Electrical Engineering and Computer Science electronic theses and dissertations (MU)
Permanent URI for this collection
The items in this collection are the theses and dissertations written by students of the Department of Electrical and Computer Engineering. Some items may be viewed only by members of the University of Missouri System and/or University of Missouri-Columbia. Click on one of the browse buttons above for a complete listing of the works.
Browse
Recent Submissions
Item Modeling of gallium oxide vertical transistors for high power applications(University of Missouri--Columbia, 2024) Titirsha, Twisha; Islam, Syed Kamrul[EMBARGOED UNTIL 12/01/2025] Ultra-wide bandgap semiconductors, such as gallium oxide (Ga2O3), have gained considerable interest in recent years due to their extremely wide bandgap >(4 eV), high breakdown strength ( 8 MV cm--1), and satisfactory electron mobility (200-250 cm2/V s). This interest stems from its potential application in high-power electronic devices across various domains, including electric vehicles, high-performance computing, and green energy technologies. However, one significant challenge in harnessing Ga2O3 for power applications has been associated with the lack of stable p-type doping. This limitation is effectively addressed by fin field-effect transistor (FinFET) structures, designed on an n-type substrate, eliminating the need for p-type doping. Vertical Ga2O3 power devices promise efficient carrier movement and fast operational speed, overcoming short-channel effects in ultra-high-density integrated circuits. This research work aims to cover two main areas of vertical Ga2O3 device modeling: physics-based analytical modeling, and device simulation using numerical simulators. An extensive physics-based surface potential model has been formulated in this study for a vertical Ga2O3 FinFET. In addition, the investigation utilizes statistical analysis using the Monte Carlo simulation technique to study the changes in leakage current in Ga2O3 FinFET. Furthermore, this study proposes a current-voltage and a capacitance-voltage model as a function of surface potential. The verification of the analytical model with experimental data, along with the incorporation of numerical simulators (TCAD), confirms the importance and potential of the proposed models in rapidly creating and characterizing next-generation high-performance vertical Ga2O3 power transistors.Item Feature learning for supervised knowledge discovery(University of Missouri--Columbia, 2024) Veal, Charlie T; Anderson, Derek T.In the expansive landscape of Artificial Intelligence (AI) / Machine Learning (ML), the identification and description of important data characteristics, termed features, is essential for solving complex real world problems. However, where do these features come from and how should they be used? The answer to these fundamental questions impact nearly every AI/ML approach and application. Traditionally, features have been either hand-crafted by human experts or data-driven derived through AI/ML. Herein, the notion of data driven features or, more specifically, feature learning is thoroughly investigated, inside of this dissertation, in the context of adversarial learning, open set recognition, and self supervised learning. First, I demonstrate a feature learning framework, driven by evolutionary optimization, that enables knowledge discovery with respect to adversarial learning. Second, I demonstrate an alternative feature learning framework, driven by neural metric learning and self supervision, that enables knowledge discovery with respect to open set recognition. Collectively, the capabilities of these frameworks are demonstrated on computer vision applications. Experiments illustrate domain improvements, including improved accuracy on open set recognition benchmarks and the capacity to discover meaningful patterns within unknown datasets.Item Neural oscillations : two characterization algorithms and a biophysical network model(University of Missouri--Columbia, 2024) Chen, Ziao; Nair, Satish S.Neural data has become increasingly accessible due to advances in recording techniques and computational capabilities. This abundance of neural data presents both a significant challenge and an essential endeavor: the systematic analysis of this data and the application of reverse engineering principles to reveal the brain's concealed mechanisms. Computational neuroscience plays a key role in this effort, aided by the rapid progress in statistical techniques and machine learning. Within this context, neural oscillations are of great importance. They coordinate neuron ensembles, facilitating communication and cognitive processes. This dissertation focuses on the analysis of electrophysiological data and computational models at the cellular and network levels. The three core chapters aim to address the following objectives: In chapter 2, a pipeline was developed to improve characterization of oscillatory bursts and synthesize surrogate data that facilitates the evaluation of detection algorithms from individual recordings. In chapter 3, a scheme using simulations and machine learning was developed to infer the properties of single neurons from in vivo extracellular recordings, enhancing the construction of realistic network models. In chapter 4, a biophysical realistic computational model was used to investigate how microcircuits in the motor cortex interact to generate beta and gamma oscillations.Item Explainable linguistic characterizations of black boxes(University of Missouri--Columbia, 2024) Alvey, Brendan; Anderson, Derek T.Recent breakthroughs in Artificial Intelligence (AI) have led to incredible new products and systems built off of Large Language Models (LLMs), such as ChatGPT. Linguistic models have the potential to communicate results much more effectively than graphical visualizations alone. Despite their undeniable power and usefulness, LLMs often hallucinate answers which makes them unsuitable for critical applications. This dissertation first presents work showing how advances in simulation and AI are used to improve explosive hazard detection (EHD) models. It then shows how to characterize those models through graphical visualizations. Next, a method for constructing accurate and deterministic linguistic summaries of black box (BB) models is developed and demonstrated on the EHD problem. Lastly, this foundation is extended to compare multiple BB systems. This opens the door for automated and explainable comparisons of BB, which could be used to make self-improving, closed-loop AI systems.Item Multimodal data fusion for real-time detection of obstructive sleep apnea(University of Missouri--Columbia, 2024) Paul, Tanmoy; Mohammad Mosa, Abu Saleh; Islam, Syed KamrulSleep apnea is a respiratory disorder that is characterized by interruption in breathing during sleep. Obstructive sleep apnea (OSA) is the most common form of apnea affecting about 29.4 million adults in the United States. It has been linked with multiple health complications including daytime fatigue, cardiovascular dysfunction, pre-operative, and post-operative complications, etc. Severe form of apnea can even be lethal if not treated timely. Yet about 80 percent of the OSA patients remain undiagnosed. Overnight polysomnography (PSG) is the current gold-standard of OSA diagnosis that has various limitations including expense, set-up complexity, and lack of facilities for conducting an overnight PSG. As a result, an alternative of laboratory PSG is highly desired. This study proposes an artificial intelligence (AI) based OSA detection model that is capable of detecting apneic activity in real-time without the supervision of a sleep expert using an optimum number of sensors. Electrocardiogram (ECG) and blood-oxygen saturation signals (SpO2) were collected for apnea detection from an open-source database. Multiple AI models were developed to detect apnea from the individual signals and their fusion. In addition, this work adopts depthwise separable convolution to build a lightweight and low-parametric apnea detection model from the raw signals without any signal pre-processing. The proposed model involves fewer floating-point operations resulting in improved energy efficiency per prediction. Moreover, the model operates on an overlapping processing window of 12s enabling per-second detection of apnea. Furthermore, this work performs a qualitative post-hoc visual explanation technique on the model and provides insights into the reasoning behind its decisions.