Signal Processing Commons^™

On Explainability Of Neural Networks, Cem Benar

Dissertations

It is widely reported that deep neural networks outperform most competitors for a range of applications. The state-of-the-art neural networks have built-in inductive bias of architectural choices, regularizations, optimizer types, and initialization methods. Using inductive bias is intuitive to enhance the model approximation. Deep neural networks are mostly dense and heavily overparameterized. They tend to be biased towards low-rank solutions to reduce complexity and improve generalization performance, known as implicit regularization. The implicit regularization as observed in specific architectures and various real-world data sets suggests to overparameterize neural networks judiciously and learn compressed representations (lower rank approximation) with improved performance. …

Characterization And Estimation Of Musculoskeletal Pain Using Machine Learning, Boluwatife Faremi

Master's Theses

Traditional scales utilized for recording pain are known to be highly subjective and biased due to inaccuracies in recollecting actual pain intensities. As a result, machine learning (ML) models that are trained using these scores as ground truth are reported to have low performance for objective pain classification because of the huge disparity between what was felt in moments of pain and the scores recorded afterward.

In the present study, two devices were designed for gathering real-time, continuous in-session subjective pain scores and the recording of the autonomic nervous system (ANS) altered endodermal (EDA) activity. 24 participants were recruited to …

Optimal Estimation Inversion Of Ionospheric Electron Density From Gnss-Pod Limb Measurements: Part I-Algorithm And Morphology, Dong L. Wu, Nimalan Swarnalingam, Cornelius C. J. H. Salinas, Daniel J. Emmons, Tyler C. Summers, Robert Gardiner-Garden

Faculty Publications

GNSS-LEO radio links from Precise Orbital Determination (POD) and Radio Occultation (RO) antennas have been used increasingly in characterizing the global 3D distribution and variability of ionospheric electron density (Ne). In this study, we developed an optimal estimation (OE) method to retrieve Ne profiles from the slant total electron content (hTEC) measurements acquired by the GNSS-POD links at negative elevation angles (ε < 0°). Although both OE and onion-peeling (OP) methods use the Abel weighting function in the Ne inversion, they are significantly different in terms of performance in the lower ionosphere. The new OE results can overcome the large Ne oscillations, sometimes negative values, seen in the OP retrievals in the E-region ionosphere. In the companion paper in this Special Issue, the HmF2 and NmF2 from the OE retrieval are validated against ground-based ionosondes and radar observations, showing generally good agreements in NmF2 from all sites. Nighttime hmF2 measurements tend to agree better than the daytime when the ionosonde heights tend to be slightly lower. The OE algorithm has been applied to all GNSS-POD data acquired from the COSMIC-1 (2006–2019), COSMIC-2 (2019–present), and Spire (2019–present) constellations, showing a consistent ionospheric Ne morphology. The unprecedented spatiotemporal sampling of the ionosphere from these constellations now allows a detailed analysis of the frequency–wavenumber spectra for the Ne variability at different heights. In the lower ionosphere (~150 km), we found significant spectral power in DE1, DW6, DW4, SW5, and SE4 wave components, in addition to well-known DW1, SW2, and DE3 waves. In the upper ionosphere (~450 km), additional wave components are still present, including DE4, DW4, DW6, SE4, and SW4. The co-existence of eastward- and westward-propagating wave4 components implies the presence of a stationary wave4 (SPW4), as suggested by other earlier studies. Further improvements to the OE method are proposed, including a tomographic inversion technique that leverages the asymmetric sampling about the tangent point associated with GNSS-LEO links.

Eddy Current Defect Response Analysis Using Sum Of Gaussian Methods, James William Earnest

Theses and Dissertations

This dissertation is a study of methods to automatedly detect and produce approximations of eddy current differential coil defect signatures in terms of a summed collection of Gaussian functions (SoG). Datasets consisting of varying material, defect size, inspection frequency, and coil diameter were investigated. Dimensionally reduced representations of the defect responses were obtained utilizing common existing reduction methods and novel enhancements to them utilizing SoG Representations. Efficacy of the SoG enhanced representations were studied utilizing common Machine Learning (ML) interpretable classifier designs with the SoG representations indicating significant improvement of common analysis metrics.

