Abstract: Wearable, intelligent, and unobtrusive smart sensor nodes that monitor the surrounding environment and even the human body have the potential to create valuable data for a wide range of applications. To attain this vision of unobtrusiveness, smart devices have to gather and analyze data over long periods of time without the need for battery frequent recharging and replacement. On the other hand, advances in low-power electronics and tiny machine learning techniques lead to many novel IoT devices making them more and more intelligent to take autonomous and low latency decisions. On the other hand, these devices have limited computational power due to the constrain of working with minimal energy to maximize the battery lifetime, thus machine learning needs to be adapted to overcome the memory and computational limits. To, even more, prolong the energy autonomy, energy harvesting from ambient sources is a promising solution to power these low-energy IoT devices. This talk presents a broad overview of the combination of Tiny Machine learning, low power design, and energy harvesting, when possible, to achieve truly unobtrusive wireless smart IoT devices. As those devices are still strongly application-specific the talk includes some examples of where that combination can be a winning solution facing real application scenarios ranging from smart biomedical patches to autonomous vehicles where the energy harvesting is not possible but the low latency and autonomy brought from the tiny ML is crucial.
MS Teams Link: https://teams.microsoft.com/l/meetup-join/19%3ameeting_YjQ4OGMwZDgtZDM3OC00MmUzLThlZWItNzAxYmUzYTc0OTg2%40thread.v2/0?context=%7b%22Tid%22%3a%224a5378f9-29f4-4d3e-be89-669d03ada9d8%22%2c%22Oid%22%3a%222356434f-03bb-4022-a7f8-ba1fd6e0c5e0%22%7d
Biography: Michele Magno (Senior Member, IEEE) received the master’s and Ph.D. degrees in electronic engineering from the University of Bologna, Bologna, Italy, in 2004 and 2010, respectively.,He has been working with ETH Zürich, since 2013, and has become a Visiting Lecturer or a Professor in several universities, namely, the University of Nice Sophia, Nice, France, Enssat, Lannion, France, University of Bologna, and Mid University Sweden, Sundsvall, Sweden. Since 2020, he has been leading the Department of Information Technology and Electrical Engineering (D-ITET) center for project-based learning. He is currently a Senior Researcher and a Lecturer with D-ITET, ETH Zürich, Zürich, Switzerland. He has authored or coauthored more than 200 articles in international journals and conferences papers. Some of his publications were awarded as best papers awards in IEEE conferences. His current research interests include smart sensing, low-power machine learning, wireless sensor networks, wearable devices, energy harvesting, low-power management techniques, and extension of the lifetime of battery-operating devices.