Scientific Paper
Machine learning approach to optimization of parameters for impedance measurements of Quartz Crystal Microbalance to improve limit of detection
Summary
Machine learning reduces the trial and error needed to set up impedance spectroscopy of QCM biosensors. Combining k-means clustering with a support vector machine cuts the number of experiments more than tenfold, and the resulting settings lower the detection limit for glycerol twelvefold on a 10 MHz crystal, an approach applicable to other resonant sensors.
Summary written by the openQCM team. The original abstract is on the publisher’s page.
More papers
Related work.
- Příprava aminových plazmových polymerů a jejich interakce s ECM proteiny 2019
- (Invited) Molecular Layer Deposition from Dissolved Precursors 2017
- Quartz Crystal Microbalance Assay of Clinical Calcinosis Samples and Their Synthetic Models Differentiates the Efficacy of Chelation-Based Treatments 2017
- Observing the Sedimentation of TiO2 Nanoparticles in Aqueous Solution Using a Quartz Crystal Microbalance with Dissipation Monitoring 2016
- Quartz Crystal Microbalance (QCM)-Based Portable System for Visualizing Reaction Kinetics in Secondary Chemistry Education 2025
- Development of gold nanospikes-modified quartz crystal microbalance biosensor for prostate specific antigen detection 2024
From the bibliography
New openQCM papers, by email.
A selection of new publications measured with openQCM, with software releases and application notes. A few emails a year.
Browse all papers.
Hundreds of peer-reviewed publications cite openQCM. Search full-text and filter by instrument, year, journal or topic.