Signal Processing Commons^™

Neural Net Estimation Of Discriminants Posterior Probability Vector, Harshvardhan Harshvardhan

Electrical Engineering Theses - Archive

Interpreting multi-layer perceptron (MLP) classifier outputs as posterior probabilities is a well-established practice in machine learning and is supported in the literature. However, several authors point out that MLP outputs are very poor estimates of the posterior probabilities. This is demonstrated for classifiers with and without nonlinear output activation. Achieving this reliability depends on key factors such as model complexity, sufficient training data availability, and optimization techniques' effectiveness. In practice, these requirements are not met, resulting in suboptimal probability estimates. Our approach introduces an innovative method based on the softmax output. The method aim to refine MLP discriminants into more …

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 …

Non-Invasive Monitoring Device For Early Detection Of Breast Cancer Related Lymphedema, Amy Prendergast

Honors Theses and Capstones

Breast Cancer Related Lymphedema (BCRL) is a common co-morbidity in cancer survivors following neoadjuvant therapies such as chemotherapy, radiation, and/or surgery. It is brought about by the disruption in the lymphatic system (think lymph node biopsy) that leads to a buildup of lymphatic fluid in the arm. Current diagnostic strategies for this condition are merely retroactive, and fairly limited in the parameters that are examined to ensure patient well-being long term. We hypothesize that with an approach that mimics bioimpedance spectroscopy analysis, we will be able to provide a clinical support tool that would better determine early stages of lymphedema …

Implementing Associative Learning Using Neuromorphic Robot, Vinay Kumar Pillalamarri

Dissertations, Master's Theses and Master's Reports

Associative learning, a key cognitive process seen across the animal kingdom, enables organisms to form connections between stimuli and adapt their behaviors based on past experiences. A particularly powerful example is fear conditioning, where animals learn to associate a neutral stimulus with an aversive one, allowing them to predict and avoid potential threats. Inspired by this mechanism, this project implements associative learning on an unmanned ground vehicle (UGV) to develop adaptive behavior through neuromorphic principles. Utilizing Nengo for neural modeling, the UGV learns to associate visual (red color) and tactile (vibration) stimuli through Hebbian learning, a biologically inspired synaptic adaptation …

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 …

Investigation Of Delta-Focused Ictal Electrical Source Imaging In Refractory Focal Epilepsy, Jared A. Rybarczyk

Theses and Dissertations--Electrical and Computer Engineering

Refractory focal epilepsy is characterized by the presence of seizures that cannot be controlled via anti-seizure medications. For patients suffering from this form of epilepsy, accurate identification of the seizure onset zone is a crucial step for many modalities of treatment. Electrical source imaging (ESI) allows for estimation of the seizure onset zone from electroencephalography. EEG feature extraction is an important step that can impact the final accuracy of source estimates. This work provides a review of 23 ictal ESI studies and proposes a delta-focused ictal ESI methodology. Our proposed delta-focused ictal ESI is implemented across 33 refractory focal epilepsy …

A Novel Processor Architecture Implementing The Stacked Error Diffusion Algorithm And Its Zynq-Based Realization, Qishi Hu

Theses and Dissertations--Electrical and Computer Engineering

Digital halftoning reproduces continuous-tone images using patterns of black and white dots, while multitoning extends this concept by incorporating inks with intermediate intensities. These techniques are extensively utilized in the printing industry to accommodate the limited range of inks available in printers. Stacked error diffusion is a high-quality multitoning algorithm that adheres to the blue-noise dithering standard. This thesis research studies the potential parallelism inherent in the algorithm and introduces the design of a novel processor architecture optimized for efficient execution. The architecture is realized on an FPGA development board featuring a Zynq SoC. Additionally, the hardware prototype can also …

Information-Theoretic Learning Framework Based On Covariance Operators On Reproducing Kernel Hilbert Spaces, Jhoan Keider Hoyos Osorio

Theses and Dissertations--Electrical and Computer Engineering

Information theory provides tools to quantify uncertainty, dependence, and similarity between probability distributions, which are crucial for addressing various machine-learning problems. However, estimating these quantities is challenging because data distributions are usually unknown, and only observations are available for analysis. In this dissertation, we advance the field of information-theoretic learning by developing a comprehensive framework using kernel methods for analyzing probability distributions using reproducing kernel Hilbert spaces (RKHS). By leveraging covariance operators in this representation space, we propose approaches to estimate a set of fundamental information-theoretic quantities, that, because of their resemblance with conventional quantities in information theory, we call …

Information Access For Infrastructurally-Challenged Environments And Beyond Through Mutually Aware Spectrum Sharing Technologies, Karyn Doke

Electronic Theses & Dissertations (2024 - present)

The Radio Frequency (RF) spectrum is scarce and to make it available for new mobile wireless services, regulators are forced to re-allocate spectrum from existing services or develop mechanisms to share spectrum with new entries. Television White Space (TVWS) and Citizen Broadband Radio Service (CBRS) are two examples of recently commercialized spectrum sharing technologies. TVWS enables sharing among fixed wireless broadband technologies (secondary users) and terrestrial TV broadcast services (primary users). CBRS enables spectrum sharing among 5G/LTE (secondary users) and naval radar (primary users). With both technologies, a central database determines when it is safe for secondary users to operate …

