Signal Processing Commons^™

Identifying Subject Bias In Wifi-Based Human Activity Recognition Evaluation Methods, Amany Elkelany, Robert J. Ross, Susan Mckeever

Conference papers

WiFi-based Human Activity Recognition (HAR) has emerged as a promising approach for monitoring and analysing human activities in a non-intrusive manner, leveraging WiFi signals for activity classification. Despite advancements, existing WiFi-based HAR research lacks consideration of subject (human) bias. This results in learning models performing well on individuals used in the training samples but failing to generalise to new/unseen subjects, in contrast to known good practices in machine learning. In this paper, we address this oversight directly by systematically examining the evaluation methodology for the WiFi-based HAR context. Specifically, we investigate the impact of Leave-One-Subject-Out Cross-Validation (LOSOCV) in a hybrid …

Strategies To Alleviate Flickering: Bayesian And Smoothing Methods For Deep Learning Classification In Video, Noah Miller, Glen Ryan Drumm, Lance Champagne, Bruce A. Cox, Trevor Bihl

Faculty Publications

Excerpt: Increasing reliance on autonomous systems requires confidence in the accuracies produced from computer vision classification algorithms. Computer vision (CV) for video classification provides phenomenal abilities, but it often suffers from “flickering” of results. Flickering occurs when the CV algorithm switches between declared classes over successive frames. Such behavior causes a loss of trust and confidence in their operations.

Global Empirical Model Of Sporadic-E Occurrence Rates, Eli V. Parsch, Anthony L. Franz, Eugene V. Dao, Dong L. Wu, Nimalan Swarnalingam, Cornelius C. J. H. Salinas, Daniel J. Emmons

Faculty Publications

Intense ionization enhancements in the Earth’s ionosphere, known as sporadic-E (E_s), can degrade and severely disrupt the propagation of radio signals. Although many previous studies have analyzed the characteristics and morphologies of sporadic-E, few efforts have attempted to model global E_s occurrence rates (ORs) at high time resolutions. This study develops a global empirical model of blanketing sporadic-E occurrence rates using a Karhunen–Loéve Expansion (KLE) of a global OR climatology built with Global Navigation Satellite System radio occultation (GNSS-RO) and ionosonde observations. Using an fbE ≥ threshold of 3 MHz, the model outputs a blanketing sporadic-E …

Real-Time Synthesis Of A Nonuniformly Correlated, Partially Coherent Beam Using An Optical Coordinate Tansformation, Milo W. Hyde Iv

Faculty Publications

We design, build, and validate an optical system for generating light beams with complex spatial coherence properties in real time. Beams of this type self-focus and are resistant to turbulence degradation, making them potentially useful in applications such as optical communications. We begin with a general theoretical analysis of our proposed design. Our approach starts by generating a Schell-model (uniformly correlated or shift-invariant) source by spatially filtering incoherent light. We then pass this light through an optical coordinate transformer, which converts the Schell-model source into a nonuniformly correlated field. After the general analysis, we discuss system engineering, including trade-offs among …

Impact Of Operational Ladar Occlusions On Point Cloud Instance Segmentation, Andrew D. Gibson

Theses and Dissertations

Data exploitation techniques are the enabler for technological advancements in military ISR applications of ladar ISR. By identifying instances of military objects in observed scenes, point cloud deep learning models can unlock new standards of real-time information delivery to warfighters. Although current deep learning training datasets do not include real-world collection occlusions consistent with military applications, this research characterizes SPT model performance by adding occlusions to the DALESObjects dataset via artificial flyby simulations.We find that a baseline model trained on unoccluded data suffers performance degradation on both semantic and instance segmentation tasks when evaluated on occluded data, but that the …

Remote Profiling Of Atmospheric Turbulence: Enhanced Resolution With Stacked Rayleigh Beacons In Tardis, Benjamin C. Wilson

Theses and Dissertations

A stacked beacon turbulence profiling methodology has been introduced and applied to have increased profiling on the Turbulence and Aerosol Research and Investigation System (TARDIS). The model was derived and demonstrated the applicability through discussion on data processing and inversion processes. The methodology was applied for two different nighttime experiments, one in Summer and one in Fall. C 2 n profiles were derived into the 1300 m altitude ranges for both nights and the summer experiment was compared to a co-located DELTA Sky measurements and LEEDR generated Climatological profiles. The comparison implied promise in the methodology with additional work needed …

