Signal Processing Commons^™

Novel Electrophysiological Biomarkers In Pediatric Drug Resistant Epilepsy And Genetic Epilepsy Syndromes, Sakar Rijal

Bioengineering Dissertations - Archive

Pediatric epilepsies, particularly those that are drug-resistant or genetically driven, represent some of the most complex neurological disorders encountered in childhood. Central to their pathophysiology is a disruption in the delicate balance between cortical excitation and inhibition (E/I), often resulting from impaired GABAergic interneuron function. This imbalance manifests as aberrant network dynamics and altered neural oscillations, giving rise to seizures and long-term cognitive impairments. In this thesis, we developed a translational framework to identify electrophysiological biomarkers that (i) assess cortical E/I imbalance and (ii) map epileptogenic zones, with the aim of enhancing diagnosis, guiding surgical planning, and informing therapeutic monitoring …

Smart Irrigation System Using Iot And Lstm For Optimal Water Management, Farley Y. Ruiz

Electrical Engineering Theses - Archive

This thesis presents the design and implementation of a smart irrigation system that combines Internet of Things hardware with a Long Short-Term Memory (LSTM) neural network for predictive soil moisture management. The goal is an affordable and reliable solution that uses real-time sensor data and environmental data to schedule irrigation before the substrate moisture drops below its target range. The system integrates soil moisture, temperature, humidity, and sensors on an Arduino Nano that communicates wirelessly with a Raspberry Pi. The Raspberry Pi runs a Python/Flask backend that collects and processes data, executes the LSTM model, and serves a secure web …

Power Quality Event Diagnosis Using Multi-Rate Neural Networks, Jordan D. Lloyd

Electrical Engineering Theses - Archive

Power quality disturbances (PQDs) are among the primary challenges facing modern electrical systems, as they degrade the performance and lifespan of connected equipment. This thesis investigates the relationship between the rate at which voltage waveform data are sampled, the reliability of these measurements, and the ability of deep neural networks to classify PQDs accurately. A one-dimensional convolutional neural network (CNN) was trained and evaluated across multiple sampling rates and signal-to-noise ratios to quantify how information loss in the temporal and spectral domains affects classification reliability. The results demonstrate that model accuracy degrades nonlinearly as sampling rate and signal-to-noise ratio (SNR) …

Revealing Spatiotemporal Neural Activation Patterns In Electrocorticography Recordings Of Human Speech Production By Mutual Information, Julio Kovacs, Dean Krusienski, Minu Maninder, Willy Wriggers

Mechanical & Aerospace Engineering Faculty Publications

Background

Spatiotemporal mapping of neural activity during continuous speech production has been traditionally approached using correlation coefficient (CC) analysis between cortical signals and speech recordings. A prior study employed this approach using electrocorticography (ECoG) data from participants who underwent invasive intracranial monitoring for epilepsy. However, CC cannot detect nonlinear relationships and is dominated by the correspondence between periods of silence and of non-silence.

New Method

We introduce the mutual information (MI) measure, which can capture both linear and nonlinear dependencies. We validated CC and MI on the sub-second spatiotemporal brain activity recorded during continuous speech tasks. To refine the results, …

Study Of Deep Neural Network Trained With Salient, Compressed Medical Video Data For Enhanced Predication, Aileen Sengupta

Electrical Engineering Dissertations - Archive

The rapid growth of surgical video analysis presents a need for efficient deep learning models for surgical training, while reducing the need for excessive image and video image storage. Traditional training approaches typically rely on uniformly compressed video data, instead of selectively preserving the most surgically relevant regions. This dissertation investigates the impact of training deep neural networks (DNNs), both convolutional and transformer-based architectures, on saliency-guided, differentially compressed surgical video sequences. The study systematically evaluates how such compression influences prediction accuracy, computational efficiency and storage requirements. Experimental results demonstrate that models trained on ROI-focused compressed data combined with motion vectors …

Neurovascular Coupling Impairments In Acute Traumatic Brain Injury: An Eeg-Nirs Analysis, Zachary Armstrong

Bioengineering Theses - Archive

Traumatic brain injury (TBI) is a major cause of neurological impairment, often leading to variable recovery and uncertain prognosis in the neurocritical care setting. There is a pressing clinical need for robust, physiologically grounded biomarkers to inform prognosis and therapeutic decision-making in acute TBI. This thesis investigates neurovascular coupling (NVC), the physiological coordination between neuronal activity and cerebral blood flow, as a candidate biomarker for brain function and recovery after injury.

