Graduation Semester and Year
Summer 2025
Language
English
Document Type
Dissertation
Degree Name
Doctor of Philosophy in Mechanical Engineering
Department
Mechanical and Aerospace Engineering
First Advisor
Hyejin Moon
Abstract
This dissertation introduces intelligent microfluidic platforms by combining advanced DEP-based manipulation with real-time visual feedback. A DEP device featuring circular corral traps and dual-plane electrodes enables precise submicron particle trapping, high-resolution particle separation, and cell-particle co-assembly. Simulations and experiments confirm enhanced electric field control and stable confinement. To enable adaptive operation in EWOD systems, a deep learning model (U-Net) was developed for real-time droplet meniscus segmentation. The model achieved 98% accuracy and remained robust under noisy, low-contrast conditions. A live video pipeline was implemented, enabling consistent frame-by-frame feedback for closed-loop control. Together, these innovations establish a foundation for autonomous, high-performance microfluidic systems in biomedical, diagnostic, and manufacturing applications.
Keywords
Dielectrophoresis, Machine Learning, Droplet Segmentation, Intelligent Microfludic Systems
Disciplines
Electro-Mechanical Systems
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Recommended Citation
Danesh, Negar, "Intelligent Microfluidic Systems for Precision Manipulation and Real-Time Recognition via Dielectrophoresis and Deep Learning" (2025). Mechanical and Aerospace Engineering Dissertations. 427.
https://mavmatrix.uta.edu/mechaerospace_dissertations/427