Date of Award

6-2025

Degree Name

Doctor of Philosophy

Department

Electrical and Computer Engineering

First Advisor

Massood Z. Atashbar, Ph.D.

Second Advisor

Bradley J. Bazuin, Ph.D.

Third Advisor

Binu B. Narakathu, Ph.D.

Fourth Advisor

Dinesh Maddipatla, Ph.D.

Keywords

Artificial intelligence, environmental sensors, flexible electronics, graphene, hysteresis compensation, machine learning

Abstract

Flexible sensor technology has recently gained tremendous momentum in both academic research and industrial applications, transitioning from conceptual frameworks to practical implementations across diverse fields. This remarkable advancement can be attributed to several converging factors, including the maturation of nanomaterial science, the advancements of machine learning algorithms, and the critical demand for intelligent sensing solutions in healthcare, environmental monitoring, and industrial automation. The growing emphasis on personalized medicine and real-time health monitoring, accelerated by global health challenges, has further highlighted the necessity for accurate, cost-effective, and adaptable sensing platforms. This dissertation presents the fulfillment of three interconnected research projects focused on developing advanced graphene-based flexible sensors and machine learning models to address fundamental challenges in humidity and temperature sensing applications.

In the first project, low cost and highly sensitive graphene oxide-based flexible temperature sensors were developed for wearable applications. Recently developed graphene-based temperature sensors have limitations such as low production scalability and requiring hazardous solvents. To address these limitations, a facile and scalable fabrication process was employed to create temperature sensors by bar-coating water-based graphene oxide ink on silver-based interdigitated electrodes printed on flexible polyimide substrates. The sensors were encapsulated by Kapton tape, resulting in outstanding humidity stability (0.2 %/% RH sensitivity). The sensors achieved high temperature sensitivity with a temperature coefficient of resistance of -1.25 %/°C.

In the second project, innovative fluorinated graphene-based humidity sensors were developed on flexible substrates for environmental monitoring applications. The sensing mechanism exploits the strong interaction between fluorinated graphene and water molecules through hydrogen bonding facilitated by the electronegativity of fluorine atoms. Fluorinated graphene was drop-cast onto silver-based interdigitated electrodes printed on flexible polyimide substrates to form the sensing layer. These sensors demonstrated excellent sensitivity across a wide humidity range (20-80% RH), achieving 0.22 %/% RH for resistive sensors and 6.23 %/% RH for capacitive sensors. First-principles density functional theory calculations confirmed the high humidity sensitivity of fluorinated graphene (water molecule adsorption energy of -0.50 eV).

In the third project, advanced machine learning models were developed and integrated with humidity sensors to address the critical challenge of hysteresis compensation and drift correction in dynamic sensing environments. Traditional calibration approaches struggle with non-linear sensor behaviors and historical dependencies that compromise measurement accuracy in real-world applications. To overcome these limitations, various machine learning regression models were trained using sensor resistance data collected across multiple humidity cycles. Moving averages of historical sensor readings were incorporated to features to capture temporal dependencies. Among the tested algorithms, a Multi-Layer Perceptron neural network achieved superior performance with a root mean square error of 3.20 and R² value of 0.9755, demonstrating effective sensor hysteresis and drift compensation environmental, providing reliable measurements in dynamic conditions where traditional methods fail.

Access Setting

Dissertation-Open Access

Download

Share

COinS