In situ fabrication of porous polymer films embedded with perovskite nanocrystals for flexible superhydrophobic piezoresistive sensors.

The application of pressure sensors based on perovskite in high-humidity environments is limited by the effect of water on their stability. Endowing sensors with superhydrophobicity is an effective strategy to overcome the issue. In this work, MAPbBr3/Polyvinylidene Fluoride-TFSI composite was prepared by a one-step in-situ strategy to form a flexible superhydrophobic pressure sensor, which exhibited a contact angle of 150.25°. The obtained sensor exhibited a sensitivity of 0.916 in 1 kPa, a detection limit of 0.2 Pa, a precision of 0.1 Pa, and a response/recovery of ∼100 ms, along with good thermal stability. Through density functional theory calculations, it is revealed that the formation of the porosity is attributed to the interaction between the polymer and EMIM TFSI, which further leads to superhydrophobicity. And, the perovskite structure is easy to change under pressure, affecting the carrier transport and electrical signals output, which explains the sensing mechanism. In addition, the sensor performed well in monitoring facial expression, pulse, respiration, finger bending, and wind speed ranging from 1 m/s to 6 m/s. With both the Linear Regression and the Random Forest algorithm, the sensor can monitor the wind speed with an R2 greater than 0.977 in 60 tests.

Machine Learning-Assisted Sensor Based on CsPbBr3@ZnO Nanocrystals for Identifying Methanol in Mixed Environments.

Methanol is a respiratory biomarker for pulmonary diseases, including COVID-19, and is a common chemical that may harm people if they are accidentally exposed to it. It is significant to effectively identify methanol in complex environments, yet few sensors can do so. In this work, the strategy of coating perovskites with metal oxides is proposed to synthesize core-shell CsPbBr3@ZnO nanocrystals. The CsPbBr3@ZnO sensor displays a response/recovery time of 3.27/3.11 s to 10 ppm methanol at room temperature, with a detection limit of 1 ppm. Using machine learning algorithms, the sensor can effectively identify methanol from an unknown gas mixture with 94% accuracy. Meanwhile, density functional theory is used to reveal the formation process of the core-shell structure and the target gas identification mechanism. The strong adsorption between CsPbBr3 and the ligand zinc acetylacetonate lays the foundation for the formation of the core-shell structure. The crystal structure, density of states, and band structure were influenced by different gases, which results in different response/recovery behaviors and makes it possible to identify methanol from mixed environments. Furthermore, due to the formation of type II band alignment, the gas response performance of the sensor is further improved under UV light irradiation.

Engineering solutions to breath tests based on an e-nose system for silicosis screening and early detection in miners.

This study aims to develop an engineering solution to breath tests using an electronic nose (e-nose), and evaluate its diagnosis accuracy for silicosis. Influencing factors of this technique were explored. 398 non-silicosis miners and 221 silicosis miners were enrolled in this cross-sectional study. Exhaled breath was analyzed by an array of 16 organic nanofiber sensors along with a customized sample processing system. Principal component analysis was used to visualize the breath data, and classifiers were trained by two improved cost-sensitive ensemble algorithms (random forest and extreme gradient boosting) and two classical algorithms (K-nearest neighbor and support vector machine). All subjects were included to train the screening model, and an early detection model was run with silicosis cases in stage I. Both 5-fold cross-validation and external validation were adopted. Difference in classifiers caused by algorithms and subjects was quantified using a two-factor analysis of variance. The association between personal smoking habits and classification was investigated by the chi-square test. Classifiers of ensemble learning performed well in both screening and early detection model, with an accuracy range of 0.817-0.987. Classical classifiers showed relatively worse performance. Besides, the ensemble algorithm type and silicosis cases inclusion had no significant effect on classification (p> 0.05). There was no connection between personal smoking habits and classification accuracy. Breath tests based on an e-nose consisted of 16× sensor array performed well in silicosis screening and early detection. Raw data input showed a more significant effect on classification compared with the algorithm. Personal smoking habits had little impact on models, supporting the applicability of models in large-scale silicosis screening. The e-nose technique and the breath analysis methods reported are expected to provide a quick and accurate screening for silicosis, and extensible for other diseases.