A 30 µW Embedded Real Time Cetacean Smart Detector

Sebastián Marzetti (1) , Valentin Gies (1) , Paul Best (2) , Valentin Barchasz (1) , Sébastien Paris (2) , Hervé Barthélémy (1) , Hervé Glotin (2)

1 IM2NP - Institut des Matériaux, de Microélectronique et des Nanosciences de Provence
2 LIS - Laboratoire d'Informatique et des Systèmes (LIS) (Marseille, Toulon)

Cetacean monitoring is key to their protection. Understanding their behaviour relies on multi-channel and high sampling rate underwater acoustic recordings for identifying and tracking them in a passive way. However, a lot of energy and data storage is required, requiring frequent human maintenance operations. To cope with these constraints, an ultra-low power mixed signal always-on wake-up is proposed. Based on pulse pattern analysis, it can be used for triggering a multi-channel high performance recorder only when cetacean clicks are detected, thus increasing autonomy and saving storage space. This detector is implemented as a mixed architecture making the most of analog and digital primitives : this combination improves drastically power consumption by processing high frequency data using analog features and lower frequency ones in a digital way. Furthermore, a bioacoustic expert system is proposed for improving detection accuracy (in ultra low-power) via state-machines. Power consumption of the system is lower than 30 µW in always-on mode, allowing an autonomy of 2 years on a single CR2032 battery cell with a high detection accuracy. The receiver operating characteristic (ROC) curve obtained has an area under curve of 85% using expert rules and 75% without it. This implementation provides an excellent trade-off between detection accuracy and power consumption. Focused on sperm whales, it can be tuned to detect other species emitting pulse trains. This approach facilitates biodiversity studies, reducing maintenance operations and allowing the use of lighter, more compact and portable recording equipment, as large batteries are not longer required. Additionally, recording only useful data helps to reduce the dataset labelling time.

Mots clés: Embedded Artificial Intelligence; Ultra-Low Power; Pattern Detection; Expert System; Biosonar; Always-On Wake-up; Pulse train

Domaines: Micro et nanotechnologies/Microélectronique; Biodiversité et Ecologie; Automatique / Robotique; Electronique

Sebastián Marzetti, Valentin Gies, Paul Best, Valentin Barchasz, Sébastien Paris, et al.. A 30 µW Embedded Real Time Cetacean Smart Detector. Electronics, 2021, 10 (7), pp.819. ⟨10.3390/electronics10070819⟩. ⟨hal-03502818⟩