Machine Learning-Based Design Of Doppler Tolerant Radar, Kyle Peter Wensell

Dissertations

In this work, machine learning theory is applied to the design of a radar detector in order to train a machine learning-based detector that is robust against Doppler shifts. The radar system is designed to work with data that would be otherwise intractable to conventional optimal detector design, such as transmitted noise waveforms and the effects of one-bit quantization at the receiver. The detection performance of the one-bit receiver is shown to match the performance of the derived square-law sign correlator detector. The resulting learning-based detector also introduces Doppler tolerance to the system, which allows for the successful detection of …

Star-Based Reachability Analysis Of Binary Neural Networks On Continuous Input, Mykhailo Ivashchenko

School of Computing: Dissertations, Theses, and Student Research

Deep Neural Networks (DNNs) have become a popular instrument for solving various real-world problems. DNNs’ sophisticated structure allows them to learn complex representations and features. However, architecture specifics and floating-point number usage result in increased computational operations complexity. For this reason, a more lightweight type of neural networks is widely used when it comes to edge devices, such as microcomputers or microcontrollers – Binary Neural Networks (BNNs). Like other DNNs, BNNs are vulnerable to adversarial attacks; even a small perturbation to the input set may lead to an errant output. Unfortunately, only a few approaches have been proposed for verifying …

Machine Learning And Geostatistical Approaches For Discovery Of Weather And Climate Events Related To El Niño Phenomena, Sachi Perera

Computational and Data Sciences (PhD) Dissertations

El Nino and La Nina are worldwide environmental phenomena brought about by repetitive changes in the water temperature of the Pacific Ocean. Even though the El-Nino impact focuses on a smaller area in the Pacific Ocean near the Equator, these developments have global repercussions, where temperature and precipitation are influenced across the globe, causing droughts and floods simultaneously. In this dissertation, we first derived a drought vulnerability index for the Nile basin, identifying regions with high and low drought risk under ENSO conditions. Next, we evaluated the coherence and periodicity of the ENSO signal to detect its implications on MENA …

Database And Machine Learning Model For Classifying Autism Spectrum Disorder From Smartphone Based Electroretinography, Rory Harris

Honors Scholar Theses

Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder that negatively affects a patient’s cognitive and communication aptitude and, therefore, can severely impact that patient’s quality of life. Because of this, early diagnosis is paramount. In recent studies, electroretinography (ERG), which is a measure of the retina’s electrical response to a brief flash of light into the eye, has shown promise in detecting ASD. Access to these scans can provide early diagnosis, improving well-being. Current ERG devices are very expensive due to their on board processing capabilities. This paper aims to create an ERG device using a smartphone as the main …

Enhancing Rotating Machinery Fault Diagnosis: A Dual-Head Attention Mechanism In Deep Learning Neural Networks, Qing Snyder

Dissertations

Rotating machinery is crucial to production efficiency and safety in manufacturing industries for an extended time. Ensuring machinery reliability necessitates effective diagnostic systems, particularly for rotating bearings, the key components of such equipment. Fault diagnosis in rotating machinery is essential to prevent failures and minimize downtime, thereby playing an important role in industrial operations. The application of advanced neural network techniques in industry has risen recently. Among these, attention-based neural networks, especially the Transformer models, are originally noteworthy for their sequential data handling capability. This research delves into attention-based algorithms for rotating machinery fault diagnosis, signifying a substantial advancement in …

Low Cost Magnetometer Calibration And Distributed Simultaneous Multipoint Ionospheric Measurements From A Sounding Rocket Platform, Joshua W. Milford

Doctoral Dissertations and Master's Theses

Low-cost and low-size-weight-and-power (SWaP) magnetometers can provide greater accessibility for distributed simultaneous measurements in the ionosphere, either onboard sounding rockets or on CubeSats. The Space and Atmospheric Instrumentation Laboratory (SAIL) at Embry-Riddle Aeronautical University has launched a multitude of sounding rockets in recent history: one night-time mid-latitude rocket from Wallops Flight Facility in August 2022 and three mid-latitude rockets from White Sands Missile Range during the October 2023 annular solar eclipse. All rockets had a comprehensive suite of instruments for electrodynamics and neutral dynamics measurements. Among this suite was one science-grade three-axis fluxgate magnetometer (Billingsley TFM65VQS / TFM100G2) and up …

Investigation Of Gas Dynamics In Water And Oil-Based Muds Using Das, Dts, And Dss Measurements, Temitayo S. Adeyemi

