Electrical and Computer Engineering Commons^™

Multimodal Deep Learning Architecture For Biomass Prediction Using Aerial Imagery, Sadikul Alim Toki

All Graduate Theses and Dissertations, Fall 2023 to Present

Grape growers rely on knowing how much leaf area their vines have, since canopy size affects how much water a vine needs, how healthy it is, and how much fruit it will produce. Measuring this by hand, plant by plant, across an entire vineyard takes enormous time and labor, so researchers have turned to cameras mounted on drones and satellites as a faster alternative. Drones capture very detailed images but only over small areas per flight, while satellites can photograph an entire farming region at once but cannot make out individual plants. 

This thesis builds a computer vision model, a …

Visual Interpretability Of Multimodal Tissue Perfusion Classification Using Grad-Cam And Saliency Maps, Metehan Zorluoglu

UNLV Theses, Dissertations, Professional Papers, and Capstones

Accurate identification of the tissue perfusion phase from hand images can aid doctors in decision-making with non-invasive techniques. The present study proposes a multimodal deep learning model for classifying the tissue perfusion phase using infrared, thermal, and visible spectrum images of the human hand. The proposed model consists of various preprocessing techniques such as manipulation, homography alignments, and masking. The significant contribution of this thesis is the interpretability analysis of deep learning models, achieved through the analysis of saliency maps and the Gradient-weighted Class Activation Mapping (Grad-CAM) methods. The purpose of this method is to find out how the convolutional …

Leveraging Convolutional Neural Networks For Through-The-Wall Radar Imaging: Challenges, Impacts, And Future Directions, Tumaini Edgar, Abdulla F. Ally, Abdi T. Abdalla

Tanzania Journal of Engineering and Technology (TJET)

Through-the-wall radar imaging (TWRI) is an essential technology for military and rescue applications; however, its performance in detecting and visualizing high-quality images of targets behind walls is significantly degraded by multipath reflections and signal attenuation. This paper reviews the current state of TWRI and its challenges, and explores the transformative potential of deep learning, particularly convolutional neural networks (CNNs), in addressing these challenges. Peer-reviewed articles published from 2018 to 2024 were analysed to examine CNN applications in addressing TWRI challenges. The analysis reveals that using CNNs, TWRI systems can be more effective by filtering wall distortions, reducing noise, lowering computational …

Predictive Analytics In Oncology And Ophthalmology: Machine Learning Applications For Diabetic Retinopathy And Breast Cancer, Ali Abidalkareem

Electronic Theses and Dissertations 2020 - Present

The convergence of artificial intelligence and healthcare represents one of the most transformative developments in modern medicine, with deep learning technologies emerging as powerful tools for addressing complex diagnostic challenges. This dissertation develops and validates machine learning frameworks that address critical challenges in medical diagnosis through innovative approaches to data augmentation, feature learning, and classification, focusing on two fundamental problems: Diabetic Retinopathy (DR) severity classification using multi-model convolutional neural networks (CNNs), and breast cancer stage identification using microRNA (miRNA) gene expression biomarkers. For diabetic retinopathy classification, this work proposes an ensemble deep learning framework that integrates Diffusion-based data augmentation for …

An Interpretable Hybrid Deep And Reinforcement Learning Paradigm For Glioma Prognosis, Renuga Devi M Ms

Theses and Dissertations

Brain tumors are highly aggressive and lethal types of cancer, particularly gliomas. These cancerous growths show complicated pathophysiological behaviours and with poor prognosis despite therapeutic advances. Due to their biological differences and infiltrating growth, as well as overlapping radiological characteristics, they pose great difficulty in diagnosis, grading, and survival prediction. Artificial intelligence technology, which includes machine learning , deep learning, and reinforcement learning has developed into a new paradigm for the automation of brain tumor diagnostics and personalized treatment. The main goal of this study is to create an integrated AI-based framework that can perform brain tumor segmentation, grading and …

Architecting A Complex Adaptive System Model For Selecting Policies To Reduce Kidney Discard, Lirim Ashiku

Doctoral Dissertations

"The kidney allocation system is a complex, evolving system involving multiple heterogeneous agents. Each agent exhibits emergent behavior that may not fully align with the complex system goals. Therefore, there is a need for a transdisciplinary systems approach to visualize the interdependency among agents and understand the dominant patterns that shape the kidney allocation system.

