cases. Next, we will review the challenges of AIoT: It operates in a dynamic and heterogeneous environment with limited resources which are used for real-time data processing, online learning, inference and decision-making under time constraints, while data streams from IoT devices are often incomplete, prone to errors, and unlabelled. In addition, AIoT systems must adhere to strict privacy and security requirements to protect sensitive user data and ensure device integrity as well as the safety of the physical environment.
Introducing the AIoTwin Orchestration Middleware. To address these challenges and unlock the full potential of AIoT, a data-driven orchestration middleware for AIoT is designed and developed within the AIoTwin project. The middleware operates within the IoT-edge-cloud continuum enabling:
- Service Orchestration: Scheduling, deploying, and managing AI/ML services at the edge or in the cloud.
- Intelligent Data Distribution and Routing: Distributing data streams from IoT devices to suitable containers running AI/ML algorithms considering load balancing and QoS requirements.
The middleware is designed to support both hierarchical federated learning and adaptive inference pipelines in dynamic and unstable execution environments. The main feature of the orchestration middleware is adaptivity and adherence to use case specific QoS and energy-efficiency requirements. It is published as open-source software in the AIoTwin GitHub repository (https://github.com/aiotwin).
AIoTwin is a twinning coordination action for spreading excellence in Artificial Intelligence of Things, bringing together researchers from three European universities (University of Zagreb, Technische Universität Wien and Technische Universität Berlin) and one research institute (RISE). The project has received funding from the European Union’s Horizon Europe programme “Widening participation and spreading excellence” under grant agreement No. 101079214.
Bio: Ivana Podnar Žarko is a Full Professor at the Faculty of Electrical Engineering and Computing, University of Zagreb, Croatia (UNIZG-FER), where she teaches courses on distributed systems and the Internet of Things. She was promoted to Full Professor in December 2017 and leads Internet of Things Laboratory at UNIZG-FER since 2015. She was a guest researcher and research associate (2001-2002) at the Vienna University of Technology, Austria, and a postdoctoral researcher (2005-2006) at the Swiss Federal Institute of Technology in Lausanne (EPFL), Switzerland.
Her research interests lie in the domain of distributed systems, especially decentralized solutions in the field of the Internet of Things (IoT). In the last five years, she has focused on the following research problems: artificial intelligence and interoperability for IoT, mobile crowd sensing solutions and distributed ledger technology.
Prof. Podnar Žarko has rich experience of participation in collaborative scientific research projects funded from national and European sources and has led six research projects. She is currently coordinating the Horizon Europe twinning project AIoTwin: Twinning action for spreading excellence in Artificial Intelligence of Things and was the Technical Manager of the H2020 project symbIoTe: Symbiosis of smart objects across IoT environments (2016-2018). She led two recently completed national projects: IoT-Field, funded by the European Structural and Investment Funds, and IoT4us, funded by the Croatian Science Foundation. She is also involved as a researcher in the Centre of Research Excellence for Data Science and Advanced Cooperative Systems, the first national centre of excellence in the field of technical sciences in Croatia. She has also served as an invited expert evaluator for the Horizon Europe program.
Ivana Podnar Žarko co-authored more than 85 scientific papers in the area of large-scale distributed systems, IoT, and Big data processing. She has served as a program committee member for many international conferences and workshops (e.g., IEEE Globecom, IEEE ICC, IEEE 5G World Forum, Global IoT Summit) and was a track chair of the 19th Annual IEEE/ACM Int. Symposium in Cluster, Cloud, and Grid Computing (CCGrid 2019). She is a member of IEEE and was the Chapter Chair of IEEE Communications Society, Croatia Chapter (2011-2014). She has received an award for engineering excellence from the IEEE Croatia Section in 2013 and the Science Award of UNIZG-FER in 2020 for outstanding achievements in research and innovation.
Website: https://www.fer.unizg.hr/en/ivana.podnar_zarko
ORCID: https://orcid.org/0000-0001-5619-2142
LinkedIn: https://www.linkedin.com/in/ivanapodnarzarko