A prospective cohort study was performed using simultaneous electroencephalography (EEG) and near-infrared spectroscopy (NIRS) recordings in patients with moderate-to-severe TBI and healthy controls. Wavelet transform coherence (WTC) analysis was …

A Multiscale Ai Framework For Forest And Agriculture Health Monitoring: Drone-Based Object Recognition And Segmentation For Automated Ecological Assessment, Sruthi Keerthi Valicharla

Graduate Theses, Dissertations, and Problem Reports (ETD)

Forest and agricultural ecosystems are increasingly at risk due to invasive species, pests, and diseases, necessitating scalable, automated, and intelligent monitoring solutions. Traditional field based forest and agriculture health assessments are limited by cost, time, and spatial coverage. This dissertation presents a multiscale deep learning framework that automates forest and agriculture health monitoring using drone imagery and computer vision techniques. The system operates across three spatial levels: forest level, tree level, and leaf level, combining object detection, segmentation, and classification models to support large scale ecological assessment.

At the forest level, high-altitude drone imagery is processed using object detection and …

Transformer-Based Symbolic Music Generation, Ben Buentello

Master’s Theses

This thesis investigates the capacity of transformer-based architectures to learn generalized musical patterns through symbolic generation. To support this exploration, a complete music generation pipeline was developed, beginning with the construction and classification of a large-scale dataset of over 170,000 MIDI files. The dataset was processed using rule-based heuristics and custom neural classifiers to separate tracks by musical function and contour. A novel tokenization scheme, MINTii, was introduced to encode musical information compactly through interval-based representations, reducing redundancy and promoting generalization. Using this infrastructure, a transformer model was trained to generate single-track melodic sequences. Its performance was evaluated through both …

Trace Flight Computer, Zachary Stratton, Vandad Mossavand Varkaneh, Nicholas Ely

Williams Honors College, Honors Research Projects

In the world of collegiate rocketry, there are currently no commercial-off-the-shelf flight computers capable of being fitted to liquid engine rockets with thrust vectoring control. Currently, amateur rocketeers utilize unreliable Arduino-based systems or expensive drone computers. The objective of this project is to design a flight computer capable of data collection and filtering, telemetry transmission, and real-time controls of critical safety systems using readily available commercial-off-the-shelf components to allow rocketeers to complete their designs within a reasonable budget. The system will collect data from two IMUs, a barometric altimeter, and a magnetometer, then filter the collected data using custom Kalman …

Cochlear Electrode Insertion Training Model, Sarah Powell, Kaelyn E. Kraley, Nathan J. Smith

Williams Honors College, Honors Research Projects

Cochlear implant surgery is a delicate procedure performed by Otolaryngologists (ENTs) to implant an electronic device into the inner ear to provide a sense of sound for people who are profoundly deaf or hard of hearing. The current practices of training involve cadavers and 3D-printed models. Cadavers are commonly used but are expensive, single-use, and do not provide visual and haptic feedback, which are essential for medical students. 3D printed models are less commonly used and are hard to fabricate and not as realistic. If medical students are not properly trained for this delicate procedure, then risks are significantly increased …

Vector Estimation For Continuous Tracking Of Observed Radio Signals (V.E.C.T.O.R.) Lunar Navigation System, Dimitry Melnikov, Evan Bartel, Andrew Burrier, Goran Gjorgievski

Williams Honors College, Honors Research Projects

NASA's Artemis program requires precise navigation capabilities to establish the first sustained presence on the lunar surface. However, as launches bring necessary orbital infrastructure, the Artemis program will face a critical period during which reliable lunar navigation is not possible. To address this challenge, the V.E.C.T.O.R. system tracks assets, such as rovers and astronauts, as User Terminals relative to a pre-existing cell tower, or Base Station. To do so, the system leverages existing Base Station hardware to calculate the location of User Terminals in conjunction with existing communications infrastructure.