LSU Master's Theses

Reliable prediction of gas migration velocity, void fraction, and length of gas-affected region in water and oil-based muds is essential for effective planning, control, and optimization of drilling operations. However, there is a gap in our understanding of gas behavior and dynamics in water and oil-based muds. This is a consequence of the use of experimental systems that are not representative of field-scale conditions. This study seeks to bridge the gap via the well-scale deployment of distributed fiber-optic sensors for real-time monitoring of gas behavior and dynamics in water and oil-based mud. The aforementioned parameters were estimated in real-time using …

Random Forests For Detecting Weak Signals And Extracting Physical Information: A Case Study Of Magnetic Navigation, Mohammadamin Moradi, Zheng-Meng Zhai, Aaron Nielsen, Ying-Cheng Lai, Aaron P. Nielsen

Faculty Publications

It has been recently demonstrated that two machine-learning architectures, reservoir computing and time-delayed feed-forward neural networks, can be exploited for detecting the Earth’s anomaly magnetic field immersed in overwhelming complex signals for magnetic navigation in a GPS-denied environment. The accuracy of the detected anomaly field corresponds to a positioning accuracy in the range of 10–40 m. To increase the accuracy and reduce the uncertainty of weak signal detection as well as to directly obtain the position information, we exploit the machine-learning model of random forests that combines the output of multiple decision trees to give optimal values of the physical …

Small Unmanned Aircraft System Detection And Tracking With Audio, Computer Vision, And Deep Learning Techniques, Anthony C. Brunson

Theses and Dissertations

sUAS present significant risks to local and federal agencies when under the control of negligent, reckless, or criminal operators. In the face of an escalating presence of sUAS in shared airspace with traditional aircraft, and their deployment in protected airspace as potential weapons, safeguarding personnel, facilities, and assets becomes paramount. This research seeks to address this emerging threat by investigating the efficacy of integrating low-cost distributed sensors and Machine learning (ML) models to enhance battlespace awareness and complement existing sensing platforms for real-time sUAS detection, classification, and localization. The thesis introduces the conceptualization and development of a Drone Detection Command …

Investigation Of High-Latitude Gnss Radio Occulation Sporadic-E And Auroral-E Measurements, Kyle D. Roberts

Theses and Dissertations

Abnormal sporadic-E (E_s) occurrences were found in the high latitude regions during a recent climatology study by (Hodos, 2022), that calculated sporadic-E occurrence rates derived from a data set of GPS radio occultation (GPS-RO) and ionosondes. In this study, sporadic-E GNSS-RO techniques are shown to falsely attribute sporadic-E events to auroral-E (E_a) events. A comparative study is conducted on GPS-RO measurement techniques to find false occurrence rates for various RO techniques using a single ionosonde site in Gakona, Alaska. Phase-based RO techniques were found to be more likely to falsely attribute sporadic-E as auroral-E, while amplitude …

Dung Dkar Cloak: Exploring Soft Interfaces For Sonic Interactions, Judit Eszter Kárpáti, Esteban De La Torre

Textile Society of America: Symposium Proceedings

The importance of crossmodal interaction within the contemporary cultural, technological and scientific panorama has evidently gained significant attention due to its remarkable advantages in creating a meaningful, interwoven, and integrated experience. The use and recontextualization of textiles in such exploratory quest into the human senses has proven to be critical. Computational science, algorithmic logic and digital devices have always been rooted and closely interwoven with textile crafts and practices. Recent technological advancements have further combined technology and textile, generating interactive textile surfaces, constructing endless possibilities for multisensorial experiences. In this presentation we will examine how we can weave a sensitive …

Gnss Software Defined Radio: History, Current Developments, And Standardization Efforts, Thomas Pany, Dennis Akos, Javier Arribas, M. Zahidul H. Bhuiyan, Pau Closas, Fabio Dovis, Ignacio Fernandez-Hernandez, Carles Fernandez-Prades, Sanjeev Gunawardena, Todd Humphreys, Zaher M. Kassas, Jose A. Lopez Salcedo, Mario Nicola, Mario L. Psiaki, Alexander Rugamer, Yong-Jin Song, Jong-Hoon Won

