Advancing sustainable beekeeping through bioacoustics, TinyML, and low-power embedded intelligence.
Audio Intelligence for Bee Health
Non-invasive colony health detection through advanced audio signal processing and machine learning.
Edge AI & TinyML for Smart Beehives
Ultra-low-power machine learning deployed on the edge for real-time colony monitoring.
Energy-Aware AI for Sustainable IoT
Energy-efficient feature extraction and inference optimized for long-term autonomous deployments.
Research
Beesualize is a research initiative focused on advancing precision apiculture through bioacoustic sensing and intelligent embedded systems.
We investigate how hive-generated audio signals can reveal critical information about colony health, including queen presence and stress conditions.
Our work combines digital signal processing, machine learning, and TinyML to enable real-time analysis directly at the edge.
We design ultra-low-power IoT devices capable of long-term autonomous deployment inside beehives without invasive modifications.
A key aspect of our research is optimizing feature extraction and model efficiency to balance accuracy, energy consumption, and hardware constraints.
By integrating bioacoustics with energy-aware AI, Beesualize aims to support sustainable beekeeping and data-driven environmental monitoring.
Publications
The publications of the authors address the development of bioacoustic analysis methods for monitoring colony health, with a particular focus on queen bee detection through machine learning techniques.
They investigate Edge AI and TinyML solutions deployed on ultra-low-power microcontrollers for on-device processing inside the hive.
A central contribution is the energy-aware optimization of feature extraction and inference, adopting an integrated hardware–software co-design approach for sustainable IoT systems.
The Team
Prof. Fabrizio Riente
Prof. Giovanna Turvani
Dott. Andrea De Simone
Find your research Thesis
Join Beesualize and work at the intersection of bioacoustics, Edge AI, and sustainable IoT systems. We are looking for motivated Master’s students interested in developing next-generation intelligent systems for precision beekeeping.