While Machine Learning is usually deployed in the cloud, lightweight versions of these algorithms that fit for constrained IoT systems such as microcontrollers are appearing. Using Machine Learning « at-the-edge » has indeed several advantages such as the reduction of network latency, it provides better privacy, and are working offline.
In this presentation, we will demonstrate how to deploy Deep Learning algorithms on IoT devices thanks to TensorFlow Lite.
We will see how to use it to design a smart vertical farming system able to predict and optimize the plant growth, at home or in developing countries where a reliable Internet connection still is missing.
I am leading the IoT security department and the R&D activities at Rtone. I am an Engineer in Telecommunications (INSA Lyon, 2015), and I have a Ph.D. in Computer Science from the University of Lyon (2018) after a thesis on Visible Light Communications for the IoT. My thesis was in collaboration between Rtone and the CITI lab under the CIFRE fellowship, and was supervised by Razvan Stanica, Hervé Rivano and Adrien Desportes, Rtone Chief Executive Officer. I am actively involved in the PACLIDO collaborative project on lightweight cryptographic protocols for the IoT, for which I am the technical lead for Rtone. I regularly attend IT conferences and give talks about security, IoT and Machine Learning.
|Talks by tracks||Talks by session types||List of Speakers||Schedule|