Faculty Publications

Taking the work conducted by the global navigation satellite system (GNSS) software-defined radio (SDR) working group during the last decade as a seed, this contribution summarizes, for the first time, the history of GNSS SDR development. This report highlights selected SDR implementations and achievements that are available to the public or that influenced the general development of SDR. Aspects related to the standardization process of intermediate-frequency sample data and metadata are discussed, and an update of the Institute of Navigation SDR Standard is proposed. This work focuses on GNSS SDR implementations in general-purpose processors and leaves aside developments conducted on …

Artificial Intelligence Enabled Machinery Fault Detection And Diagnosis Using Vibro-Acoustic Signals, Srinivasa Rao Ippili

Theses and Dissertations--Mechanical and Aerospace Engineering

In various industries, the early detection of faults in rotating machinery is crucial to prevent system failures and ensure customer satisfaction. Typically, vibration measurement and diagnosis are employed for fault detection, but this process faces challenges in automation due to the complexity of installing and maintaining accelerometers, particularly in end-of-line quality control or pre-installed machinery health assessments. Acoustic signals, as a form of mechanical wave, offer an alternative for monitoring machinery while in operation. Unlike accelerometers, acoustic transducers are non-contact and easy to set up, enabling real-time data collection without interrupting equipment operation. However, utilizing acoustic signals in manufacturing poses …

Decompositions Of Nonlinear Input-Output Systems To Zero The Output, W. Steven Gray, Kurusch Ebrahimi-Fard, Alexander Schmeding

Electrical & Computer Engineering Faculty Publications

Consider an input–output system where the output is the tracking error given some desired reference signal. It is natural to consider under what conditions the problem has an exact solution, that is, the tracking error is exactly the zero function. If the system has a well defined relative degree and the zero function is in the range of the input–output map, then it is well known that the system is locally left invertible, and thus, the problem has a unique exact solution. A system will fail to have relative degree when more than one exact solution exists. The general goal …

Sparse Representation Learning For Temporal Networks, Maxwell Mcneil

Electronic Theses & Dissertations (2024 - present)

Temporal networks arise in many domains including activity of social network users, sensor network readings over time, and time course gene expression within the interaction network of a model organism. Data of this type contains a wealth of prior information such as the connectivity among nodes (e.g., a friendship graph), and prior knowledge of expected temporal patterns (e.g., periodicity). Modeling these temporal and network patterns jointly is essential for state-of-the-art performance in temporal network data analysis and mining. Sparse dictionary encoding is one modeling approach for such underlying patterns. However, most classical approaches consider only one dimension of the data …

An Analysis Of Precision: Occlusion And Perspective Geometry’S Role In 6d Pose Estimation, Jeffrey Choate, Derek Worth, Scott Nykl, Clark N. Taylor, Brett J. Borghetti, Christine M. Schubert Kabban

Faculty Publications

Achieving precise 6 degrees of freedom (6D) pose estimation of rigid objects from color images is a critical challenge with wide-ranging applications in robotics and close-contact aircraft operations. This study investigates key techniques in the application of YOLOv5 object detection convolutional neural network (CNN) for 6D pose localization of aircraft using only color imagery. Traditional object detection labeling methods suffer from inaccuracies due to perspective geometry and being limited to visible key points. This research demonstrates that with precise labeling, a CNN can predict object features with near-pixel accuracy, effectively learning the distinct appearance of the object due to perspective …

Resilient, Sustainable, And Secure Systems Support For Ultra-Low-Power Computational Things, Nicole Tobias

All Dissertations

Wireless battery-free and energy-harvesting devices are expanding the reach and vision of the Internet of Things, where trillions of embedded computational things interconnect ubiquitously around us and inform many different aspects of our everyday lives. Designing these systems without batteries and interconnecting wires lowers maintenance, environmental, and economic costs while also extending device lifetime and deployment opportunities. Over the last decade, research on these ultra-low-power embedded sensors and systems has dramatically increased — enabling new and exciting prospects in many different scientific fields, from smart building and health monitoring applications to animal and activity tracking.