First, this research presented an incremental hierarchical system engineering approach in identifying the agents’ needs and behaviors toward the complex systems’ goal of maximizing deceased donor kidney utilization and reducing kidney discard. The hierarchical systems approach linked with model-based system engineering aided in eliciting agents’ …

Deep Learning For Wireless Communications, Swarada Ajit Kulkarni

Electrical Engineering Dissertations

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

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

Dataless Neural Networks For Boolean Satisfiability And Network Optimization, Andrew Evan Gautier

Graduate Theses, Dissertations, and Problem Reports (ETD)

Combinatorial optimization problems (COPs) require searching over a finite solution space subject to constraints, with the goal of satisfying an objective function. They arise in operations research, scheduling, resource allocation, circuit design, and many other fields. Many problems in combinatorial optimization (including satisfiability and network design) are NP-hard. Traditionally, researchers have built approximate solvers that return near- optimal solutions efficiently by developing increasingly sophisticated heuristics and meta- heuristics. Deep learning has provided new opportunities for improving combinatorial solvers by leveraging neural guidance to prune the search space. Traditional neural networks have distinct drawbacks in this context: separate training and …

Real-Time Deep Learning Detection Of Toraja Carving Motifs Using Yolo11m For Cultural Heritage Preservation, Herman Herman, Farid Wajdi Mufti, Abdul Rachman Manga, Haidawati Nasir

Knowledge Engineering and Data Science

Toraja carvings are an important part of Indonesia’s cultural heritage, rich in symbolic, aesthetic, and philosophical meaning. However, the identification and preservation of carving motifs still rely on subjective, time-consuming manual processes, limiting scalability and inconsistent knowledge transmission. From a Knowledge Engineering and Cognitive Data Science perspective, this challenge highlights the need for mechanisms that can transform visual cultural artifacts into structured, machine-interpretable knowledge. This study investigates the use of the YOLO11m model as a data-driven approach for modeling cultural knowledge through automated detection of three Toraja carving motifs: pa_tedong, pa_kapu_baka, and pa_manu_londongan using original images collected directly from traditional …

Ai-Optimized Resource Management In Next-Gen Wireless Networks, Fatemeh Lotfi

All Dissertations

Next-generation wireless networks must deliver highly adaptive, scalable, and intelligent connectivity to satisfy the heterogeneous demands of emerging services, including enhanced mobile broadband, massive machine-type communications, and ultra reliable low latency applications. The Open Radio Access Network (O-RAN) paradigm has emerged as a key enabler of this vision, introducing openness, virtualization, and artificial intelligence (AI)-driven control into the RAN ecosystem. O-RAN’s disaggregated architecture facilitates multi-vendor interoperability and empowers intelligent management through the RAN Intelligent Controller (RIC). However, achieving real-time, autonomous, and generalized optimization in such a dynamic environment remains a significant challenge due to its distributed nature, non-stationary traffic, and …

Adaptive Deep Learning In Physical Layer Applications, Ali Owfi

All Dissertations

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

Abdominal Ultrasound Image Dataset For Organ Classification And Disease Detection, Sifat Zina Karim

Research Data

This is a dataset of Ultrasound (US) images of abdominal organs. US imaging is widely accessible and a very common diagnostic tool, as it is non-invasive and does not involve radiation risk. This dataset was curated solely for research in deep learning, with potential applications in supervised, semi-supervised, and unsupervised learning to support disease detection in resource-constrained settings.

