AI-Enabled Portable E-Nose Regression Predicting Harmful Molecules in a Gas Mixture.

The biomimetic electronic nose (e-nose) technology is a novel technology used for the identification and monitoring of complex gas molecules, and it is gaining significance in this field. However, due to the complexity and multiplicity of gas mixtures, the accuracy of electronic noses in predicting gas concentrations using traditional regression algorithms is not ideal. This paper presents a solution to the difficulty by introducing a fusion network model that utilizes a transformer-based multikernel feature fusion (TMKFF) module combined with a 1DCNN_LSTM network to enhance the accuracy of regression prediction for gas mixture concentrations using a portable electronic nose. The experimental findings demonstrate that the regression prediction performance of the fusion network is significantly superior to that of single models such as convolutional neural network (CNN) and long short-term memory (LSTM). The present study demonstrates the efficacy of our fusion network model in accurately predicting the concentrations of multiple target gases, such as SO2, NO2, and CO, in a gas mixture. Specifically, our algorithm exhibits substantial benefits in enhancing the prediction performance of low-concentration SO2 gas, which is a noteworthy achievement. The determination coefficient (R2) values of 93, 98, and 99% correspondingly demonstrate that the model is very capable of explaining the variation in the concentration of the target gases. The root-mean-square errors (RMSE) are 0.0760, 0.0711, and 3.3825, respectively, while the mean absolute errors (MAE) are 0.0507, 0.0549, and 2.5874, respectively. These results indicate that the model has relatively small prediction errors. The method we have developed holds significant potential for practical applications in detecting atmospheric pollution detection and other molecular detection areas in complex environments.

UV-light-assisted gas sensor based on PdSe2/InSe heterojunction for ppb-level NO2 sensing at room temperature.

The fabrication of van der Waals (vdWs) heterostructures mainly extends to two-dimensional (2D) materials. Nevertheless, the current processes for obtaining high-quality 2D films are mainly exfoliated from their bulk counterparts or by high-temperature chemical vapor deposition (CVD), which limits industrial production and is often accompanied by defects. Herein, we first fabricated the type-II p-PdSe2/n-InSe vdWs heterostructure using the ultra-high vacuum laser molecular beam epitaxy (LMBE) technique combined with the vertical 2D stacking strategy, which is reproducible and suitable for high-volume manufacturing. This work found that the introduction of 365 nm UV light illumination can significantly improve the electrical transport properties and NO2 sensing performance of the PdSe2/InSe heterojunction-based device at room temperature (RT). The detailed studies confirm that the sensor based on the PdSe2/InSe heterojunction delivers the comparable sensitivity (Ra/Rg = ∼2.6 at 10 ppm), a low limit of detection of 52 ppb, and excellent selectivity for NO2 gas under UV light illumination, indicating great potential for NO2 detection. Notably, the sensor possesses fast response and full recovery properties (275/1078 s) compared to the results in the dark. Furthermore, the mechanism of enhanced gas sensitivity was proposed based on the energy band alignment of the PdSe2/InSe heterojunction with the assistance of investigating the surface potential variations. This work may pave the way for the development of high-performance, room-temperature gas sensors based on 2D vdWs heterostructures through the LMBE technique.