Investigating The Use Of Recurrent Neural Networks In Modeling Guitar Distortion Effects, Caleb Koch, Scott Hawley, Andrew Fyfe

[Archive] Belmont University Research Symposium (BURS)

Guitar players have been modifying their guitar tone with audio effects ever since the mid-20th century. Traditionally, these effects have been achieved by passing a guitar signal through a series of electronic circuits which modify the signal to produce the desired audio effect. With advances in computer technology, audio “plugins” have been created to produce audio effects digitally through programming algorithms. More recently, machine learning researchers have been exploring the use of neural networks to replicate and produce audio effects initially created by analog and digital effects units. Recurrent Neural Networks have proven to be exceptional at modeling audio effects …

Chatgpt As Metamorphosis Designer For The Future Of Artificial Intelligence (Ai): A Conceptual Investigation, Amarjit Kumar Singh (Library Assistant), Dr. Pankaj Mathur (Deputy Librarian)

Library Philosophy and Practice (e-journal)

Abstract

Purpose: The purpose of this research paper is to explore ChatGPT’s potential as an innovative designer tool for the future development of artificial intelligence. Specifically, this conceptual investigation aims to analyze ChatGPT’s capabilities as a tool for designing and developing near about human intelligent systems for futuristic used and developed in the field of Artificial Intelligence (AI). Also with the helps of this paper, researchers are analyzed the strengths and weaknesses of ChatGPT as a tool, and identify possible areas for improvement in its development and implementation. This investigation focused on the various features and functions of ChatGPT that …

Gamelan Gong Directivity Dataset, Samuel D. Bellows, Dallin T. Harwood, Kent L. Gee, Micah R. Shepherd

Directivity

No abstract provided.

Accelerating A Software Defined Satnav Receiver Using Multiple Parallel Processing Schemes, Logan Reich, Sanjeev Gunawardena, Michael Braasch

Faculty Publications

Excerpt: Satnav SDRs present many benefits in terms of flexibility and configurability. However, due to the high bandwidth signals involved in satnav SDR processing, the software must be highly optimized for the host platform in order to achieve acceptable runtimes. Modules such as sample decoding, carrier replica generation, carrier wipeoff, and correlation are computationally intensive components that benefit from accelerations.

Generalizable And Adaptable Data-Driven Methods For Overcoming Barriers To Practical Industrial Condition Monitoring, Matthew B. Russell

Theses and Dissertations--Electrical and Computer Engineering

The future of smart manufacturing relies on predictive maintenance systems that intelligently minimize expensive downtime through timely assessment of machine condition. Deep Learning (DL) has achieved excellent performance in industrial condition monitoring experiments, but the constraints of the manufacturing environment prevent many algorithms from being practically deployed on the factory floor. Ubiquitous sensing from online machines generates high velocity data streams that require new techniques for efficient transmission and storage. Despite these ever-increasing data lakes, many applications still lack the data needed for training DL fault diagnosis and wear tracking models since most data is unlabeled and only from nominal …

Defending Ai-Based Automatic Modulation Recognition Models Against Adversarial Attacks, Haolin Tang, Ferhat Ozgur Catak, Murat Kuzlu, Evren Catak, Yanxiao Zhao

Engineering Technology Faculty Publications

Automatic Modulation Recognition (AMR) is one of the critical steps in the signal processing chain of wireless networks, which can significantly improve communication performance. AMR detects the modulation scheme of the received signal without any prior information. Recently, many Artificial Intelligence (AI) based AMR methods have been proposed, inspired by the considerable progress of AI methods in various fields. On the one hand, AI-based AMR methods can outperform traditional methods in terms of accuracy and efficiency. On the other hand, they are susceptible to new types of cyberattacks, such as model poisoning or adversarial attacks. This paper explores the vulnerabilities …

Deep-Learning-Based Classification Of Digitally Modulated Signals Using Capsule Networks And Cyclic Cumulants, John A. Snoap, Dimitrie C. Popescu, James A. Latshaw, Chad M. Spooner

Electrical & Computer Engineering Faculty Publications

This paper presents a novel deep-learning (DL)-based approach for classifying digitally modulated signals, which involves the use of capsule networks (CAPs) together with the cyclic cumulant (CC) features of the signals. These were blindly estimated using cyclostationary signal processing (CSP) and were then input into the CAP for training and classification. The classification performance and the generalization abilities of the proposed approach were tested using two distinct datasets that contained the same types of digitally modulated signals, but had distinct generation parameters. The results showed that the classification of digitally modulated signals using CAPs and CCs proposed in the paper …

Eeg-Based Spanish Language Proficiency Classification: An Eeg Power Spectrum And Cross-Spectrum Analysis, Blaise Xavier O'Mara, Skyler Baumer

