Triboelectric-induced ion mobility for artificial intelligence-enhanced mid-infrared gas spectroscopy

Isopropyl alcohol molecules, as a biomarker for anti-virus diagnosis, play a significant role in the area of environmental safety and healthcare relating volatile organic compounds. However, conventional gas molecule detection exhibits dramatic drawbacks, like the strict working conditions of ion mobility methodology and weak light-matter interaction of mid-infrared spectroscopy, yielding limited response of targeted molecules. We propose a synergistic methodology of artificial intelligence-enhanced ion mobility and mid-infrared spectroscopy, leveraging the complementary features from the sensing signal in different dimensions to reach superior accuracy for isopropyl alcohol identification. We pull in "cold" plasma discharge from triboelectric generator which improves the mid-infrared spectroscopic response of isopropyl alcohol with good regression prediction. Moreover, this synergistic methodology achieves ~99.08% accuracy for a precise gas concentration prediction, even with interferences of different carbon-based gases. The synergistic methodology of artificial intelligence-enhanced system creates mechanism of accurate gas sensing for mixture and regression prediction in healthcare.