Electrical and Computer Engineering Commons^™

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; …

Implantable, Sensor-Embedded Vascular Graft Towards Wireless Monitoring Of Stenosis, Nnamdi Dike

LSU Master's Theses

Arteriovenous (AV) grafts are commonly used to provide vascular access for hemodialysis in patients with end-stage renal disease. Despite their widespread use, AV grafts are prone to complications such as stenosis and thrombosis. Early detection of these conditions remains challenging with current monitoring methods too costly or insufficient. This work presents the design, fabrication, and validation of an LC pressure sensor embedded within a model AV graft to enable real-time monitoring. The proposed system integrates a parallel-plate capacitive pressure sensor with a spiral inductor to form an LC circuit embedded within an elastomeric graft wall. The Ecoflex 00-30 dielectric layer …

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 …

Polymer Microstructures For Advanced Biomanufacturing, Tongyao Wu

LSU Doctoral Dissertations

With the continued growth of the biopharmaceutical industry, the demand for scalable, robust, and resource-efficient platforms for large-scale mammalian cell culture is amplified. Recent developments in microfluidic technology, such as precise control of the microenvironment, showed the potential to improve the performance of cell culture systems. However, constrained by scalability and operational efficiency, applying such approaches to large-scale cell culture and biopharmaceutical production presents challenges. This dissertation addresses these challenges through three independent but conceptually related technological developments. First, a roll-to-roll (R2R) fabrication process was developed for the scalable production of hollow microcarriers (HMCs). HMCs provide three-dimensional microenvironments suitable for …

Identification Of Thruster Faults In Underwater Vehicles By Using Custom Encodings In Spiking Neural Networks, Donovan Gegg

LSU Master's Theses

Autonomous Underwater Vehicles (AUVs) are untethered robotic platforms used for tasks such as seafloor mapping, infrastructure inspection, and environmental monitoring. Recent technological advances have produced smaller, more affordable platforms, broadening access to research teams and small companies alike. This miniaturization comes at the cost of them handling drawbacks associated with a more compact machine such as reduced battery capacity as well as limited processing and sensing capabilities. These constraints make small-sized marine vehicle’s reliability critical as they can cause malfunctions, making the loss of a vehicle more likely. Actuator faults are particularly consequential as unintended and unstable control in an …

Quantifying And Integrating Community Hardship Into Two-Stage Stochastic Grid Reliability Optimization With Battery Storage, Fredrica Arthur

LSU Master's Theses

Traditional reliability planning for conventional distribution systems is largely utility-oriented, with a focus on collective system performance metrics like Expected Energy Not Supplied (EENS), where implicitly all unserved energy is considered of equal weight in terms of post-outage economic hardship. Yet, it is well understood that extended outage durations cause an uneven level of hardship to socioeconomically disadvantaged communities. This thesis proposes a community-informed reliability planning framework where the hardship caused by outages is explicitly considered in the battery energy storage system (BESS) location and sizing problem. First, a hardship-weighted Energy Not Supplied (WENS) measure is proposed, where income, education, …

Cache-Conscious Sparse Matrix Dense Matrix Multiplication On Gpus, Haoqiang Guo

LSU Doctoral Dissertations

Over the past decade, high-performance deep learning has evolved into a critical research domain, driven by the demand for efficient models and high inference throughput. Deep learning architectures have shifted from stacked convolutional layers to transformer-based models, while pruning techniques and graph-structured data have established sparse matrix–dense matrix multiplication (SpMM) as a fundamental kernel—particularly in graph neural networks (GNNs). Modern GPUs, with their massive parallelism and high-bandwidth memory, offer immense potential for accelerating these workloads. While SpMM implementations using the compressed sparse row (CSR) format remain common to avoid conversion overhead, preprocessing-based methods have recently demonstrated superior potential. In GNN …

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 …

Participation Of Battery Energy Storage Systems In Load Frequency Control Of Power Systems, Zakaria Afsharbakeshloo

