Classifying continuous, real-time e-nose sensor data using a bio-inspired spiking network modelled on the insect olfactory system

Abstract

In many application domains, conventional e-noses are frequently outperformed in both speed and accuracy by their biological counterparts. Exploring potential bio-inspired improvements, we note a number of neuronal network models have demonstrated some success in classifying static datasets by abstracting the insect olfactory system. However, these designs remain largely unproven in practical settings, where sensor data is real-time, continuous, potentially noisy, lacks a precise onset signal and accurate classification requires the inclusion of temporal aspects into the feature set. This investigation therefore seeks to inform and develop the potential and suitability of biomimetic classifiers for use with typical real-world sensor data. Taking a generic classifier design inspired by the inhibition and competition in the insect antennal lobe, we apply it to identifying 20 individual chemical odours from the timeseries of responses of metal oxide sensors. We show that four out of twelve available sensors and the first 30 s (10%) of the sensors' continuous response are sufficient to deliver 92% accurate classification without access to an odour onset signal. In contrast to previous approaches, once training is complete, sensor signals can be fed continuously into the classifier without requiring discretization. We conclude that for continuous data there may be a conceptual advantage in using spiking networks, in particular where time is an essential component of computation. Classification was achieved in real time using a GPU-accelerated spiking neural network simulator developed in our group.

GeNN: a code generation framework for accelerated brain simulations

“…GeNN is already being used in a number of projects including the Green Brain Project 41 and a sub-project of the Human Brain Project 42 43 . It has already provided new biological insights by allowing to simulate our insect olfaction model 30 with the more realistic Hodgkin-Huxley neurons for the first time and it is used for underpinning the efficient simulation of a model of the honeybee brain in the Green Brain Project 44 .…”

Online decorrelation of humidity and temperature in chemical sensors for continuous monitoring

“…Additionally, humidity sensors are extremely appealing due to a high correlation between humidity levels and human perception of air quality [45,46]. Thus, when combined with other techniques [18,35,47,27,48,49], our model is likely to significantly enhance the performance of chemical detection systems, as for instance of home monitoring tasks. Our contribution thus emphasizes the importance of simultaneous recordings of humidity and temperature, and that their use is computationally amenable in sensor boards using low-energy micro-controllers.…”

Bio-Inspired Strategies for Improving the Selectivity and Sensitivity of Artificial Noses: A Review

“…The European universities involved in this project explored different neuromorphic algorithms implemented in a platform suitable for robotic integration. Diamond et al [200] proposed a model of the insect antennal lobe, able to process noisy signals in real time. Recently, Borthakur et al [201] utilized an external plexiform layer to enable online training without risk of forgetting and integrating a confidence indicator.…”