tinyML Talks Pakistan: Machine Learning without batteries: the case for light-powered tinyML

“Machine Learning without batteries: the case for light-powered tinyML”
Andres Gomez
Postdoctoral Fellow
University of St. Gallen

Over the last decade, energy harvesting has seen significant growth as different markets adopt green, sustainable ways to produce electrical energy. Even though costs have fallen, the embedded machine learning and Internet of Things community have not yet widely adopted energy-harvesting-based solutions. In this talk, I will present a design methodology for smart batteryless sensors, capable of gathering data, processing it, and transmitting inference results wirelessly. A newly developed gesture detection feature for the open-source MiroCard will be presented, along with the cost-benefits and privacy implications of batteryless sensing systems.

source