The dataset comprises 5,468 unique images organized into ten anatomical categories: Abdominal Aorta (0), Gallbladder (1), Hepatic Vein (2), Kidneys (3), Liver (4), Ovaries (5), Pancreas (6), Portal Vein (7), Spleen (8), and a composite Pelvic Urinary/Reproductive category (9), comprising the Urinary …

Detecting Electrical Submersible Pump (Esp) Failures And Estimating Run Life Using Artificial Neural Networks, Mostafa Ahmed Sobhy

Theses and Dissertations

Electric Submersible Pumps (ESPs) are one of the important artificial lift methods for sustaining production in mature and high-water-cut wells; but may suffer frequent failures due to mechanical, electrical, hydraulic, chemical, and operational failures. These failures can yield substantial deferred production and intervention costs. Plenty of ESP installations are fitted with downhole sensors. Yet, it is observed that the current industry practice underutilizes the wealth of available sensor and operational data and lacks standardized, explainable failure-type identification and classification.

In this thesis, a comprehensive Machine Learning (ML) and Deep Learning (DL) framework was introduced for ESPs that simultaneously estimates remaining …

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 …

Computational Modeling For Automatic Superconducting Cavity Fault Prediction And Classification Using Time Series Signals, Md Monibor Rahman

Electrical & Computer Engineering Theses & Dissertations

Processing multivariate time series signals collected from sensor networks is challenging because of complex temporal dependencies and non-stationarity. With the advent of artificial intelligence (AI) like machine learning and deep learning, it has become possible to process sensor-driven time series data more effectively than traditional statistical methods.

This dissertation aims to develop machine learning and deep learning models to address machine fault diagnosis using multivariate time series signals collected from the Continuous Electron Beam Accelerator Facility (CEBAF) at Jefferson Lab. The first goal of the proposed work is to develop deep learning–based classification models and an unsupervised fault clustering approach …

Input Structure Based Optimization For Privacy Preserving Ai Systems, Feng Yizhou

Electrical & Computer Engineering Theses & Dissertations

As Artificial Intelligence (AI) systems become increasingly integrated into critical domains, ensuring privacy-preserving model design and system deployment has become a pressing priority. Safeguarding both sensitive user data and proprietary model parameters is critical throughout the AI model and system, from data acquisition and pre-processing to model inference and deployment. However, existing privacy-preserving frameworks face several limitations, including fragmented data ownership, incomplete protection across system stages, substantial computational overhead, and poor scalability to modern architectures such as large language models. This dissertation explores a unifying optimization strategy centered on input structure design to address these challenges. The core idea is …

Implementation Of Residual Tandem Neural Networks For Photonic Inverse Design, Ponthea A. Zahraii

Electrical Engineering and Computer Science (MS) Theses

Deep-learning approaches can greatly benefit the modeling and design of nanophotonic and optical structures. Traditional full-wave simulations are time and resource-intensive, which can act as a bottleneck in photonic design. On the other hand, deep-learning approaches for designing the response of nanophotonic geometries can be computationally inexpensive and produce accurate and efficient results. In this project, we specifically investigate the case of optical forces near meta-structures. We propose using an inverse design approach with residual blocks to account for the deep nature of this architecture and inherently address the non-uniqueness problem. A tandem approach, which consists of two interconnected models, …

Removing Eog Artifacts From Eeg Recordings Using Deep Learning, Christian O'Reilly, Scott Huberty

Faculty Publications

The electroencephalogram (EEG) directly measures the electrical activity generated by the brain. Unfortunately, it is often contaminated by various artifacts, notably those caused by eye movements and blinks (EOG artifacts). Such artifacts are usually removed using an independent component analysis (ICA) or other blind source separation techniques. However, it is difficult to assess whether subtracting EOG components estimated through ICA removes some neurogenic activity. It is crucial to address this question to avoid biasing EEG analyses. Toward that objective, we developed a deep learning model for EOG artifact removal that exploits information about eye movements available through eye-tracking (ET). Using …

Enhancing Ai Reliability: Probabilistic Inference And Neural Optimization, Behnam Zeinali Rizi

