Signal Processing Commons^™

Extending Geometric Acoustic Ray Tracing To Multi-Room Environments: A Case Study On Gunshot Sound Transmission Between Adjacent Rooms, Tyler Ton

Theses and Dissertations

Accurate localization of gunshots in multi-room building environments remains a challenging problem in acoustic forensics and public safety applications. Existing approaches model sound propagation within a single room, neglecting the transmission of acoustic energy through walls and other building materials. This thesis presents a study on modeling multi-room gunshot acoustic transmission, combining geometric ray tracing with structural acoustic transmission-loss modeling to generate impulse responses for two horizontally adjacent rooms separated by a shared wall, providing a foundation for future inter-room gunshot localization work. The proposed system uses GSound-SIR, a geometric acoustics engine, to simulate sound propagation in both of the …

Ai-Driven Biomarker Discovery & Progression Modeling For Precision Diagnosis Of Glaucoma, Cheng Huang

Computer Science and Engineering Theses and Dissertations

This dissertation presents a comprehensive study on the integration of artificial intelligence (AI) for glaucoma diagnosis and retinal image analysis. Leveraging multimodal imaging data including fundus photography, Optical Coherence Tomography Optical Coherence Tomography (OCT) and Optical Coherence Tomography Angiography (OCTA), the research develops a suite of deep learning frameworks designed to detect early glaucomatous changes with high precision, robustness, and interpretability. A series of novel architectures are introduced, spanning vessel segmentation networks, biomarker discovery pipelines, and multimodal fusion models, all designed to enhance diagnostic accuracy and generalizability across diverse populations. To facilitate reproducible and scalable ophthalmic AI research, this work …

Explainable Machine Learning For Biomedical Diagnostics: Optical Imaging And Eeg Signal Analysis, Fozia Rajbdad

LSU Doctoral Dissertations

The growing convenience of complex biomedical data begins new roads for better disease detection and functional identification via artificial intelligence (AI). Nevertheless, conventional analysis methods often rely on basic metrics that drop sensitive biotic differences, and various AI systems are difficult to infer, limiting their clinical reliability and practical use. There is a growing need for explainable, physiologically relevant computational models that can extract key biomarkers from diverse biomedical data sources. This dissertation addresses this problem by obtaining explainable machine learning and deep learning procedures for studying biomedical signals and optical imaging data.

This dissertation is divided into two parts; …

Constructing Orthonormal Bases With The Residuals Of Successive Approximations, An Introduction To Multiresolution Analysis, Elijah J. Guptill

Master's Theses

Wavelets and wavelet analysis are used in the study of signal processing, quantum field theory, functional analysis, multifractal analysis, and various other areas of mathematics. Multiresolution analysis provides a framework for building a wavelet basis of $\mathcal{L}^{2}(\mathbb{R})$ from a scaling function $\phi$, whose dyadic dilations and translations, $\{2^{j /2}\phi(2^{j}x-k):j,k\in \mathbb{Z}\}$, approximate $\mathcal{L}^{2}(\mathbb{R})$. One of the key properties of  $\phi$ is that it must satisfy $\phi(x)=\sum_{k\in \mathbb{Z}}{p_{k}2^{j /2}\phi(2^{j}x-k)}$ with respect to the norm on $\mathcal{L}^{2}(\mathbb{R})$. This equation is called a two-scale difference equation. Such equations enforce a regularity on the ordinary generating function $2^{-1 /2}\sum_{k\in \mathbb{Z}}{p_{k}z^{k}}$, known as the quadrature condition. …

Efficient Mathematical Modeling And Synthesis Of Realistic Musical Instrument Sounds, Andrew Chookaszian

Master's Theses

This thesis develops and evaluates a compact parametric additive synthesis model for isolated musical instrument tones. The method analyzes a single-note recording, estimates its fundamental frequency, extracts harmonic amplitude and frequency behavior, and stores the sound as a reduced set of interpretable parameters. These parameters include the note duration, pitch, per-harmonic amplitude envelopes, phase information, and amplitude- and frequency-modulation vibrato parameters. The stored model is then used to resynthesize the tone without directly using the original audio waveform.

