Laser-ablated nanoparticle-enhanced quartz tuning fork (QTF) sensor array for detection of volatile organic compounds (VOCs) and their mixtures assisted by neural network.
Journal:
Mikrochimica acta
Published Date:
Jul 28, 2025
Abstract
The detection of volatile organic compounds (VOCs) and their mixtures is critical for applications ranging from environmental monitoring and industrial process control to non-invasive disease diagnostics. Electronic noses offer a promising route for selective VOC identification. In this work, we report an enhanced e-nose platform based on quartz tuning fork (QTF) sensors functionalized with polymer-nanoparticle (NP) composites. Silver (Ag), copper (Cu), and zinc oxide (ZnO) nanoparticles were synthesized via laser ablation at 532 nm and characterized. These nanoparticles were integrated into a polymer matrix, and QTFs were modified using these to fabricate four sensor configurations. The sensors were evaluated across a wide concentration range (200 ppb to 100 ppm) for acetone, isoprene, acetaldehyde, and their binary and ternary mixtures. Compared to polymer-only sensors, the NP-functionalized QTFs exhibited significantly improved sensitivity and stability. A neural network regressor trained on sensor response data achieved a prediction accuracy of 0.93 and an average area under the curve (AUC) of 0.98, demonstrating excellent classification performance. Double-blind tests yielded a mean prediction error of 6 ppm and an score of 0.85, with the model performing best at concentrations below 60 ppm. This work highlights a scalable approach for constructing high-performance, machine-learning-enabled VOC sensing platforms.
Authors
Keywords
No keywords available for this article.