USF Tampa Graduate Theses and Dissertations

Deep neural networks have recently shown better performance than traditional machine learning algorithms in various applications such as computer vision, natural language processing, indoor navigation, and biomedical signal/bio-informatics data processing tasks. However, some main challenges still exist when harnessing these models for different applications. The first challenge is the performance of these methodologies for some specific types of data, such as Biomedical images, IMU measurements, and even bioinformatics data, such as genome expression. Moreover, deploying these models on mobile and IoT devices is computationally challenging. Most devices use cloud computing, where powerful deep-learning models analyze the data on a server. …

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 …

Yolot: A Recurrent Yolo Model For Robust Video-Based Automotive Object Detection, Dylan Jay Baxter

Master's Theses

Though incredibly effective at detecting objects in isolated frames, modern object detection models are often not designed to take advantage of information present in previous frames of a video stream, despite that data being readily avail- able. To address this shortcoming, this paper proposes YOLOT, a modification of the widely used YOLOv8 object detection model, which seeks to utilize this temporal information with the addition of recurrent structures. In the design of YOLOT, a series of recurrent convolutional modules were inserted at backbone and neck outputs and the final and most effective design was found to be the insertion of …

Deep Target Recognition: Semi-Supervised Annotation, Sensor Fusion And Super-Resolution, Shoaib Meraj Sami

Graduate Theses, Dissertations, and Problem Reports (ETD)

Despite the recent expansion of machine learning algorithms to cover a wide range of disciplines, several areas of automatic target recognition (ATR) remain underexplored. This dissertation presents tools developed to improve performance in three significant aspects of ATR: semi-supervised annotation, sensor fusion, and image super-resolution. The aim of the semi-supervised methods is to automatically annotate targets in scenarios where labeled data are scarce in the target domain but available in the source domain. Secondly, to address the limitations of individual image sensors and enhance robustness under different environmental conditions and man-made constraints, a sensor fusion algorithm was developed to improve …

Electricity Theft Detection With An Adaptive Deep Learning Architecture, Mohammed Sleiman, Cihan Dagli, Rui Bo

Engineering Management and Systems Engineering Faculty Research & Creative Works

Electricity theft presents a significant challenge to the power industry. This paper demonstrates an adaptive deep framework integrating dimensionality reduction, graph modeling, attention mechanisms, and dynamic feature refinement for improving theft detection. Principal Component Analysis squeezes consumption data while an Autoencoder extracts latent representations and denoises the input. A Gated Graph Convolutional Neural Network uses k-Nearest Neighbors to model local relationships, while Transformers capture long range global dependencies. Neural Ordinary Differential Equations then refine features over continuous time, improving adaptability to complex patterns. The framework achieves 94.01% accuracy with stratified 5-fold cross validation. However, class imbalance challenges the minority class …

A Multiscale Ai Framework For Forest And Agriculture Health Monitoring: Drone-Based Object Recognition And Segmentation For Automated Ecological Assessment, Sruthi Keerthi Valicharla

Graduate Theses, Dissertations, and Problem Reports (ETD)

Forest and agricultural ecosystems are increasingly at risk due to invasive species, pests, and diseases, necessitating scalable, automated, and intelligent monitoring solutions. Traditional field based forest and agriculture health assessments are limited by cost, time, and spatial coverage. This dissertation presents a multiscale deep learning framework that automates forest and agriculture health monitoring using drone imagery and computer vision techniques. The system operates across three spatial levels: forest level, tree level, and leaf level, combining object detection, segmentation, and classification models to support large scale ecological assessment.

