https://scholar.google.co.in/scholar_url?url=https://www.mdpi.com...

https://scholar.google.co.in/schola...Nf3FUzbLitYfhPsIehKty_Q&html=&folt=kw

Application of Neuromorphic Olfactory Approach for High-Accuracy Classification of Malts
Anup Vanarse 1,* , Adam Osseiran 1, Alexander Rassau 2 and Peter van der Made 1

1 Brainchip Research Institute, Perth 6000, Australia; [email protected] (A.O.); [email protected] (P.v.d.M.) 2 School of Engineering, Edith Cowan University, Joondalup 6027, Australia; [email protected]
* Correspondence: [email protected]

Abstract: Current developments in artificial olfactory systems, also known as electronic nose (e-nose) systems,havebenefitedfromadvancedmachinelearningtechniquesthathavesignificantlyimproved the conditioning and processing of multivariate feature-rich sensor data.

These advancements are complemented by the application of bioinspired algorithms and architectures based on findings from neurophysiological studies focusing on the biological olfactory pathway.

The application of spiking neural networks (SNNs), and concepts from neuromorphic engineering in general, are one of the key factors that has led to the design and development of efficient bioinspired e-nose systems. However, only a limited number of studies have focused on deploying these models on a natively event-driven hardware platform that exploits the benefits of neuromorphic implementation, such as ultra-low-powerconsumptionandreal-timeprocessing,forsimplifiedintegrationinaportablee-nose system.

In this paper, we extend our previously reported neuromorphic encoding and classification approach to a real-world dataset that consists of sensor responses from a commercial e-nose system when exposed to eight different types of malts.

We show that the proposed SNN-based classifier was able to deliver 97% accurate classification results at a maximum latency of 0.4 ms per inference with a power consumption of less than 1 mW when deployed on neuromorphic hardware. One of the key advantages of the proposed neuromorphic architecture is that the entire functionality, including pre-processing, event encoding, and classification, can be mapped on the neuromorphic system-on-a-chip (NSoC) to develop power-efficient and highly-accurate real-time e-nose systems.