Robust gas recognition with mixed interference using a spiking neural network

Abstract Spiking neural networks (SNNs) have attracted significant interest owing to their high computing efficiency. However, few studies have focused on the robustness of SNNs and their application to electronic noses for gas recognition under strong interference. The goal of this study was to explore the robustness of a SNN for gas recognition under mixed interference. Data on mixed gases with different levels of interference were simulated by fitting experimental data. Two layers of a SNN based on leaky integrate-and-fire (LIF) neurons were constructed and the network was trained solely on datasets of pure targeted gases. Testing was then performed using data with mixed interference. The SNN achieved superior performance compared to other algorithms and remained 100% accurate for gas recognition up to a 10% interference ratio. The interval distance of spiking times between classes represents the robust capacity of the SNN according to the algorithm of the LIF neurons. SNNs have excellent capacity to maximize the differences between data of different classes and are promising candidates for electronic noses.