The model was evaluated using synthetic signals, real instrument samples, objective error metrics, storage comparisons, pitch and duration modification tests, and listening …

A Study On Quantization And Hardware Cost Tradeoffs In A 5g Nr Ldpc Decoder On Fpga, Giancarlo Acosta

Master's Theses

The fixed-point implementation of a 5G New Radio LDPC decoder forces a tradeoff between precision and hardware cost, governed by the variable node word length W_L, the check node message width W_R, and the normalized min-sum correction factor α. This thesis characterizes how these three parameters affect both error correction performance and FPGA resource utilization for an LDPC decoder on an established LDPC decoder architecture. A bit-accurate MATLAB core model records bit error rate (BER) and frame error rate (FER) while a verified HDL Coder model generates synthesizable VHDL for Vivado synthesis, and both are swept …

Deep Learning For Affect Recognition: A Comparative Study Of Physiological Sensor-Based And Facial Image-Based Approaches, Ravi Panchal, Ravi Panchal

Master's Theses

This thesis investigates deep learning approaches for affect recognition using wearable physiological signals and facial image data. The sensor-based component evaluates stress and affect recognition on the WESAD dataset using wrist-based physiological windows and examines multiple temporal modeling strategies, including convolutional, recurrent, hybrid CNN-LSTM, attention-based, ensemble, and time-frequency approaches.

The image-based component evaluates hard-label facial expression recognition on AffectNet+ using pre-trained ResNet-50, EfficientNet-B3, and ConvNeXt-Tiny architectures across Easy, Challenging, and Difficult subsets representing different levels of expression ambiguity.

Experimental results show that the proposed Multi-Branch Attention CNN-BiLSTM (MBA-CNN-BiLSTM) model achieves the strongest wearable stress- and affect-recognition performance among the evaluated …

Practical Multimodal Wearable Sensing For Functional Upper Extremity Primitive Classification With Application To Stroke Rehabilitation, Nicholas Weiss

Master's Theses

Stroke often causes long-term weakness and impaired motor control in the upper extremity (UE), making everyday tasks such as reaching, grasping, and moving objects more difficult. Restoring functional arm use is therefore a central goal of post-stroke rehabilitation. Measuring affected arm use continuously and objectively is important because isolated clinical assessments may not fully capture how the affected arm is used during therapy or daily life. Wearable sensors offer a promising approach for monitoring, but raw sensor signals are difficult to interpret directly. Functional movement primitives address this issue by describing UE behavior as smaller, task-agnostic movement units.

This thesis …

Transcranial Ac Modulation Of Cerebellar Nuclear Activity In Awake Animals, Nuran Kavakli

Dissertations

Entrainment of cerebellar nuclear (CN) cells via cerebellar transcranial alternating current stimulation (ctACS) has been reported in animals under ketamine/xylazine anesthesia. Our main objective was to demonstrate modulation of CN activity in unanesthetized, freely moving animals using ctACS. Multi-channel carbon-fiber electrodes were implanted into the interpositus nucleus for recording multi-unit (MU) activity, and thin-film electrodes were implanted subcutaneously over the posterior cerebellum for stimulation. A frequency-domain-based metric was developed to quantify modulation from MU signals. The results demonstrated modulation in a wide range of frequencies (4 Hz-300 Hz) as in anesthetized animals. In contrast, the amplitude of the peak in …

Visualization And Marker-Less Tracking Of User-Defined Pre-Processed Mri Articulator Data Using Deep Learning, Michael De George

Student Theses

This thesis presents a comprehensive framework for the automated tracking and visualization of articulatory movements based on magnetic resonance imaging (MRI) data. A well-known data analysis tool for markerless pose estimation, known as DeepLabCut, is investigated for this purpose. The performance of this tool is enhanced through the design and implementation of a pre-processor. DeepLabCut is a markerless pose estimation toolbox based on deep learning, which overcomes the issue of making manual annotations frame-by-frame. Limitations from manually marking the MRI images are addressed by implementing transfer learning with convolutional neural networks to achieve accurate, user-defined articulator tracking without markers. Current …

Securing Distributed Energy Resources: A Dnp3 Master Station With Semantic Web Integration For Decentralized Der Data Sovereignty, Ethan J. Coffman

Electrical Engineering and Computer Science Undergraduate Honors Theses

As current electrical grids trend toward a heavier reliance on DERs, there is a growing need to secure DER communications while maintaining data sovereignty for device owners. Previously, work by Donna Thakadipuram established the foundation for a decentralized framework using Solid by implementing a prototype that used a Raspberry Pi and a DSP to simulate Modbus traffic and upload the data to a Solid server. This thesis extends her work to simulate multiple DERs using Typhoon HIL and communicate to each device over DNP3/TCP. The system uses a Python-based DNP3 master to collect telemetry from all 12 DERs before transforming …

Hardware Integration Of Preamble Based 802.11a Wi-Fi Frame Location For Usrp Radios, Nicholas P. Margavio

