Research

Ideas explored.
Findings shared.

Selected publications spanning wearable sensing, artificial intelligence, and biomedical signal processing.

Explore projects

Selected publications

Research across disciplines.

EMG · Inertial sensing · Wearable robotics

2026 IEEE International Conference on Robotics and Automation (ICRA)

A Modular, Wireless and Wearable Biosignal Acquisition Platform

Antonios Doukakis, Aikaterini Smyrli, Makis Livadas, Henrique De Melo Ribeiro, Shadiya Alingal Meethal, Mohamad Reza Shahabian Alashti, Gabriella Lakatos, Patrick Holthaus, Farshid Amirabdollahian

A modular platform combines wireless muscle-activity sensing and motion measurements for wearable robotics. The work demonstrates synchronised acquisition for assistive technologies, rehabilitation, and human–robot interaction.

Computer vision · Artificial intelligence · Circular construction

2024 IEEE International Workshop on Metrology for Living Environment (MetroLivEnv)

How to Valorize Construction and Demolition Wastes? Beyond the State of the art Through Vision Systems and Artificial Intelligence Tools

Gloria Cosoli, Giovanni Salerno, Maria Teresa Calcagni, Giuseppe Pandarese, Luca Violini, Evelyne El Masri, Henrique De Melo Ribeiro, Mohmmad Ali Asgar Abbas, Gian Marco Revel

Vision systems and AI support the detection, measurement, and characterisation of construction and demolition waste. The paper explores how this information can guide material recovery and reuse.

Voice classification · Bioimpedance · Deep learning

Journal of Voice · Published online 2023

Classification of Speaking and Singing Voices Using Bioimpedance Measurements and Deep Learning

Eugenio Donati, Christos Chousidis, Henrique De Melo Ribeiro, Nicola Russo

A deep learning approach distinguishes speaking from singing using bioimpedance measurements. The study explores electroglottographic signals as an alternative to audio recordings for efficient, near-real-time voice classification.

ECG · Arrhythmia · Quantized neural networks

Computers in Biology and Medicine · Volume 143 · Article 105249

ECG-based real-time arrhythmia monitoring using quantized deep neural networks: A feasibility study

Henrique De Melo Ribeiro, Ahran Arnold, James P. Howard, Matthew J. Shun-Shin, Ying Zhang, Darrel P. Francis, Phang B. Lim, Zachary Whinnett, Massoud Zolgharni

Quantized neural networks classify raw ECG signals with low computational and energy requirements. The feasibility study examines local, real-time arrhythmia monitoring on edge devices, including smartphones.

Bring a different perspective.

Discuss a collaboration