[D-3] Advanced Technologies for Bio- and Chemical Sensing

[D-3-03] A Neuromorphic Olfactory System Using Temporal Encoded Spiking Neural Networks

〇Jiseong Im^1,2, Donghee Kim^1,2, Woo Young Choi^1,2, Jong-Ho Lee^1,2 (1. Seoul National Univ. (Korea), 2. Inter-Univ. Semiconductor Res. Center (ISRC) (Korea))

Presentation style: On-site (in-person)

https://doi.org/10.7567/SSDM.2022.D-3-03

An efficient neuromorphic system for fast and relia-ble gas detection is proposed. FET-type gas sensors with an In2O3 sensing layer are fabricated and measured. Temporal encoded spiking neural network (SNN) predicts the type and concentration of the target gas using the gas responses of the sensors. Only 10 sensors are used and the network successfully detects the type and concentration of H2S and NO2 gases with low error (~3%) and fast infer-ence time (~7 s).