At the forest level, high-altitude drone imagery is processed using object detection and …

Prediction Of Audit Findings Using Deep Learning With Financial And Non-Financial Data: A Case Study In Province X, Fery Yohan Setiawan, Eko Mulyanto Yuniarno, Reza Fuad Rachmadi

Knowledge Engineering and Data Science

The implementation of the audit from the local government financial statements by The Audit Board of The Republic of Indonesia (BPK RI), especially for the Province X representative, are frequently faced by the various limitations, one of them being the required audit time. At this moment, the BPK RI representative of Province X doesn’t have the tools that are able to help the accurate of sample determination for the pick test, which resulted in this study proposing the application of multi-label classification to predict the findings of financial statement (Laporan Keuangan, LK) audits based on financial and non …

Assessing Deep Learning Models And Hyperparameter Optimization For Stable Time-Series Electricity Load Forecasting, Sukma Patrya, Aji Prasetya Wibawa, Aripriharta Aripriharta

Knowledge Engineering and Data Science

Long-term electricity load forecasting plays an important role in ensuring system reliability, optimizing energy management, and making operational plans in face of continuously rising electricity demands. This study suggests a complete deep learning method for univariate forecasting of future electricity loads based on climatology and electricity consumption data for the period between 2019 and 2023. The initial dataset was cleaned, normalized, and partitioned chronologically into train/test datasets. Four train/test split cases (20/80, 40/60, 60/40, 80/20) were considered to explore the impact of different levels of historical data availability on the performance of the suggested framework from data-poor to data-rich situations. …

Deep Learning For Uav Classification: Impact Of Noise And Multipath Fading In Rf Signals, Prajoy Podder, Maciej Jan Zawodniok, Sanjay Kumar Madria

Electrical and Computer Engineering Faculty Research & Creative Works

The increasing presence of unmanned aerial vehicles (UAVs) raises serious security concerns, particularly regarding unauthorized drone operations. Recent U.S. security statistics report a sharp rise in unauthorized UAV activities, with the Federal Aviation Administration (FAA) receiving over 100 monthly reports of illegal drone operations near airports. In 2024 alone, Dedrone records 1.19 million unauthorized drone flights across major U.S. cities, highlighting the need for robust UAV detection and classification systems. In this work, a lightweight Convolutional Neural Network (CNN) model is proposed for RF-based UAV classification under noisy and multipath fading conditions. The proposed CNN consists of multiple convolutional blocks, …

Time Series Forecasting With Lstm: An Extensive Content Analysis, Andri Pranolo, Xiaofeng Zhou, Yingchi Mao

Knowledge Engineering and Data Science

This paper presents a comprehensive bibliometric and content review of the trend, architecture, and application of long short-term memory (LSTM) models for time series forecasting. The study aims to provide insights into the overall statistics and distribution of papers focused on LSTM for forecasting. Additionally, the research questions address the most highly cited papers based on LSTM approaches in forecasting, the most productive journals in this field, and identifying trends, gaps, summary tasks and their performance, datasets availability, and future research directions for LSTM in forecasting. This paper is a comprehensive review of LSTM for forecasting from 2017 to 2023 …

Improving Large Scale Face Recognition With Identity Codes, Mohammad Saeed Ebrahimi Saadabadi

Graduate Theses, Dissertations, and Problem Reports (ETD)

Despite significant advances in deep face recognition, current systems face several practical challenges in real-world scenarios. These include high computational cost of training on large-scale datasets, inefficient use of metric space, and mismatch between training and evaluation frameworks. This dissertation addresses these limitations through three completed studies. The first part presents a research effort aimed at addressing the computational bottlenecks of large-scale FR training. This work proposes a framework that replaces conventional scalar identity labels with structured identity codes, \ie, sequences of tokens optimized to preserve semantic and metric separation. The formulation is designed to reduce the computational cost of …

Modelling V-Band Atmospheric Loss With Deep Learning, Ralph Lyndon Gesner

Electrical and Computer Engineering ETDs

Modelling atmospheric loss is fundamental to implementation of future mm-wave terrestrial and earth space communication links. Atmospheric losses have traditionally been estimated by calculating the contributions of individual weather phenomena through in-situ meteorological measurements and statistically derived models for estimating localized atmospheric water content. Collecting data for all points along the propagation path and calculating the physical effects of gases, clouds, and precipitation individually is both time consuming and impractical for large-scale use cases.

In response to these present limitations, this work proposes the use of novel deep learning models for estimating atmospheric losses from tabular meteorological sensor data and …