Mo Alloulah
alloulah at outlook dot com

I am the founder and CEO of RADAREYE. Previously, I was a member of technical staff at Nokia Bell Labs, where I worked on sensing and perception. My track record includes 18+ years experience in tech-based R&D, having envisioned, led, and delivered systems in multiple industrial settings in areas spanning signal processing and machine learning.

Before that I did a PhD at Lancaster University, an MSc with distinction at The University of Manchester where I ranked 1st and won the National Instruments award, and a BSc at the University of Balamand (Dean's honour lists).

LinkedIn  /  Strava  /  GitHub

My research focuses these days on self-supervised and multi-modal machine learning techniques for vision+radar perception, including representation learning. I continue to occasionally contribute to wireless problems, particularly those intersecting with machine learning.

I have led a programme (over a period of 4 years) that envisioned and delivered a self-supervised learning algorithm for automotive radar perception. Our algorithm uses contrastive learning and domain-specific radar augmentations to provide substantial improvements over supervised learning: 70% in label efficiency and 5.8% in mAP. Performance characterised in the real-world under nontrivial MIMO radar artefacts.

Bounding box estimation from radar-only for autonomous perception by distillation from vision using contrastive learning and domain-specific radar augmentations.

Automatic localisation of objects in the environment by tapping into the cross-modal information captured simultaneously by vision and radar.

For our synthetic dataset MaxRay, contact my ex-employer Nokia Bell Labs.

Building a radar classification model by distillation from vision using contrastive learning.

Position paper on why and how should we care to build a unified communication-perception network.

Benchmarking 8 flavours of real-world learnt RF localisation across three performance axes: (i) learning, (ii) proneness to distribution shift, and (iii) localisation, as well as against classic maximum likelihood estimation.

Practical inertial navigation system using deep learning and cloud-device partitioning.

In-situ adaptation of deep inertial navigation through spatial diversity, optimal transport, and domain adaptation.

Measuring breathing and body motion markers wirelessly towards sleep monitoring.

Best-effort inferencing using a variable instantaneous energy budget by means of knobs at featurisation-level as well as at neural network-level.

How would future networks in mm-wave bands exchange information using vibrational (i.e. kinetic) modulation in order to support security and spontaneous interaction applications.

Degradable vision inference by means of knobs at featurisation- and neural network-level.

Thoughts and guidelines on how to build sensing models for commodity radar HW indoors.

Joint compression and wireless coding scheme for robust and ultra-low power medical physiological sensing.

Indoor acoustic localisation chip. Part of two further technical reports here and here.

Traditional direct conversion RF transmitters are not suitable for IoT devices with stringent power budget. A polar transmitter in wideband WiFi channels is challenging. We made it work with couple key innovations. Achieved 3x power reduction.

Silicon + several patents.

Led work on multiple architecture-aware PHY implementations, part of a terrestrial DVB-T2 chipset. Keywords included inter-symbol interference (ISI) and inter-carrier interference (ICI).

Silicon in the field + several patents.

Adapted from the webpages of these lady and gentleman.