Spike latency coding in a biologically inspired micro-electronic nose

Hung Tat Chen (1) , Kwan Ting Ng (1) , Amine Bermak (1) , Man Kay Law (1) , Dominique Martinez (2)

1 HKUST - Hong Kong University of Science and Technology
2 CORTEX - Neuromimetic intelligence

Recent theoretical and experimental findings suggest that biological olfactory systems utilize relative latencies or time-to-first spikes for fast odor recognition. These time domain encoding methods have been demonstrated to exhibit reduced computational requirements and improved classification robustness [9], [12]. In this paper, we introduce a microcontroller (MCU) based electronic nose system using time domain encoding schemes to achieve a power efficient, compact and robust gas identification system. A compact (4.5cm×5cm×2.2cm) electronic nose, which is integrated with a tin oxide gas sensor array and capable of wireless communication with computers or mobile phones through Bluetooth, was implemented and characterized using three different gases (ethanol, carbon monoxide and hydrogen). During operation, the readout circuit digitizes the gas sensor resistances into a concentration independent spike timing pattern, which is unique for each individual gas. Both sensing and recognition operations have been successfully demonstrated in hardware. Two classification algorithms (rank-order and spikedistance) have been implemented. Both algorithms require no explicit knowledge of the gas concentration to achieve simplified training procedures, and exhibit comparable performances with conventional pattern recognition algorithms while enabling hardware friendly implementation.

Mots clés: Neuromorphic engineering; olfactory system; Electronic nose; Gas Sensors; Spiking neurons

Domaines: Réseau de neurones [cs.NE]

Hung Tat Chen, Kwan Ting Ng, Amine Bermak, Man Kay Law, Dominique Martinez. Spike latency coding in a biologically inspired micro-electronic nose. IEEE Transactions on Biomedical Circuits and Systems, 2011, 5, 2, pp.160-168. ⟨inria-00543031⟩