Honors Theses and Capstones

Second language proficiency may be predicted with electrophysiological techniques. In a machine learning application, this electrophysiological data may be used for language instructors and language students to assess their language learning. This study identifies how electroencephalogram (EEG) power spectrum and cross spectrum data of the brain cortex relates to Spanish second language (L2) proficiency of 20 Spanish language students of varying proficiency levels at the University of New Hampshire. The two metrics for assessing cortical power and processing were event-related desynchronization (ERD)—a measure of relative change in power—of the alpha (8-12 Hz) brain frequency band, and alpha and beta (13-30Hz) …

Perceptual Anthropomorphic Walking Robot Platform For Navigation In Unstructured And Undifferentiated Environments, Luige Vladareanu, Mihai Rădulescu, Marius Pandelea, Hongbo Wang, Florentin Smarandache, Yongfei Feng, Ionel-Alexandru Gal, Alexandra C. Ciocîrlan

Branch Mathematics and Statistics Faculty and Staff Publications

This scientific presentation studies the VIPRO Platform for control of Anthropomorphic Walking Robots (AWR), the architecture control system of the SiMeLA MP robot motion, and shows several experimental results.

Application Of Distributed Fiber-Optic Sensing For Pressure Predictions And Multiphase Flow Characterization, Gerald Kelechi Ekechukwu

LSU Doctoral Dissertations

In the oil and gas industry, distributed fiber optics sensing (DFOS) has the potential to revolutionize well and reservoir surveillance applications. Using fiber optic sensors is becoming increasingly common because of its chemically passive and non-magnetic interference properties, the possibility of flexible installations that could be behind the casing, on the tubing, or run on wireline, as well as the potential for densely distributed measurements along the entire length of the fiber. The main objectives of my research are to develop and demonstrate novel signal processing and machine learning computational techniques and workflows on DFOS data for a variety of …

A Statistical Analysis Of Sporadic-E Characteristics Associated With Gnss Radio Occultation Phase And Amplitude Scintillations, Daniel J. Emmons, Dong L. Wu, Nimalan Swarnalingam

Faculty Publications

Statistical GNSS-RO measurements of phase and amplitude scintillation are analyzed at the mid-latitudes in the local summer for a 100 km altitude. These conditions are known to contain frequent sporadic-E, and the S4-σ_ϕ trends provide insight into the statistical distributions of the sporadic-E parameters. Joint two-dimensional S4-σ_ϕ histograms are presented, showing roughly linear trends until the S4 saturates near 0.8. To interpret the measurements and understand the sporadic-E contributions, 10,000 simulations of RO signals perturbed by sporadic-E layers are performed using length, intensity, and vertical thickness distributions from previous studies, with the assumption that the sporadic-E layer acts …

Denoising And Deconvolving Sperm Whale Data In The Northern Gulf Of Mexico Using Fourier And Wavelet Techniques, Kendal Mccain Leftwich

LSU New Orleans Theses and Dissertations

The use of underwater acoustics can be an important component in obtaining information from the oceans of the world. It is desirable (but difficult) to compile an acoustic catalog of sounds emitted by various underwater objects to complement optical catalogs. For example, the current visual catalog for whale tail flukes of large marine mammals (whales) can identify even individual whales from their individual fluke characteristics. However, since sperm whales, Physeter microcephalus, do not fluke up when they dive, they cannot be identified in this manner. A corresponding acoustic catalog for sperm whale clicks could be compiled to identify individual …

Design And Comparison Of Asynchronous Fft Implementations, Julie Bigot

Graduate Theses and Dissertations

Fast Fourier Transform (FFT) is a widely used digital signal processing technology in a large variety of applications. For battery-powered embedded systems incorporating FFT, its physical implementation is constrained by strict power consumption, especially during idle periods. Compared to the prevailing clocked synchronous counterpart, quasi-delay insensitive asynchronous circuits offer a series of advantages including flexible timing requirement and lower leakage power, making them ideal choices for these systems. In this thesis work, various FFT configurations were implemented in the low-power Multi-Threshold NULL Convention Logic (MTNCL) paradigm. Analysis illustrates the area and power consumption trends along the changing of the number …

Oam-Based Wavelets In A High Speed Optical Probing System For Measuring The Angular Decomposition Of The Environment, Justin Free

