Electronic nose (e-nose) technology for selectively identifying a target gas through chemoresistive sensors has gained much attention for various applications, such as smart factory and personal health monitoring. To overcome the cross-reactivity problem of chemoresistive sensors to various gas species, herein, we propose a novel sensing strategy based on a single micro-LED (μLED)-embedded photoactivated (μLP) gas sensor, utilizing the time-variant illumination for identifying the species and concentrations of various target gases. A fast-changing pseudorandom voltage input is applied to the μLED to generate forced transient sensor responses. A deep neural network is employed to analyze the obtained complex transient signals for gas detection and concentration estimation. The proposed sensor system achieves high classification (~96.99%) and quantification (mean absolute percentage error ~ 31.99%) accuracies for various toxic gases (methanol, ethanol, acetone, and nitrogen dioxide) with a single gas sensor consuming 0.53 mW. The proposed method may significantly improve the efficiency of e-nose technology in terms of cost, space, and power consumption.
In this study, a novel sensing strategy to identify gas species selectively and to estimate the concentrations of multiple gases was proposed. Highly sensitive gold NPs coated GLAD In2O3 was used as a gas-sensing material, and time-variant pseudorandom illumination of a single monolithic micro-LED (μLED) photoactivated (μLP) gas sensor was applied. Transient sensor signals, owing to the rapid changes in the light intensity of μLED and different reaction kinetics of various gas species, facilitate the identification of gas species. A deep convolutional neural network (CNN) was used to effectively analyze the complex frequency spectrogram of the transient sensor signals. As such, the identification of four mono-gas environments and binary gas mixtures (mixed ethanol and methanol) were successfully demonstrated with high accuracy. The total power consumption of the μLP was only 0.53 mW, one-hundredth of the conventional electronic nose (e-nose) system. Therefore, the proposed method may significantly improve the efficiency of e-nose technology in terms of cost, space, and power consumption.