Detecting Bearing Race Defects With Inductive Magnetic Reluctance Sensors And Artificial Neural Networks, Collin Daly

College of Graduate Studies: Theses & Dissertations

This work proposes a method of detecting physical damage to bearing races in a rotational assembly by means of magnetic reluctance sensors generating a signal from a rotating gear-tooth wheel. A nominally sinusoidal signal is generated based on the rotation of a gearwheel with regularly spaced voids and lands. Detection is based on the time variance of the signal periodically in relation to the gearwheel and the bearing damage. The purpose of this work is to propose a process to detect and classify bearing race defects using existing sensors and neural networks for hazardous area equipment applications.

Passive Wireless Corrosion And Temperature Detection In High-Temperature Environments, Noah Lane Strader

Graduate Theses, Dissertations, and Problem Reports (ETD)

This work focuses on the theory and development of LC sensors for high temperature and corrosion measurement for stainless steel and copper surfaces with power industry and general corrosion detection applications. The LC resonators were fabricated via screen printing an Ag inductor on an alumina substrate. The LC design was modeled using the ANSYS HFSS modeling package. The LC passive wireless sensors operate with resonant frequencies centered at 85-110 MHz. The wireless response of the LC sensor was interrogated and received by a radio frequency signal generator and spectrum analyzer at temperatures from 50-800 °C for copper ground planes and …

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 …

Estimating And Detecting Slow-Wave Events In Eeg Signals, Zhenghao Xiong

McKelvey School of Engineering Graduate Student Theses & Dissertations

Slow wave activity (SWA) is an electroencephalogram (EEG) pattern commonly occurring during anesthesia and deep sleep, and is hence a candidate biomarker to quantify such states and understand their connection to various phenotypes. SWA consists of individual slow waves (ISW), high-amplitude deflections lasting for approximately 0.5 to 1 second, and occurring quasi-periodically. This latter fact poses a challenge for conventional power spectral density EEG analysis methods that perform best when there is persistency of oscillatory activity. In this work, we pursue a time-domain detection framework for identifying and quantifying ISWs as a metric for SWA. Our method works, in essence, …

Energy Efficiency And Fault Tolerance In Open Ran And Future Internet, Saish Urumkar, Byrav Ramamurthy, Sachin Sharma

Conference papers

Open Radio Access Networks (Open RAN) repre- sent a promising technological advancement within the realm of the future internet. Research efforts are currently directed towards enhancing energy efficiency and fault tolerance, which are critical aspects for both Open RAN and the future internet landscape. In the context of energy saving in Open RAN, there exists a spectrum of methods for achieving energy efficiency. These methods include the toggling of on/off states for different hardware resources such as base station units, distributed units, and radio units. Conversely, for enhancing fault tolerance in Open RAN, Software-Defined Networking (SDN) and OpenFlow based techniques …

Improving Energy Efficiency In Open Ran Through Dynamic Cpu Scheduling, Saish Urumkar, Byrav Ramamurthy, Sachin Sharma

Conference papers

Open RAN is a promising cellular technology that is currently undergoing extensive research for future wireless radio access networks. Achieving optimal energy efficiency in Open RAN poses a significant challenge. This paper introduces a CPU scheduling algorithm that specifically targets this chal- lenge by optimizing energy consumption at the base station while maintaining optimal performance levels. With the goal of minimizing energy consumption, the proposed algorithm dynamically adjusts the CPU core states, seamlessly switching between active and sleep modes based on the load conditions. To evaluate the algorithm’s effectiveness in terms of energy saving and performance, experimental testing is conducted …

Design And Fabrication Of A Low Power 7.2 Terabit Transmitter For Exascale Computing, Scott Mcwilliams

Electrical Engineering Theses and Dissertations

Enhanced Coupled Strength (ECS) gratings fabricated into III-V based devices offer high reflected power per unit length and broad band reflectivity as compared to conventional 1st order gratings, desired qualities for short-haul high speed transmitters that can be implemented without the need for chip-level temperature control, contributing to the low power per transmitted bit. For commercial DBR lasers, the grating reflectivity results in an extremely narrow reflectivity spectrum, which is highly desired for most/many applications, but requires a power hungry thermo-electric cooler to maintain a fixed frequency. The proposed LEAM (laser electro-absorption modulator) requires a broad reflectivity spectrum, which, by …

Route Condition Estimation By Video Data Analysis, Sharafat Hossain

Theses and Dissertations

Catastrophic natural disasters have an impact on millions of individuals each year, whether directly or indirectly. A successful rescue operation can save a great deal of lives in the post-disaster phase, but researchers are still facing difficulties in carrying this out. Even while they are in peril, today's people frequently post updates about their whereabouts on well-known social media platforms, sometimes even asking for help. A prompt and appropriate response to these catastrophic events depends on developing an efficient and automated approach capable of retrieving real-time data from impacted locations and extracting essential elements. The research focuses on predicting flood …

