Vivian Dsouza

Ph.D Candidate

Embedded Systems Group

TU Delft

Building 28, Room 2.W.760
Van Mourik Broekmanweg 6, 2628XE Delft
The Netherlands
v.k.p.dsouza@tudelft.nl   +31 613 880 934
LinkedIn Account Github Account Google Scholar Account

Publications

Education

I am a Ph.D Candidate supervised by dr. Przemysław Pawełczak and Prof. dr. Koen Langendoen at the Embedded systems group at TU Delft.

My interests are at the intersection of machine learning and embedded systems. My research primarily revolves around the development and exploration of ultra-low power wearable devices, with a particular emphasis on the innovative realms of earable devices and oral sensing technologies. These devices are strategically designed to focus on sensing in the vicinity of the head, capitalizing on the wealth of information that can be gathered from this central region of the human body. By harnessing the potential of ultra-low power systems in these specialized wearables, we aim to not only redefine the way we interact with technology but also unlock previously untapped avenues of data collection and processing that hold immense promise for healthcare, lifestyle enhancement, and beyond.Earable devices, worn discreetly in or around the ear, have the potential to revolutionize how we gather data about vital signs, cognitive states, and even environmental factors. Similarly, oral sensing technologies, which can be seamlessly integrated into everyday objects, hold the promise of collecting valuable information about our health, nutrition, and hydration levels.

Publications

  • C.R.Reddy, V.Dsouza, A.Thangarajan, P. Pawełczak, F.Kawsar, A.Montanari BioPulse: Towards Enabling Perpetual Vital Signs Monitoring using a Body Patch, Proc. ACM HotMobile 2025
  • V.Dsouza, J.Pronk, C.Peppelman, V.I.Madariaga, T.Pereira-Cenci, B.Loomans, P. Pawełczak Densor: An Intraoral Battery-Free Sensing Platform, Proc. ACM IMWUT 2024
  • S.K. Ghiasi*, V.Dsouza*, K. Langendoen, M. Zuniga, SpectraLux: Towards Exploiting the Full Spectrum with Passive VLC, Proc. ACM/IEEE IPSN 2023 (*equal contribution)
  • Education