Skip to main page content
Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
, 19 (5)

Odor Recognition With a Spiking Neural Network for Bioelectronic Nose

Affiliations

Odor Recognition With a Spiking Neural Network for Bioelectronic Nose

Ming Li et al. Sensors (Basel).

Abstract

Electronic noses recognize odors using sensor arrays, and usually face difficulties for odor complicacy, while animals have their own biological sensory capabilities for various types of odors. By implanting electrodes into the olfactory bulb of mammalian animals, odors may be recognized by decoding the recorded neural signals, in order to construct a bioelectronic nose. This paper proposes a spiking neural network (SNN)-based odor recognition method from spike trains recorded by the implanted electrode array. The proposed SNN-based approach exploits rich timing information well in precise time points of spikes. To alleviate the overfitting problem, we design a new SNN learning method with a voltage-based regulation strategy. Experiments are carried out using spike train signals recorded from the main olfactory bulb in rats. Results show that our SNN-based approach achieves the state-of-the-art performance, compared with other methods. With the proposed voltage regulation strategy, it achieves about 15% improvement compared with a classical SNN model.

Keywords: bioelectronic nose; odor recognition; spiking neural network.

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Odor recognition with spiking neural network.
Figure 2
Figure 2
(a) illustration of rat brain and olfactory bulb area (red circle); (b) microelectrode array (8 × 2 microwires).
Figure 3
Figure 3
Odor recognition accuracy using different bin sizes: (a) two-class case; (b) three-class case; (c) four-class case. The horizontal axis represents the bin size.
Figure 4
Figure 4
Odor recognition accuracy using different training sets: (a) two-class case; (b) three-class case; (c) four-class case. The blue line and red line represent Tempotron-VR and Tempotron algorithms, respectively. The horizontal axis represents the number of sample groups in training sets (each sample group contains a sample from each class).
Figure 5
Figure 5
Odor recognition accuracy within short time periods: (a) two-class case; (b) three-class case; (c) four-class case. The horizontal axis represents the length of time periods.

Similar articles

See all similar articles

References

    1. Persaud K., Dodd G. Analysis of recognition mechanisms in the mammalian olfactory system using a model nose. Nature. 1982;299:352. doi: 10.1038/299352a0. - DOI - PubMed
    1. Gardner J.W., Bartlett P.N. A brief history of electronic noses. Sens. Actuators B Chem. 1994;18:210–211. doi: 10.1016/0925-4005(94)87085-3. - DOI
    1. Breer H. Olfactory receptors: Molecular basis for recognition and discrimination of odors. Anal. Bioanal. Chem. 2003;377:427–433. doi: 10.1007/s00216-003-2113-9. - DOI - PubMed
    1. Lee S.H., Park T.H. Recent advances in the development of bioelectronic nose. Biotechnol. Bioprocess Eng. 2010;15:22–29. doi: 10.1007/s12257-009-3077-1. - DOI
    1. Wasilewski T., Gębicki J., Kamysz W. Bioelectronic nose: Current status and perspectives. Biosens. Bioelectron. 2017;87:480–494. doi: 10.1016/j.bios.2016.08.080. - DOI - PubMed
Feedback