Abstract

Recent studies in bioinspired artificial olfaction, especially those detailing the application of spike-based neuromorphic methods, have led to promising developments towards overcoming the limitations of traditional approaches, such as complexity in handling multivariate data, computational and power requirements, poor accuracy, and substantial delay for processing and classification of odors. Rank-order-based olfactory systems provide an interesting approach for detection of target gases by encoding multi-variate data generated by artificial olfactory systems into temporal signatures. However, the utilization of traditional pattern-matching methods and unpredictable shuffling of spikes in the rank-order impedes the performance of the system. In this paper, we present an SNN-based solution for the classification of rank-order spiking patterns to provide continuous recognition results in real-time. The SNN classifier is deployed on a neuromorphic hardware system that enables massively parallel and low-power processing on incoming rank-order patterns. Offline learning is used to store the reference rank-order patterns, and an inbuilt nearest neighbor classification logic is applied by the neurons to provide recognition results. The proposed system was evaluated using two different datasets including rank-order spiking data from previously established olfactory systems. The continuous classification that was achieved required a maximum of 12.82% of the total pattern frame to provide 96.5% accuracy in identifying corresponding target gases. Recognition results were obtained at a nominal processing latency of 16ms for each incoming spike. In addition to the clear advantages in terms of real-time operation and robustness to inconsistent rank-orders, the SNN classifier can also detect anomalies in rank-order patterns arising due to drift in sensing arrays.

Highlights

  • In recent years, research focusing on the development of artificial olfactory systems, known as electronic nose systems, has gained significantly increased attention

  • The accuracy of the classifier recorded for this dataset was 100%, and a positive recognition was obtained following the reception of 20.3% (3.25 spikes) of the total 16-element pattern frame

  • The learning data consisting of six rank-order patterns were determined using the probabilistic rank-score coding, described in [17], which calculates the probability of a sensor spiking at a specific rank in the pattern for a target gas using j j

Read more

Summary

Introduction

Research focusing on the development of artificial olfactory systems, known as electronic nose systems, has gained significantly increased attention. This has been largely due to the diverse applications of these systems [1]. Whilst artificial olfactory systems emulate the biological model for sensing and processing of odor data, the biological olfactory pathway outperforms the current electronic systems in terms of accuracy and speed and can perform effectively even under rapidly changing environmental conditions [2,3]. The idea of implementing bioinspired methods for artificial olfaction generally focuses on using a sensor array with wide selectivity range, and processing methods that rely on extracting features from the sensor output, encoding them in patterns, and using pattern-matching algorithms for recognition logic [5,6].

Methods
Results
Discussion
Conclusion
Full Text
Published version (Free)

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 call