Insect-inspired neural network classifies gases using low power

Online gas classification at the edge

Emerging TechnologiesMachine Learning

Summary

Detecting different gases quickly and with low power is important for safety and robots in the field. The authors created a tiny neural network inspired by how insects smell, which uses a simple way to represent data and can learn on the spot. It can tell apart single gases and mixed gases from raw sensor data, performing as well as complex existing methods but much more efficiently. They even tested it on a special low-power chip that runs the model with very little energy.

What this means in practice

  • For mobile robot developers: Use neural gas classifiers that run efficiently on low-power chips to improve real-time detection of diverse gases in outdoor environments.
  • For portable safety device manufacturers: Incorporate lightweight, fast-learning gas classifiers on energy-efficient hardware for better hazard monitoring with limited labeled data.$Commercial implications: Enables new portable gas detectors that classify hazardous gases accurately with minimal battery use, enhancing safety equipment.

Authors

Ton Juny Pina, Hugh Greatorex, Elisabetta Chicca

Abstract

Field applications in chemical sensing, from portable safety monitors to mobile robots, require models that are lightweight, fast to respond, and can be recalibrated from limited labelled data. Current gas classification pipelines assume controlled sampling cycles and offline feature extraction, and rely on computationally expensive models. With a few thousand neurons and sub-milliwatt power consumption, insects reliably classify odours in open environments. Inspired by the insect olfactory system, we present a neural network architecture that classifies raw sensor array readings using a sparse, high-dimensional binary representation. We evaluate it on random sequences of single gases and binary mixtures, introducing new samples dynamically and classifying gas identity from the transient sensor response. In this setting, the architecture out-performs a linear \gls{svm} on gas mixtures and matches an optimised non-linear \gls{svm}, while maintaining online class-level frequency estimates that distinguish familiar from novel stimuli. It relies exclusively on binary weights and Hebbian-based local learning, remaining computationally lightweight and well suited to ultra-low-power neuromorphic processors. We demonstrated the network on-chip with a hazardous gas detection experiment running on the mixed-signal neuromorphic chip TEXEL. The on-chip classifier yielded an accuracy of 74.6\% while running at 482 $\unit{\nano\joule}$ per inference and 27 \unit{\micro\watt} of static-power.