These systems are not without …

Electronic Note-String Detector, Gavin Garcia-Rossi, Tommy Smail

Electrical Engineering

As the virtual space has become a dominant part of everyone’s day-to-day lives, many normal face-to-face interactions and services have not yet been facilitated by adapting technology. One of these prevailing areas is music lessons. Over Zoom meetings, or other virtual platforms, it is tremendously challenging to teach students. These challenges include recognizing student mistakes audibly and visually, and being able to give confident feedback on the incorrect notes played by learning musicians. Without having to delve into improving the complex systems that would be required to improve audio, video, and connection quality of these connections, we have another solution …

Accelerating Machine Learning Inference For Satellite Component Feature Extraction Using Fpgas., Andrew Ekblad

Theses and Dissertations

Running computer vision algorithms requires complex devices with lots of computing power, these types of devices are not well suited for space deployment. The harsh radiation environment and limited power budgets have hindered the ability of running advanced computer vision algorithms in space. This problem makes running an on-orbit servicing detection algorithm very difficult. This work proposes using a low powered FPGA to accelerate the computer vision algorithms that enable satellite component feature extraction. This work uses AMD/Xilinx’s Zynq SoC and DPU IP to run model inference. Experiments in this work centered around improving model post processing by creating implementations …

System-Level Noise Performance Of Coherent Imaging Systems, Derek J. Burrell, Joshua H. Follansbee, Mark F. Spencer, Ronald G. Driggers

Faculty Publications

We provide an in-depth analysis of noise considerations in coherent imaging, accounting for speckle and scintillation in addition to “conventional” image noise. Specifically, we formulate closed-form expressions for total effective noise in the presence of speckle only, scintillation only, and speckle combined with scintillation. We find analytically that photon shot noise is uncorrelated with both speckle and weak-to-moderate scintillation, despite their shared dependence on the mean signal. Furthermore, unmitigated speckle and scintillation noise tends to dominate coherent-imaging performance due to a squared mean-signal dependence. Strong coupling occurs between speckle and scintillation when both are present, and we characterize this behavior …

Spoken Language Processing And Modeling For Aviation Communications, Aaron Van De Brook

Doctoral Dissertations and Master's Theses

With recent advances in machine learning and deep learning technologies and the creation of larger aviation-specific corpora, applying natural language processing technologies, especially those based on transformer neural networks, to aviation communications is becoming increasingly feasible. Previous work has focused on machine learning applications to natural language processing, such as N-grams and word lattices. This thesis experiments with a process for pretraining transformer-based language models on aviation English corpora and compare the effectiveness and performance of language models transfer learned from pretrained checkpoints and those trained from their base weight initializations (trained from scratch). The results suggest that transformer language …

Trumpet Directivity From A Rotating Semicircular Array, Samuel D. Bellows, Joseph E. Avila, Timothy W. Leishman

Directivity

The directivity function of a played musical instrument describes the angular dependence of its acoustic radiation and diffraction about the instrument, musician, and musician’s chair. Directivity influences sound in rehearsal, performance, and recording environments and signals in audio systems. Because high-resolution, spherically comprehensive measurements of played musical instruments have been unavailable in the past, the authors have undertaken research to produce and share such data for studies of musical instruments, simulations of acoustical environments, optimizations of microphone placements, and other applications. The authors acquired the data from repeated chromatic scales produced by a trumpet played at mezzo-forte in an anechoic …

Comparison Of A Bottom-Up Gnss Radio Occultation Method To Measure D- And E-Region Electron Densities With Ionosondes And Firi, Dylan J. Shaver, Dong L. Wu, Nimalan Swarnalingam, Anthony L. Franz, Eugene V. Dao, Daniel J. Emmons

Faculty Publications

High-frequency skywave propagation can be heavily impacted by D- and E-region dynamics requiring accurate global measurements to optimize performance. A standard measurement technique is to use ionosondes, but they are unable to measure below 1 MHz and are only available at a limited number of land-locked sites around the globe. In contrast, the Global Navigation Satellite System radio occultation (GNSS-RO) bottom-up method is a new approach specifically designed to generate electron density profiles in the D- and E- region ionosphere. It takes advantage of satellite constellations that currently provide over 20,000 daily measurements and global coverage. In this paper, GNSS-RO …

Quantifying Atmospheric Turbulence Effects On Image Quality Using A Deconvolution Algorithm, Ahmad M. Almalki

Theses and Dissertations

Imaging through turbulence is affected by several factors including imaging system specifications, imaging system setup and more importantly the atmospheric turbulence as it is uncontrollable. One important parameter which is used to quantify the atmospheric turbulence severity is the atmospheric coherence diameter (𝑟₀ ), known as Fried's parameter. This thesis explores ways to characterize the atmospheric turbulence effects on image quality using simulated and laboratory generated turbulence where 𝑟₀ is estimated using a maximum a posteriori (MAP) estimator and frequency domain analysis algorithms. Furthermore, image quality metrics such as Peak Signal to Noise Ratio (PSNR), Structural Similarity (SSIM) …