Efficient Hybrid Neuromorphic-Bayesian Model for Olfaction Sensing: Detection and Classification

TL;DR

This paper presents a hybrid neuromorphic-Bayesian model for olfaction sensing in robotics, combining spiking neural networks for feature extraction and probabilistic inference for detection, achieving energy efficiency and robustness.

Contribution

It introduces a novel hybrid neuromorphic-Bayesian approach that integrates convolutional and Bayesian spiking neural networks for odor detection and classification in robotics.

Findings

Superior energy efficiency compared to non-spiking models

Robustness to sensor drift demonstrated on dataset

Comparable accuracy with existing methods

Abstract

Olfaction sensing in autonomous robotics faces challenges in dynamic operations, energy efficiency, and edge processing. It necessitates a machine learning algorithm capable of managing real-world odor interference, ensuring resource efficiency for mobile robotics, and accurately estimating gas features for critical tasks such as odor mapping, localization, and alarm generation. This paper introduces a hybrid approach that exploits neuromorphic computing in combination with probabilistic inference to address these demanding requirements. Our approach implements a combination of a convolutional spiking neural network for feature extraction and a Bayesian spiking neural network for odor detection and identification. The developed algorithm is rigorously tested on a dataset for sensor drift compensation for robustness evaluation. Additionally, for efficiency evaluation, we compare the energy consumption of our model with a non-spiking machine learning algorithm under identical dataset and operating conditions. Our approach demonstrates superior efficiency alongside comparable accuracy outcomes.