Honors Theses

Internet of Things (IoT) refers to a network of devices that can exchange information over the internet, and its deployments are projected to reach 30.9 billion by 2025, with most lacking encryption. One solution for these unencrypted devices is to use Specific Emitter Identification (SEI). SEI exploits distinct, native, and unintentional features of a radio’s signal to identify it and enhance wireless network security uniquely. For example, IEEE 802.11a Wireless-Fidelity (Wi-Fi) radio waveforms have a fixed structure that occupies the first 16 microseconds, from which SEI features can be extracted and used to identify the originating radio. By removing the …

Learning Global Context For Sparse Activity Recognition In Lengthy Recordings With Limited Dataset Size, Zeyu Tang

All Dissertations

This dissertation describes methods to analyze lengthy recordings of data in order to detect sparsely occurring activities. The narrative below describes the progression of research that led to the development of these methods and their generalization into a unified framework. My research started with designing models for dietary monitoring, including detecting meals from day-long recordings and detecting intake gestures from meal-length recordings. Both tasks share some common characteristics: (a) the target event takes only a small portion of data recordings, and (b) there is global context within full-length data recordings that can help a model make better decisions. After finishing …

Cooperative Unmanned Aerial System (Uas) Geolocation Of Emitters, Christopher Peters

Electrical Engineering Theses and Dissertations

A collection of unmanned aerial systems (UAS) can be networked as a cooperative wireless sensor array to geolocate an unknown-location RF emitter using time-based measurements. In operation, however, environmental multipath and hardware errors in sensor positioning and timing can degrade emitter localization accuracy and limit the practicality of single-snapshot solutions. This dissertation evaluates time-of-arrival and time-difference-of-arrival (TOA/TDOA) geolocation for cooperative UAS arrays under realistic error sources and develops geometry-control strategies that actively reduce localization uncertainty through iterative UAS repositioning.

This work studies the Location on a Conic Axis (LOCA) method for emitter localization. Using Monte Carlo simulations with hardware error …

Ellie - Exteroceptive Light Locomotion In Eukaryote-Fungi, Brandon Etwarroo

Doctoral Dissertations and Master's Theses

Over the past decade, fungal research and its technological applications have expanded across multiple disciplines, including the emerging field of biohybrid systems. This thesis develops and evaluates a wireless, untethered mobile robot controlled by the action potential-like activity generated by Pleurotus ostreatus sporocarps under red, green, and blue optical stimulation. Light is applied to the sporocarps, the resulting electrical responses are recorded, and these signals are transmitted wirelessly to actuate the mobile robot. Both the action potential-like activity patterns and the robot’s movement trajectories were analyzed. The results demonstrate that wireless robotic control mediated by fungal electrophysiology is feasible. Overall, …

A Pretraining-Based Framework For On-Device Training Of Imu-Based Locomotion Mode Detection For Wearable Active Exoskeletons, Muhammad Tahir Khan

LSU Master's Theses

Active exoskeletons are being developed to support human movement in physically demanding industries such as construction. For these systems to work effectively, they must be able to correctly identify the user’s current activity. This process is known as locomotion mode detection and plays an important role in selecting the appropriate control parameters for exoskeletons. Many existing approaches use inertial measurement units (IMUs) to recognize these activities and have shown strong performance. However, most of these methods depend on large amounts of labeled data collected under specific conditions. As a result, they often do not perform well when applied to new …

Flexible Fault-Tolerant Multi-Die Fpga-Based Architectures For Varying Space Environments, Yosof Ali Seif El Din Ali Maklad

Theses and Dissertations

It is well-known fact that spacecraft’s electronic components operate in an extreme harsh and varying space environments, beside changing orbit or passing through Van Allan Belts during orbital course results of radiation levels change. This thesis focuses on SRAM-based FPGA systems on-board of such spacecrafts, that are commonly utilized in space applications’ critical applications due to their capabilities and flexibility to reconfigure, since these systems are vulnerable to frequent negative impacts of ionizing radiation, thus inducing soft and hard errors leading to disastrous failures that could jeopardize the entire spacecraft. The soft errors’ effects are frequent yet can be mitigated, …

Universal Sound Separation: Distance-Aware Mixture Simulation, Co-Occurrence Conditioning, And Chain-Of-Inference, Wonjun Park

Computer Science and Engineering Theses - Archive

Universal Sound Separation (USS) -- the task of disentangling arbitrary sound sources from a single-channel acoustic mixture -- remains an open challenge due to the ill-posed nature of the problem and the distributional gap between synthetic training data and real-world recordings. This thesis addresses three distinct bottlenecks in the USS pipeline: training data realism, inference strategy, and conditioning richness. We first present two knowledge-guided approaches to sound source separation. The first is a distance-aware mixing strategy that leverages Large Language Models (LLMs) to assign plausible loudness relationships between audio sources during training data synthesis. By querying an LLM about the …