All Theses

This thesis presents the theoretical development of orbital angular momentum (OAM) based wavelets for the analysis of localized OAM information in space. An optical probing system for generating and detecting these wavelets is demonstrated; individual wavelets can scan the environment in 10µs or less. The probing system was applied to a three-dimensional atmospheric turbulence distribution to obtain a continuous wavelet transform of the angular information of the turbulent propagation path about a fixed radius. An entire continuous wavelet transform was measured in 3.8ms; the measurements are much faster than the turbulence and give insight into the short time scale of …

Long-Distance Propagation Of 162 Mhz Shipping Information Links Associated With Sporadic E, Alex T. Chartier, Thomas R. Hanley, Daniel J. Emmons

Faculty Publications

This is a study of anomalous long-distance (>1000 km) radio propagation that was identified in United States Coast Guard monitors of automatic identification system (AIS) shipping transmissions at 162 MHz. Our results indicate this long-distance propagation is caused by dense sporadic E layers in the daytime ionosphere, which were observed by nearby ionosondes at the same time. This finding is surprising because it indicates these sporadic E layers may be far more dense than previously thought.

Development Of A Smartphone Application As An Asset To Pavement Management Engineers, Smartp3m, Damien Stephens

Electrical Engineering Theses

An application specific multi-platform smartphone application can utilize on-board accelerometer, gyroscope, and GPS sensors, along with software derived signals from the same sensors, to sample vibrational and geolocation datasets to capture pavement distresses such as potholes when mounted in a standardized configuration in a vehicle. Several observations were made with regard to the signals obtained from the accelerometer, gyroscope, and GPS sensors, and it was determined that the raw sensor outputs are capable of sampling statistically significant datasets which can be used to distinguish pavement distress from normal driving conditions. Furthermore, an approximate sensor noise margin is established, and a …

Predicting Insulin Pump Therapy Settings, Riccardo L. Ferraro, David Grijalva, Alex Trahan

SMU Data Science Review

Millions of people live with diabetes worldwide [7]. To mitigate some of the many symptoms associated with diabetes, an estimated 350,000 people in the United States rely on insulin pumps [17]. For many of these people, how effectively their insulin pump performs is the difference between sleeping through the night and a life threatening emergency treatment at a hospital. Three programmed insulin pump therapy settings governing effective insulin pump function are: Basal Rate (BR), Insulin Sensitivity Factor (ISF), and Carbohydrate Ratio (ICR). For many people using insulin pumps, these therapy settings are often not correct, given their physiological needs. While …

Distribution Of Dds-Cerberus Authenticated Facial Recognition Streams, Andrew T. Park, Nathaniel Peck, Richard Dill, Douglas D. Hodson, Michael R. Grimaila, Wayne C. Henry

Faculty Publications

Successful missions in the field often rely upon communication technologies for tactics and coordination. One middleware used in securing these communication channels is Data Distribution Service (DDS) which employs a publish-subscribe model. However, researchers have found several security vulnerabilities in DDS implementations. DDS-Cerberus (DDS-C) is a security layer implemented into DDS to mitigate impersonation attacks using Kerberos authentication and ticketing. Even with the addition of DDS-C, the real-time message sending of DDS also needs to be upheld. This paper extends our previous work to analyze DDS-C’s impact on performance in a use case implementation. The use case covers an artificial …

Emotion Detection Using An Ensemble Model Trained With Physiological Signals And Inferred Arousal-Valence States, Matthew Nathanael Gray

Electrical & Computer Engineering Theses & Dissertations

Affective computing is an exciting and transformative field that is gaining in popularity among psychologists, statisticians, and computer scientists. The ability of a machine to infer human emotion and mood, i.e. affective states, has the potential to greatly improve human-machine interaction in our increasingly digital world. In this work, an ensemble model methodology for detecting human emotions across multiple subjects is outlined. The Continuously Annotated Signals of Emotion (CASE) dataset, which is a dataset of physiological signals labeled with discrete emotions from video stimuli as well as subject-reported continuous emotions, arousal and valence, from the circumplex model, is used for …

Computational Models To Detect Radiation In Urban Environments: An Application Of Signal Processing Techniques And Neural Networks To Radiation Data Analysis, Jose Nicolas Gachancipa

Beyond: Undergraduate Research Journal

Radioactive sources, such as uranium-235, are nuclides that emit ionizing radiation, and which can be used to build nuclear weapons. In public areas, the presence of a radioactive nuclide can present a risk to the population, and therefore, it is imperative that threats are identified by radiological search and response teams in a timely and effective manner. In urban environments, such as densely populated cities, radioactive sources may be more difficult to detect, since background radiation produced by surrounding objects and structures (e.g., buildings, cars) can hinder the effective detection of unnatural radioactive material. This article presents a computational model …