LSU Doctoral Dissertations

In this research, functionalities and roles of Battery Energy Storage Systems (BESSs) in power systems are extended beyond primary frequency control (PFC). The BESSs, while participating in PFC, are controlled through charge controllers to first maintain their state-of-charge (SOC) within an acceptable range through a primary charge controller, and to recharge the BESS to its maximum SOC through a secondary charge controller. This forms a hierarchical frequency and SOC control of power grids with BESSs. In this regard, multiple BESS case is considered as well, and by employing the SOC balancing principle, it is shown that desired power sharing among …

Deep Learning Applications For Predictive Modeling In Cancer Therapy And Enzyme Encoding, Mengmeng Liu

LSU Doctoral Dissertations

Predictive modeling has revolutionized computational biology and molecular bioinformatics, enabling significant advancements in cancer therapy and functional enzyme characterization. Despite considerable progress, significant challenges remain in accurately predicting combinational cancer therapies and systematically representing enzyme functions for computational applications. Traditional methods struggle with capturing the complex interactions between drugs and biological networks, as well as representing hierarchical relationships within enzyme classifications. This dissertation addresses these limitations by developing advanced deep learning models tailored to enhance predictive performance in both domains.

First, a data augmentation strategy is introduced to improve anticancer drug synergy prediction by generating pharmacologically relevant drug pairs based …

State-Of-Charge Estimation Using Deep Learning For Electric Vehicles, Samer Yahya Ribhe Tahboub

LSU Master's Theses

This thesis investigates the application of deep learning models for State of Charge (SOC) estimation in Battery Management Systems (BMS) for electric vehicles (EVs), focusing on optimizing EV range, lifespan, and performance while addressing challenges like range anxiety. The study explores three deep learning architectures—Long Short-Term Memory (LSTM), Bidirectional LSTM (BiLSTM), and Gated Recurrent Unit (GRU)—each designed to capture complex temporal dependencies in battery data. The LSTM model is trained on EV battery data, including voltage, current, temperature, and SOC, providing a strong baseline for SOC estimation. The BiLSTM model enhances accuracy by processing data in both forward and backward …

Learning Proximal Operators With Gaussian Process And Adaptive Quantization In Distributed Optimization, Aldo Duarte Vera Tudela

LSU Doctoral Dissertations

In networks consisting of agents communicating with a central coordinator and working together to solve a global optimization problem in a distributed manner, the agents are often required to solve private proximal minimization subproblems. Such a setting often requires a further decomposition method to solve the global distributed problem, resulting in extensive communication overhead. In networks where communication is expensive, it is crucial to reduce the communication overhead of the distributed optimization scheme. Integrating Gaussian processes (GP) as a learning component to the Alternating Direction Method of Multipliers (ADMM) has proven effective in learning each agent's local proximal operator to …

Analysis And Improvement Of Efficient Charge Recovery Logic Adiabatic Circuits, William Morell

LSU Doctoral Dissertations

Power consumption has been an ever-present concern since the dawn of electronic computing. Every operation that a device performs consumes some amount of energy and as the demand for computation increases, both in scale and ubiquity, reducing this energy loss becomes more important. While modern devices are orders of magnitude more efficient than their ancestors on a per-operation basis, they are increasingly used in more resource constrained applications. Tiny, Internet of Things (IoT) machines are prevalent these days and demanded to perform data collection and analysis at all hours of the day for days at a time on small battery. …

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 …

Power Grid Resiliency Enhancement Against Flood-Induced Hazards, Mohadese Movahednia

LSU Doctoral Dissertations

Natural disasters, such as floods, may damage power system assets and lead to widespread and long outages. The impact of flood can be alleviated by preventive actions such as installing tiger dams around power substations before the flood. In this regard, it is imperative that critical substations are identified in terms of the connected load and imposed costs to the system. This study presents a resource allocation approach for protecting power substations against flood events a day ahead of the event. First, the required information for the model is extracted. Flood probability distribution functions are used to generate several flood …

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 …

Electrophertic Deposition And Characterization Of Molybdenum Disulfide On Silicon Substrates, Alex J. Young