Deep Learning For Wireless Communications, Swarada Ajit Kulkarni

Electrical Engineering Dissertations

The rapid evolution of wireless communication imposes stringent requirements for ultra-reliable, low-latency transmission in dynamic, interference-prone environments. Traditional model-driven signal processing struggles to adapt to nonlinear hardware effects, time-varying channels, and complex interference patterns. Deep learning (DL) offers a transformative, data-driven alternative, enabling end-to-end optimization and robust adaptation under uncertain propagation conditions.

This dissertation investigates deep learning architectures for intelligent and resilient wireless communication through three complementary contributions. The first introduces a Vision Transformer (ViT)-based modulation classification framework that leverages self-attention to capture local and global dependencies in spectrogram representations of Quadrature Amplitude Modulation (QAM) signals. The ViT achieves superior …

A Digital Calibration Source For 21 Cm Cosmology Telescopes, Kalyani Balkrishna Bhopi

Graduate Theses, Dissertations, and Problem Reports (ETD)

Precise calibration of radio telescope beams and gains is a central requirement for 21 cm intensity mapping experiments, which aim to measure large scale cosmological structure through the redshifted emission line of neutral hydrogen. Bright astrophysical foregrounds dominate the sky at these frequencies, and separating them from the cosmological signal demands precise control over instrumental systematics, particularly the telescope beam and its frequency-dependent response. Existing aerial calibration sources are incoherent broadband emitters, detectable only as total power. They provide no direct phase information and suffer from poor sensitivity in low signal-to-noise regimes.

We present the Precision Emitter for 21cm Array …

Robotizing Complex Welding Processes Through Imitation Learning And Generative Models From Human Demonstration, Yue Cao

Theses and Dissertations--Electrical and Computer Engineering

Arc welding processes demand real-time adaptive control that current robotic systems cannot achieve autonomously. This dissertation develops a systematic framework to robotize complex welding by learning from human demonstration, integrating generative modeling, physics-informed reconstruction, and model-based imitation learning. First, human--robot collaboration systems are established for both Gas Tungsten Arc Welding (GTAW) and Double-Electrode Gas Metal Arc Welding, combining robotic teleoperation with virtual reality interfaces to capture high-quality operator demonstrations. Second, a physics-informed neural network framework reconstructs complete molten pool flow fields from high-speed imaging, enriching process understanding beyond direct sensor observation. Third, generative models, including a hybrid latent variational autoencoder …

Hyperglycemia Detection From Sigle - Lead Ecg Using A Hybrid Cnn & Transformer Model, Adam Ayomikun Ogunjembola

Graduate Theses, Dissertations, and Problem Reports (ETD)

Abstract
Hyperglycemia Detection from Single-Lead ECG using a Hybrid CNN & Transformer Model
Adam Ogunjembola

Diabetes Mellitus is known as high blood glucose. This high blood glucose level happens when the body has a problem with producing or using insulin. Insulin is a very important hormone that the pancreas makes to control how much glucose gets into the bloodstream and cells. Diabetes Mellitus has an effect on the body if it is not treated, such as damaging the blood vessels and nerves which can lead to stroke, kidney failure, heart attack and permanent loss of vision. Since people with diabetes …

Bridging Physics-Based Modeling And Machine Learning To Predict Material Behavior: Applications In Fatigue Crack Growth And Dielectric Property Characterization, Ansan Pokharel

Graduate Theses, Dissertations, and Problem Reports (ETD)

This dissertation integrates physics-based modeling with machine learning (ML) to predict how materials behave under complex thermal and mechanical conditions. A key innovation of this work is the use of finite element analysis (FEA) to supplement experimental data. This approach creates more diverse and representative synthetic datasets, helping to reduce the limitations and biases that arise when training ML models solely on experimental measurements. The research focuses on two applications: improving the prediction of fatigue properties in superalloys and estimating temperature-dependent, high-frequency dielectric properties relevant to microwave-based chemical processing.

In the first study, low-cycle fatigue experiments were performed on the …

The Design And Analysis Of Robust Mems Devices For Extreme Space Environments, Joshua Taggart

Honors Undergraduate Theses

The purpose of this study is to analyze aluminum nitride (AlN) micro-electromechanical systems (MEMS) resonators designed for extreme-environment applications. The devices of study are Lamb wave, piezoelectric resonators designed and fabricated using conventional semiconductor manufacturing processes and operating around various frequencies in the megahertz range. The purpose of this study is to advance understanding of MEMS devices in extreme-temperature and radiated environments for outer-space applications.

