The Human Intranet is envisioned as an open, scalable platform that seamlessly integrates an ever-increasing number of sensor, actuation, computation, storage, communication, and energy nodes located on, in, or around the human body, acting in symbiosis with the functions provided by the body itself. The limited amount of available energy and the critical nature of its applications require such a network to be extremely efficient and robust. This project introduces a learning-based adaptive network structure to overcome these challenges [1].

The proposed architecture consisting of two orthogonal planes: a network data plane and an adaptive control plane. The data plane follows a standard wireless sensor network stack (from the bottom physical layer to the top application layer). The adaptive control plane manages the dynamic evolution of the network.

As the number and variety of nodes, network protocols, and technologies available at each network layer continuously increase [2], the design of such an open, adaptive, and scalable network platform becomes a daunting task. Hence, we proposed an optimization-based design space exploration approach for a Human Intranet network across the entire communication stack, capable of exploring network lifetime versus reliability trade-offs [3].

(left) Diagram of Human Intranet network stack model. (right) Reliability versus lifetime of the feasible network configurations for a sample network optimization problem.

This work was in collaboration with Prof. Alberto Sangiovanni-Vincentelli (UC Berkeley), Prof. Pierluigi Nuzzo (University of Southern California), Prof. Alvaro Araujo (Universidad Politecnica de Madrid) and Dr. Arno Thielens (UC Berkeley).

  1. Adaptive Body Area Networks Using Kinematics and Biosignals A. Moin, A. Thielens, A. Araujo, A. Sangiovanni-Vincentelli, and J. M. Rabaey IEEE Journal of Biomedical and Health Informatics 2020 [arXiv] [Link]
  2. A Comparative Study of On-Body Radio-Frequency Links in the 420 MHz–2.4 GHz Range Arno Thielens, Robin Benarrouch, Stijn Wielandt, Matthew Anderson, Ali Moin, Andreia Cathelin, and Jan Rabaey Sensors 2018 [Link]
  3. Optimized Design of a Human Intranet Network A. Moin, P. Nuzzo, A. L. Sangiovanni-Vincentelli, and J. M. Rabaey In Proceedings of the 54th Annual Design Automation Conference (DAC) 2017 [PDF]