Automatic Contact Tracing Using Bluetooth Low Energy Signals And Imu Sensor Readings, Suriyadeepan Ramamoorthy, Joyce Mahon, Michael O'Mahony, Jean Francois Itangayenda, Tendai Mukande, Tlamelo Makati

Other resources

In this report, we present our solution to the challenge provided by the SFI Centre for Machine Learning (ML-Labs) in which the distance between two phones needs to be estimated. It is a modified version of the NIST Too Close For Too Long (TC4TL) Challenge, as the time aspect is excluded. We propose a feature-based approach based on Bluetooth RSSI and IMU sensory data, that outperforms the previous state of the art by a significant margin, reducing the error down to 0.071. We perform an ablation study of our model that reveals interesting insights about the relationship between the distance …

Full Pattern Analysis And Comparison Of The Center Fed And Offset Fed Cassegrain Antennas With Large Focal Length To Diameter Ratios For High Power Microwave Transmission, Derek W. Mantzke

Theses and Dissertations

High power microwaves (HPM) have been a topic of research since the Cold War era. This paper will present a comparison between two Cassegrain-type antennas: the axially, or center fed, and the offset fed. Specifically, the 10 GHz operating frequency will be investigated with large focal length to diameter () ratios. Beam patterns which encompass the entire radiation pattern will be included for data validation and optimization. The simulations will follow a design of experiments factorial model to ensure all possible combinations of prescribed parameters are included, including an analysis of variance (ANOVA) study to find parameter influence on the …

Methods For Focal Plane Array Resolution Estimation Using Random Laser Speckle In Non-Paraxial Geometries, Phillip J. Plummer

Theses and Dissertations

The infrared (IR) imaging community has a need for direct IR detector evaluation due to the continued demand for small pixel pitch detectors, the emergence of strained-layer-super-lattice devices, and the associated lateral carrier diffusion issues. Conventional laser speckle-based modulation transfer function (MTF) estimation is dependent on Fresnel propagation and a wide-sense-stationary input random process, limiting the use of this approach for lambda (wavelength)-scale IR devices. This dissertation develops two alternative methodologies for speckle-based resolution evaluation of IR focal plane arrays (FPAs). Both techniques are formulated using Rayleigh-Sommerfield electric field propagation, making them valid in the non-paraxial geometries dictated for resolution …

Design & Analysis Of Mixed-Mode Integrated Circuit For Pulse-Shape Discrimination, Bryan Orabutt

McKelvey School of Engineering Graduate Student Theses & Dissertations

In nuclear science experiments it is usually necessary to determine the type of radiation, its energy and direction with considerable accuracy. The detection of neutrons and discriminating them from gamma rays is particularly difficult. A popular method of doing so is to measure characteristics intrinsic to the pulse shape of each radiation type in order to perform pulse-shape discrimination (PSD).

Historically, PSD capable systems have been designed with two approaches in mind: specialized analog circuitry, or digital signal processing (DSP). In this work we propose a PSD capable circuit topology using techniques from both the analog and DSP domains. We …

State Estimation—Beyond Gaussian Filtering, Haozhan Meng

LSU New Orleans Theses and Dissertations

This dissertation considers the state estimation problems with symmetric Gaussian/asymmetric skew-Gaussian assumption under linear/nonlinear systems. It consists of three parts. The first part proposes a new recursive finite-dimensional exact density filter based on the linear skew-Gaussian system. The second part adopts a skew-symmetric representation (SSR) of distribution for nonlinear skew-Gaussian estimation. The third part gives an optimized Gauss-Hermite quadrature (GHQ) rule for numerical integration with respect to Gaussian integrals and applies it to nonlinear Gaussian filters.

We first develop a linear system model driven by skew-Gaussian processes and present the exact filter for the posterior density with fixed dimensional recursive …

Machine Learning Classification Of Digitally Modulated Signals, James A. Latshaw

Electrical & Computer Engineering Theses & Dissertations

Automatic classification of digitally modulated signals is a challenging problem that has traditionally been approached using signal processing tools such as log-likelihood algorithms for signal classification or cyclostationary signal analysis. These approaches are computationally intensive and cumbersome in general, and in recent years alternative approaches that use machine learning have been presented in the literature for automatic classification of digitally modulated signals. This thesis studies deep learning approaches for classifying digitally modulated signals that use deep artificial neural networks in conjunction with the canonical representation of digitally modulated signals in terms of in-phase and quadrature components. Specifically, capsule networks are …