Abstract
Current developments in artificial olfactory systems, also known as electronic nose (e-nose) systems, have benefited from advanced machine learning techniques that have significantly improved 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-power consumption and real-time processing, for simplified integration in a portable e-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.
Highlights
Published: 7 January 2022Research in machine olfaction and electronic nose (e-nose) systems has garnered much interest due to a number of novel applications that can be envisaged by implementing this technology [1]
The past thirty years have seen an increasingly large number of studies building on this foundational research to link the functional emulation of the biological olfactory pathway to artificial olfactory systems that can be implemented for real-world applications [1,4,5,6]
In the work presented in this paper, we extend our previously reported neuromorphic encoding and spiking neural networks (SNNs)-based classification approach to include performance parameters when deployed on Akida neuromorphic hardware [12]
Summary
Research in machine olfaction and electronic nose (e-nose) systems has garnered much interest due to a number of novel applications that can be envisaged by implementing this technology [1]. Inspired by the biological olfactory pathway, Persaud and Dodd proposed an electronic nose system that implemented a multi-sensor approach, combined with a signal conditioning and processing module, for the identification of various volatile compounds. The past thirty years have seen an increasingly large number of studies building on this foundational research to link the functional emulation of the biological olfactory pathway to artificial olfactory systems that can be implemented for real-world applications [1,4,5,6]. A conventional approach of processing electronic nose data includes four key stages: data
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
