Browsing by Subject "Gaussian Process Regression"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Gaussian Process Regression and Monte Carlo Simulation to Determine VOC Biomarker Concentrations Via Chemiresistive Gas Nanosensors
    (IEEE Xplore, 2021-06) Rivera, Paula Angarita; Woollam, Mark; Siegel, Amanda P.; Agarwal, Mangilal; Mechanical and Energy Engineering, School of Engineering and Technology
    Utilizing chemiresistive gas sensors for volatile organic compound (VOC) detection has been a growing area of investigation in the last decade. VOCs have been extensively studied as potential biomarkers for biomedical applications as they are byproducts of metabolic pathways which are dysregulated by disease. Therefore, sensor arrays have been fabricated in previous studies to detect VOC biomarkers. In the process of testing these sensors, it is highly advantageous to quantify the concentration of the VOC biomarkers with high accuracy to diagnose the disease with high sensitivity and specificity. To investigate, analyze, and understand the relation between the concentrations of the VOC to the sensor resistance response, Gaussian Process (GP) models were implemented to predict the behavior of the data with respect to the resistance when the sensor is exposed to a range of concentrations of VOCs. Additionally, the relation between the concentration and resistance of the sensor was studied to predict the concentration of the VOC when a resistance is obtained. Monte Carlo Simulation Sampling from the GP model was utilized to generate data to further understand the trend. The results demonstrated that the relation between the concentration and resistance is linear. The model was tested with sampling data and its accuracy was evaluated.
  • Thumbnail Image
    Item
    Image Segmentation, Parametric Study, and Supervised Surrogate Modeling of Image-based Computational Fluid Dynamics
    (2022-05) Islam, Md Mahfuzul; Yu, Huidan (Whitney); Du, Xiaoping; Wagner, Diane
    With the recent advancement of computation and imaging technology, Image-based computational fluid dynamics (ICFD) has emerged as a great non-invasive capability to study biomedical flows. These modern technologies increase the potential of computation-aided diagnostics and therapeutics in a patient-specific environment. I studied three components of this image-based computational fluid dynamics process in this work. To ensure accurate medical assessment, realistic computational analysis is needed, for which patient-specific image segmentation of the diseased vessel is of paramount importance. In this work, image segmentation of several human arteries, veins, capillaries, and organs was conducted to use them for further hemodynamic simulations. To accomplish these, several open-source and commercial software packages were implemented. This study incorporates a new computational platform, called InVascular, to quantify the 4D velocity field in image-based pulsatile flows using the Volumetric Lattice Boltzmann Method (VLBM). We also conducted several parametric studies on an idealized case of a 3-D pipe with the dimensions of a human renal artery. We investigated the relationship between stenosis severity and Resistive index (RI). We also explored how pulsatile parameters like heart rate or pulsatile pressure gradient affect RI. As the process of ICFD analysis is based on imaging and other hemodynamic data, it is often time-consuming due to the extensive data processing time. For clinicians to make fast medical decisions regarding their patients, we need rapid and accurate ICFD results. To achieve that, we also developed surrogate models to show the potential of supervised machine learning methods in constructing efficient and precise surrogate models for Hagen-Poiseuille and Womersley flows.