LSU Doctoral Dissertations

The electrical characteristics of 2D materials such as high electron mobility and current density are of great interest to various fields from optoelectronics to renewable energy. Researchers have focused their efforts on transition metal dichalcogenides (TMDCs) due to their direct energy band gap. One such TMDC that has garnered much attention is molybdenum disulfide (MoS2). MoS2 has electrical properties comparable to graphene and is a TMDC with characteristics amenable to applications such as solar cells and sensors. Commonly deposited through time-consuming and complex deposition methods such as chemical vapor deposition (CVD), the viability of MoS2 as an electronic material will …

Cyberinet: Integrated Semi-Modular Sensors For The Computer-Augmented Clarinet, Matthew Bardin

LSU Doctoral Dissertations

The Cyberinet is a new Augmented instrument designed to easily and intuitively provide a method of computer-enhanced performance to the Clarinetist to allow for greater control and expressiveness in a performance. A performer utilizing the Cyberinet is able to seamlessly switch between a traditional performance setting and an augmented one. Towards this, the Cyberinet is a hardware replacement for a portion of a Clarinet containing a variety of sensors embedded within the unit. These sensors collect various real time data motion data of the performer and air fow within the instrument. Additional sensors can be connected to the Cyberinet to …

Learning Dynamic Information Of High-Dimensional Signal Time-Series Using Advanced Machine Learning/Artificial Intelligence, Guannan Liu

LSU Doctoral Dissertations

In this dissertation, we propose a novel simulation-based device-free indoor localization and tracking system using the received signal strength indicators (RSSIs) of WiFi signals as the input features. The Feko channel-propagation simulation software is used to process the RSSI maps of the given arbitrary indoor geometry. In order to learn the dynamic information of high-dimensional RSSI time-series, we propose three procedures for the localization and dynamic tracking system.

First, The indoor geometry is partitioned into several equi-size zones and the localization problem is treated as the typical \multi-classification" problem. The advanced machine-learning techniques such as decision tree (DT) classifier, random …

Learning–Assisted Constraint Filtering To Enhance Power System Optimization Performance, Fouad Hasan

LSU Doctoral Dissertations

Machine learning (ML) is a powerful tool that provides meaningful insights for operators to make fast and efficient decisions by analyzing data from power systems. ML techniques have great potential to assist in solving optimization problems within a shorter time frame and with less computational burden. AC optimal power flow (ACOPF), dynamic economic dispatch (D-ED), and security-constrained unit commitment (SCUC) are the three energy management optimization functions studied in this dissertation. ACOPF is solved every 5~15 minutes. Because of the nonconvex and complex nature of ACOPF, solving this problem for large systems is computationally expensive and time-consuming. Classification and regression …

Stabilizing Control Schemes For Grid-Connected Hybrid Pv-Energy Storage Systems, Indra Narayana Bhogaraju

LSU Doctoral Dissertations

A nonlinear stabilizing control scheme based on Lyapunov theory is proposed for a grid- connected hybrid photovoltaic (PV)/ battery/supercapacitor (SC) system. The system dynamics is developed in the stationary reference frame, and the state-space model of the system is derived and used to formulate the Lyapunov function (LF) candidate. The global asymptotic stability of the LF-based controller is discussed in detail. The real-time implementation feasibility of the proposed control scheme is validated through hardware-in-the-loop (HIL) studies of a grid- connected hybrid system under solar energy generation and grid load variations. To address the issue of digital computational time that leads …

Control And Optimization Of Multi-Agent Systems With Applications In Connected And Autonomous Electric Vehicles, Shaopan Guo

LSU Doctoral Dissertations

A multi-agent system (MAS) is a system in which multiple autonomous agents interact with each other to achieve a common goal. Nevertheless, current designs of MAS controllers typically rely on particular requirements, such as time-triggered communication, linear dynamics, and access to global information. These limitations restrict the applicability of MASs. This thesis aims to eliminate these constraints and optimize the energy consumption of a specific MAS, namely connected autonomous electric vehicles (CAEVs).

