Engineering Commons^™

Exploring Machine Learning Techniques For Embedded Hardware, Neel R. Vora

Computer Science and Engineering Theses

This thesis delves into the intricate symbiosis between machine learning (ML) methodologies and embedded hardware systems, with a primary focus on augmenting efficiency and real-time processing capabilities across diverse application domains. It confronts the formidable challenge of deploying sophisticated ML algorithms on resource-constrained embedded hardware, aiming not only to optimize performance but also to minimize energy consumption. Innovative strategies are explored to tailor ML models for streamlined execution on embedded platforms, with validation conducted across various real-world application domains. Notable contributions include the development of a deep-learning framework leveraging a variational autoencoder (VAE) for compressing physiological signals from wearables while …

A Wearable Sensing System For High-Speed Interface Of Wide Range Electrochemical Sensor Array, Shanthala Lakshminarayana

Electrical Engineering Dissertations

Electrochemical sensing systems have emerged as indispensable tools in various fields due to their remarkable sensitivity, selectivity, and versatility. They play a pivotal role in modern research, industry, environmental monitoring, and healthcare devices. In environmental monitoring, these systems are deployed for detecting pollutants, heavy metals, and toxic gases, facilitating real-time monitoring, and ensuring environmental safety. Whereas, in the biomedical field, electrochemical sensing systems play a crucial role in diagnosing diseases, monitoring biomarkers etc, thereby revolutionizing healthcare practices.

Cost-effective wearable electrochemical sensing devices are significant for democratizing healthcare and improving public health outcomes. These devices enable continuous monitoring of physiological parameters, …

A Comprehensive Exploration Of Fundamental And Experimental Characteristics Of Nanophotonic Metasurfaces, Nasrin Razmjooei

Electrical Engineering Dissertations

The advent of diffraction gratings with periodic unit cells has led to numerous advancements in theoretical studies and practical applications. Recently, these structures have been recognized as subsets of “meta-surfaces” or “meta-materials”, employing periodically aligned features at the wavelength scale to manipulate electromagnetic wave properties for diverse applications. This manipulation extends to controlling amplitude, phase, spectral distribution, polarization state, and the local mode structure of light across various spectral expressions. A significant characteristic of these metasurfaces is their ability to couple incident light to laterally propagating leaky Bloch modes in the subwavelength regime, resulting in resonance at specific wavelengths known …

Pulsed Dielectric Breakdown And Permittivity Characterization Of Composite Solid Insulators In Pulsed Power Systems, Shawn T. Scoggin

Electrical Engineering Dissertations

In high voltage pulsed power systems, liquids and gases are often used as insulating materials because they offer high breakdown strengths, conform around complex geometries, and are self-healing, but they can introduce significant engineering challenges and restrictions when it comes to implementing them. Solid dielectrics can be desirable for improving the maintenance requirements, shelf life, and power/energy density metrics associated with insulating high voltage pulsed power systems, however they possess design challenges of their own. Solid dielectrics are not self-healing and can be difficult to manufacture, especially around complex geometries. Epoxy dielectrics are of high interest because of their naturally …