Neural Networks For Improved Signal Source Enumeration And Localization With Unsteered Antenna Arrays, John T. Rogers Ii

Theses and Dissertations

Direction of Arrival estimation using unsteered antenna arrays, unlike mechanically scanned or phased arrays, requires complex algorithms which perform poorly with small aperture arrays or without a large number of observations, or snapshots. In general, these algorithms compute a sample covriance matrix to obtain the direction of arrival and some require a prior estimate of the number of signal sources. Herein, artificial neural network architectures are proposed which demonstrate improved estimation of the number of signal sources, the true signal covariance matrix, and the direction of arrival. The proposed number of source estimation network demonstrates robust performance in the case …

Traffic Light Detection And V2i Communications Of An Autonomous Vehicle With The Traffic Light For An Effective Intersection Navigation Using Mavs Simulation, Mahfuzur Rahman

Theses and Dissertations

Intersection Navigation plays a significant role in autonomous vehicle operation. This paper focuses on enhancing autonomous vehicle intersection navigation through advanced computer vision and Vehicle-to-Infrastructure (V2I) communication systems. The research unfolds in two phases. In the first phase, an approach utilizing YOLOv8s is proposed for precise traffic light detection and recognition, trained on the Small-Scale Traffic Light Dataset (S2TLD). The second phase establishes seamless connectivity between autonomous vehicles and traffic lights in a simulated Mississippi State University Autonomous Vehicle Simulation (MAVS) environment resembling a small city with multiple intersections. This V2I system enables the transmission of Signal Phase and Timing …

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 …

Ism-Band Energy Harvesting Wireless Sensor Node, Fnu Naveed

Graduate Theses and Dissertations

In recent years, the interest in remote wireless sensor networks has grown significantly, particularly with the rapid advancements in Internet of Things (IoT) technology. These networks find diverse applications, from inventory tracking to environmental monitoring. In remote areas where grid access is unavailable, wireless sensors are commonly powered by batteries, which imposes a constraint on their lifespan. However, with the emergence of wireless energy harvesting technologies, there is a transformative potential in addressing the power challenges faced by these sensors. By harnessing energy from the surrounding environment, such as solar, thermal, vibrational, or RF sources, these sensors can potentially operate …

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 …

Low-Power, Event-Driven System On A Chip For Charge Pulse Processing Applications, Joseph A. Schmitz

Department of Electrical and Computer Engineering: Dissertations, Theses, and Student Research

This dissertation presents an electronic architecture and methodology capable of processing charge pulses generated by a range of sensors, including radiation detectors and tactile synthetic skin. These sensors output a charge signal proportional to the input stimulus, which is processed electronically in both the analog and digital domains. The presented work implements this functionality using an event-driven methodology, which greatly reduces power consumption compared to standard implementations. This enables new application areas that require a long operating time or compact physical dimensions, which would not otherwise be possible. The architecture is designed, fabricated, and tested in the aforementioned applications to …

4-Band Personal Eq Device, Carson Kellerman

Electrical Engineering

The device is a 4-band EQ with 3.5mm audio input and output jacks. The device has 4 adjustable EQ bands. Each of the 4 bands are adjustable via knob potentiometers, and are able to boost or cut their respective center frequencies of 150Hz, 400Hz, 2500Hz, and 10kHz from -15dB to +15dB. The device is battery powered off of 1 9V battery and is able to function for 10 hours before needing to replace the batteries. The device has a Total Harmonic Distortion of less than 1% and a Signal to Noise Ratio greater than 60dB. Overall, this device allows music …

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 …

Improving Cellphone-Based Bio-Imaging Technique For Fluorescence Detection, Erteza T. Efaz

LSU Master's Theses

The research presented in this thesis focuses on the design, development, and evaluation of a fluorescence detection system. The system is implemented primarily as an Android application, Auto Camera, which leverages smartphone cameras to capture and analyze fluorescent images. The application provides a user-friendly interface with some configurable features like exposure time, ISO speed, and storage limit; as well as defining detection thresholds and setting acquisition intervals. This study begins with the architectural framework of the Android application, which is written in Java using Android Studio. The API compatibility is set to version 33, and users are prompted to grant …

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 …

Study Of Improved Sorting Weighting Cfar Detectors For Gaussian Environment, Souad Chabbi, Khadidja Belhi, M'Hamed Hamadouche

Emirates Journal for Engineering Research

The goal of this paper is to improve the detection performance and the false alarm regulation of the conventional order statistics Constant False Alarm Rate (OS-CFAR) detectors in a non-homogeneous Gaussian environment. To this end, we design and study the New Sorting Weighting (NSW-) and the Modified Sorting Weighting (MSW-) CFAR detectors. We find closed forms of the detection ( ) and the false alarm ( ) probabilities for both detectors. Moreover, we identify the optimum pairs of weights that maximize the and ensure a constant . Finally, we prove through Monte Carlo simulations that these detectors provide better detection …