Efficient Hybrid Neuromorphic-Bayesian Model for Olfaction Sensing: Detection and Classification
Rizwana Kausar, Fakhreddine Zayer, Jaime Viegas, Jorge Dias
TL;DR
The paper addresses energy efficiency, edge processing, and robustness in artificial olfaction for mobile robots under sensor drift. It proposes a hybrid neuromorphic-Bayesian architecture that uses a convolutional spike layer for feature extraction and a Bayesian spiking readout for detection and classification. Key findings include substantial energy savings and competitive accuracy under short- and long-term drift on the Gas Sensor Array Drift Dataset. The work demonstrates a practical framework for robust, low-power odor sensing with potential for enhancements via feedback mechanisms and uncertainty-aware filtering.
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.