This thesis first addresses the consensus problem of linear MASs with intermittent communication. An adaptive distributed control algorithm that integrates edge-based event-triggered (ET) communication mechanisms is presented in …

Data-Driven Nonparametric Joint Chance-Constrained Programming For Power Systems Scheduling, Chutian Wu

LSU Doctoral Dissertations

This dissertation is dedicated to implementing data-driven nonparametric joint chance constraints (JCC) to power system optimization problems. Power generated by renewable sources, such as solar farms, is an uncertain parameter. Several approaches solve optimization under uncertainty, including stochastic programming, robust programming, and chance-constrained programming. Uncertain parameters may not belong to any parametric class of probability functions. Thus, methods that consider such uncertainty as a random variable that fits in a known probability density function (PDF) have limitations. This study focuses on chance-constrained programming under nonparametric or data-driven distributionally robust uncertainty settings.

Studies based on chance-constrained programming usually focus on individual …

Introduction To Control Engineering, Xiangyu Meng

E-Textbooks

This is an introductory level textbook for control engineering.

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 …

Compilation Optimizations To Enhance Resilience Of Big Data Programs And Quantum Processors, Travis D. Lecompte

LSU Doctoral Dissertations

Modern computers can experience a variety of transient errors due to the surrounding environment, known as soft faults. Although the frequency of these faults is low enough to not be noticeable on personal computers, they become a considerable concern during large-scale distributed computations or systems in more vulnerable environments like satellites. These faults occur as a bit flip of some value in a register, operation, or memory during execution. They surface as either program crashes, hangs, or silent data corruption (SDC), each of which can waste time, money, and resources. Hardware methods, such as shielding or error correcting memory (ECM), …

Spam Detection Using Machine Learning And Deep Learning, Olubodunde Agboola

LSU Doctoral Dissertations

Text messages are essential these days; however, spam texts have contributed negatively to the success of this communication mode. The compromised authenticity of such messages has given rise to several security breaches. Using spam messages, malicious links have been sent to either harm the system or obtain information detrimental to the user. Spam SMS messages as well as emails have been used as media for attacks such as masquerading and smishing ( a phishing attack through text messaging), and this has threatened both the user and service providers. Therefore, given the waves of attacks, the need to identify and remove …

Sers Platform For Single Fiber Endoscopic Probes, Debsmita Biswas

LSU Doctoral Dissertations

Molecular detection techniques have huge potential in clinical environments. In addition to many other molecular detection techniques, endoscopic Raman spectroscopy has great ability in terms of minimal invasiveness and real-time spectra acquisition. However, Raman Effect is low in sensitivity, limiting the application. Surface-Enhanced Raman Scattering (SERS), addresses this limitation. SERS brings rough nano-metallic surfaces in contact with specimen molecules which enormously enhances Raman signals. This provides Raman spectroscopy with immense capabilities for diverse fields of applications.

Generally, in clinical probe applications, the spectrometer is brought near the target molecules for detection. Typically, optical fibers are used to couple spectrometers to …

A Field-Deployable Quartz Crystal Microbalance System For Gas Detection, Jongyoon Park

LSU Doctoral Dissertations

Quartz crystal microbalance (QCM) has been widely studied as a mass sensing technique in laboratory environments and has shown a wide range of industrial applications such as food quality control, various forms of chemical detection, and biomolecular recognition under gas phase as well as liquid phase media. The construction of multi-sensor arrays combined with special sensor coatings enables multiple analyte detections and discrimination of multi-analyte along with statistical analysis. Despite the great sensing capabilities of QCM and growing interest in practical applications beyond the laboratory setup, most QCM studies are still performed in laboratory settings with benchtop QCM instruments. Therefore, …

Device Free Indoor Localization Of Human Target Using Wifi Fingerprinting, Prasanga Neupane

LSU Master's Theses

Indoor localization of human objects has many important applications nowadays. Proposed here is a new device free approach where all the transceiver devices are fixed in an indoor environment so that the human target doesn't need to carry any transceiver device with them. This work proposes radio-frequency fingerprinting for the localization of human targets which makes this even more convenient as radio-frequency wireless signals can be easily acquired using an existing wireless network in an indoor environment. This work explores different avenues for optimal and effective placement of transmitter devices for better localization. In this work, an experimental environment is …