Scalable Hypergraph Structure Learning With Diverse Smoothness Priors, Benjamin T. Brown

Theses and Dissertations--Electrical and Computer Engineering

In graph signal processing, learning weighted connections between nodes from signals is a fundamental task when the underlying relationships are unknown. With the extension of graphs to hypergraphs, where edges can connect more than two nodes, graph learning methods have similarly been generalized to hypergraphs. However, the absence of a unified framework for calculating total variation has led to divergent definitions of smoothness and, consequently, differing approaches to hyperedge recovery. This challenge is confronted in this work through generalization of several previously proposed hypergraph total variations, allowing ease of substitution into a vector-based optimization. To this end, a novel hypergraph …

Waveforms For Next Generation Non-Stationary Channels, Zhibin Zou

Electronic Theses & Dissertations (2024 - present)

Waveform design aims to achieve orthogonality among data signals/symbols across all available Degrees of Freedom (DoF) to avoid interference while transmitted over the channel. Precoding involves the decomposition of the channel matrix into orthogonal components for the purpose of constructing a precoding matrix that is then combined with the data signal to achieve orthogonality in the spatial dimension. On the other hand, modulation uses orthogonal carriers in a certain signal space to carry data symbols with minimal interference from other symbols. However, it is widely evident that next Generation (xG) wireless systems will experience very high mobility, density and time-varying …

Improving Large Scale Face Recognition With Identity Codes, Mohammad Saeed Ebrahimi Saadabadi

Graduate Theses, Dissertations, and Problem Reports (ETD)

Despite significant advances in deep face recognition, current systems face several practical challenges in real-world scenarios. These include high computational cost of training on large-scale datasets, inefficient use of metric space, and mismatch between training and evaluation frameworks. This dissertation addresses these limitations through three completed studies. The first part presents a research effort aimed at addressing the computational bottlenecks of large-scale FR training. This work proposes a framework that replaces conventional scalar identity labels with structured identity codes, \ie, sequences of tokens optimized to preserve semantic and metric separation. The formulation is designed to reduce the computational cost of …

Neural Network-Based Image Compression, Atefeh Khoshkhahtinat

Graduate Theses, Dissertations, and Problem Reports (ETD)

The rapid advancement of information technology and the exponential growth of digital communication have significantly increased the demand for efficient data compression techniques that reduce storage requirements, minimize bandwidth consumption, and accelerate data transmission—without substantially compromising data quality. This dissertation addresses these challenges by investigating and developing advanced learned image compression (LIC) methods, with a particular focus on lossy compression for both natural images and scientific imagery obtained from NASA’s Solar Dynamics Observatory (SDO) mission. Traditional image compression standards—such as JPEG, JPEG2000, BPG, and HEVC—rely on manually engineered transforms and heuristic rules, which often lack the adaptability required to accommodate …

Green Bank Chime/Frb Outriggers Commissioning And Analog System Development, Kholoud Sharif Tag Alkhatem Khairy

Graduate Theses, Dissertations, and Problem Reports (ETD)

The main objective of this thesis is to document the development and commissioning of the Canadian Hydrogen Intensity Mapping Experiment. (CHIME) outrigger at the Green Bank Observatory. (GBO) in Green Bank, WV. This novel cylindrical wide-field radio transient telescope is currently operating in conjunction with CHIME. The CHIME outrigger at GBO aims to contribute significantly to the field of radio astronomy, with implications for both Fast Radio Burst. (FRB) science and broader astronomical research. The construction and commissioning of the CHIME outrigger at the GBO mark a pivotal step forward in pursuing high-precision wide-field detection and localization of radio transients, …

Identification Of Fiducial Points In Seismocardiographic Cycles Using Manual And Automated Annotation Methods, Jasmine-Vy T. Truong

Honors Undergraduate Theses

There is currently a need for complementary methods for non-invasive cardiac monitoring. Seismocardiography (SCG), the measurement of cardiac-induced vibrations at the chest surface, has shown potential clinical utility. Improving the reliability of detecting fiducial points of electrocardiography (ECG) and SCG, which collectively capture the electro-mechanical cardiac activities, could expand ECG/SCG utility as a low-cost, accessible tool for clinical assessment. This study identifies commonly accepted criteria for fiducial point detection in SCG and ECG through an extensive literature review and signal processing techniques. The previous criteria were evaluated to identify their strengths and weaknesses. Based on the findings, an improved set …

Design, Fabrication, & Laboratory Testing Of A Strain Gage Instrumentation System For Marine Applications, Salem C. Homrighausen

UNF Graduate Theses and Dissertations

A strain gage-based instrumentation system was designed and fabricated to measure the moment present at the base of a mock, diesel-engine snorkel for a submerged vehicle designed to operate in the surf zone. Afterwards, a lab experiment was designed and executed to determine the accuracy of the instrument and a 2-dimensional, matrix-vector equation was formulated to relate pairs of voltages, Vx and Vy, to moments, Mx and My for the experiment. Three versions of this model were built. The first model was created using traditional statics equations governing strain, stress, moment, force. The second and third models were built directly …