Devices were tested under vacuum at temperatures ranging from room temperature (~21°C) to 800°C. Under these conditions, the device was measured both as a resonator and in an oscillator circuit. Results show that the resonant …

Experimental Validation Of Optical Wireless Communication And Power Transfer For Uav Applications, Fnu Dhruv

UNF Graduate Theses and Dissertations

Unmanned Aerial Vehicles (UAVs) have revolutionized emergency response, disaster assessment, and search-and-rescue operations. However, their operational efficacy is fundamentally constrained by limited battery endurance and the susceptibility of traditional radio-frequency communication to disruption in adverse weather. To address these limitations, this thesis proposes and experimentally validates a novel architecture integrating Free-Space Optical (FSO) communication with Simultaneous Lightweight Information and Power Transfer (SLIPT). This system utilizes a split-beam configuration to concurrently enable high-bandwidth data transmission and optical energy harvesting to replenish the UAV's battery pack. The research was conducted in three progressive phases. Initially, system feasibility was established through rigorous optical …

Adaptive Deep Learning In Physical Layer Applications, Ali Owfi

All Dissertations

Traditionally, signal processing models in communication systems have been designed based on solid foundations in statistics and information theory, often assuming linearity and optimizing for simplified models. However, real-world communication systems exhibit numerous imperfections and non-linearities that traditional linear models struggle to capture accurately. Deep Learning (DL)-based approaches, unconstrained by rigid mathematical models, have shown promise in optimizing system performance by accommodating specific hardware configurations and dynamic channel conditions as an alternative to the traditional methods. Despite all the recent research efforts on DL-based methods for physical layer applications, DL models have still not been widely applied to physical layer …

Deterministic Methods To Improve The Field-Of-View For Direction Finding Using Sparse Digital Arrays, Nolan J. Egging

Master's Theses

Direction finding algorithms are used with digital phased arrays to determine the incoming angle of arrival (AoA) of an incident signal. These algorithms, and direction finding as a whole, have a wide range of civilian and military applications from radar, electronic reconnaissance, mobile communication, et cetera. However, for situations where the spacing between antenna elements needs to be large, gating lobes appear in the radiation pattern of analog arrays. This work demonstrates that for digital beamforming algorithms, the field of view (FoV) of a uniform linear digital array matches the grating lobe free range of a similarly spaced analog array. …

Beam Steering Control For A Small-Scale 5g Antenna Array, Omar Wagih Elkalesh

Graduate Theses and Dissertations

This thesis demonstrates the design, development, and validation of a full-scale adaptive beam steering control system of a small-scale 5G antenna array, designed and thoroughly evaluated with MATLAB Simulink. Overcoming the significant challenge of establishing strong wireless links in dynamic environments, the new system uses a new closed-loop control framework that can automatically detect the signal sources and automatically change the beam direction in real-time. The use of the adaptation is necessary to combat tracking errors that are caused by the mobility of the mobile users, environmental variations, as well as channel estimation errors, widespread in future wireless communication systems. …

Multi-Modal Depth Estimation Using Camera And Mmwave Sensors, Alston D. Devero-Belfon

Student Theses

For accurately estimating the depth of environments with varying lighting conditions, reliable methods are limited. By utilizing wireless sensor technology in conjunction with cameras, a wide range of environments can be visualized, and objects within these environments can be tracked and monitored. Such methods offer cost-effective alternatives and provide a more secure, data-at-rest option for individuals with low vision, while also enhancing machine perception. In this work, we develop such a prototype that utilizes wireless sensors and cameras, which act in sync, enabling us to estimate the depth of objects within varying lighting environments to a level that is recognizable …

Exploring Longitudinal Stability Of Spatiotemporal Sequential Patterns By Means Of Autoencoder Schemes For Eeg Based Personal Identification, Muhammed E. Oztemel

LSU Doctoral Dissertations

Robust personal identification remains a critical and challenging task in the digital era. Electroencephalography (EEG) offers a unique biometric modality that captures individual brain dynamics through complex neural signals. This dissertation proposes autoencoder (AE) based feature extraction and subject identification through these features. EEG recordings are first transformed into topographic maps to represent spatial brain activity. Consecutive topomaps are then concatenated to capture temporal transitions across frames. Convolutional autoencoders (CAEs) are used to learn spatial and temporal patterns, while domain-adaptive AEs are designed to model evoked potential based responses. Additionally, self-attention mechanism is incorporated to enhance feature representation. To analyze …