Electrical and Computer Engineering Commons^™

Deep Learning In Lung Cancer Pre- And Post-Radiation Therapy: Diagnosis Of Malignancy And Radiation-Induced Lung Injury From 3d X-Ray Ct., Benjamin Peter Veasey

Electronic Theses and Dissertations

Lung cancer remains the leading cause of cancer-related mortality worldwide, with early detection and accurate diagnosis being critical for improving patient outcomes. Additionally, the progression of Radiation-Induced Lung Injury (RILI) following Stereotactic Body Radiation Therapy (SBRT) for lung cancer presents a significant diagnostic challenge. This dissertation addresses these challenges by developing deep learning-based diagnostic tools for both pre-treatment lung nodule malignancy classification and post-treatment RILI identification using 3D X-ray CT imaging. The research is divided into two primary objectives. First, for lung nodule malignancy classification, we developed a biopsy-confirmed dataset, called NLSTx, to train and evaluate deep learning models while …

A Study Of The Impact Of Balancing, Geometric Transformation, Generative Networks, And Roi Techniques In Eye Diseases Classification, Sghaira Hareb Alnuaimi

Theses

Automatic detection of ocular diseases helps medical professionals efficiently identify eye disorders, reduce diagnostic errors, and accelerate diagnoses to prevent blindness. Deep learning has been successfully utilized in various fields, including medical image classification. However, in spite of these advancements, challenges remain in ocular disease classification.

The objective of this work is to address these challenges using data processing, data augmentation in combination with Region of Interest (ROI) techniques. Medical datasets often suffer from scarcity, imbalance, and low-quality images, leading to inaccurate classification. To mitigate these issues, we utilize the ODIR dataset, which contains 7,000 labelled training images for both …

Multimodal Emotion Recognition For Human-Robot Interaction Across Neuro-Diverse Populations., Ruchik Mishra

Electronic Theses and Dissertations

This dissertation explores the integration of multimodal data streams and artificial intelligence pipelines to understand human affect in neurotypical and children with Autism Spectrum Disorder (ASD). This dissertation captures human affect in the context of human-robot interaction. For this, multiple studies have been presented with both children with ASD and neurotypical adults. This dissertation makes four contributions: 1) The first study introduces autonomy during perspective-taking teaching sessions by making verbal content generation through large language models (LLMs). This system is the first of its kind for teaching perspective-taking in a semi-autonomous manner under the supervision of domain experts. Furthermore, this …

An Automatic Colorectal Polyps Detection Approach For Ct Colonography., Mohamed Yousuf

Electronic Theses and Dissertations

Colon cancer, also known as colorectal cancer, is a significant health concern, with increasing incidence rates, particularly among individuals under 50. This rise has led experts to recommend the introduction of regular screenings at 45 years of age for adults at average risk. Early detection through such screenings can identify precancerous polyps, allowing their removal before they develop into cancer. This proactive approach has the potential to reduce colorectal cancer deaths by up to 60%. In addition, research indicates that people diagnosed before age 50 have better survival rates, which emphasizes the importance of early diagnosis. Therefore, adhering to recommended …

Artificial Intelligence Applications For Grid-Connected Solar Inverters, Utkirjon Ubaydullaev, Sarvinoz Mirzaeva, Hasan Mustafoev

Chemical Technology, Control and Management

The increasing global demand for renewable energy has highlighted the importance of grid-connected solar inverters in ensuring efficient and stable power conversion. However, challenges such as fluctuations in solar energy generation, grid disturbances, and power quality issues necessitate advanced control strategies. The integration of artificial intelligence (AI) into solar inverters presents a transformative solution, enhancing performance, adaptability, and reliability in real-world applications.

This review explores the role of AI techniques, including machine learning (ML), deep learning (DL), fuzzy logic, and reinforcement learning (RL), in optimizing key inverter functionalities such as maximum power point tracking (MPPT), fault detection, power quality enhancement, …

Deep Learning-Based Gain Estimation For Multi-User Software-Defined Radios In Aircraft Communications, Viraj K. Gajjar, Kurt L. Kosbar

Electrical and Computer Engineering Faculty Research & Creative Works

It may be helpful to integrate multiple aircraft communication and navigation functions into a single software-defined radio (SDR) platform. To transmit these multiple signals, the SDR would first sum the baseband version of the signals. This outgoing composite signal would be passed through a digital-to-analog converter (DAC) before being up-converted and passed through a radio frequency (RF) amplifier. To prevent non-linear distortion in the RF amplifier, it is important to know the peak voltage of the composite. While this is reasonably straightforward when a single modulation is used, it is more challenging when working with composite signals. This paper describes …

Advanced Prediction Of Events And Temporal Expressions In Medical Text Using The Jena Api: Integrating Ontologies And Deep Learning, Hafida Tiaiba, Lyazid Sabri, Okba Kazar

Turkish Journal of Electrical Engineering and Computer Sciences

The automatic recognition of medical concepts and temporal expressions in narrative clinical text enhances the utility of electronic health records (EHRs) and supports clinical decision-making and research. However, challenges arise due to the complexity of medical language, ambiguity of terms, and variability in expression. To address these issues, the use of medical ontologies significantly improves data management in healthcare. A novel approach integrates various medical ontologies covering drugs, symptoms, diseases, anatomy, disease drivers, and food, and with convolutional neural networks (CNNs) -including Standard, Transposed, and Separable convolution models (CONSEPTR)- to extract both medical events (e.g., clinical departments, treatments, problems) and …

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 …

Explaining Deep Learning-Based Anomaly Detection In Energy Consumption Data By Focusing On Contextually Relevant Data, Mohammad Noorchenarboo, Katarina Grolinger

Electrical and Computer Engineering Publications

Detecting anomalies in energy consumption data is crucial for identifying energy waste, equipment malfunction, and overall, for ensuring efficient energy management. Machine learning, and specifically deep learning approaches, have been greatly successful in anomaly detection; however, they are black-box approaches that do not provide transparency or explanations. SHAP and its variants have been proposed to explain these models, but they suffer from high computational complexity (SHAP) or instability and inconsistency (e.g., Kernel SHAP). To address these challenges, this paper proposes an explainability approach for anomalies in energy consumption data that focuses on context-relevant information. The proposed approach leverages existing explainability …

Leveraging Hypernetworks And Learnable Kernels For Consumer Energy Forecasting Across Diverse Consumer Types, Muhammad Umair Danish, Katarina Grolinger

Electrical and Computer Engineering Publications

Consumer energy forecasting is essential for managing energy consumption and planning, directly influencing operational efficiency, cost reduction, personalized energy management, and sustainability efforts. In recent years, deep learning techniques, especially LSTMs and transformers, have been greatly successful in the field of energy consumption forecasting. Nevertheless, these techniques have difficulties in capturing complex and sudden variations, and, moreover, they are commonly examined only on a specific type of consumer (e.g., only offices, only schools). Consequently, this paper proposes HyperEnergy, a consumer energy forecasting strategy that leverages hypernetworks for improved modeling of complex patterns applicable across a diversity of consumers. Hypernetwork is …

Transplant Surgeon Fuzzy Associative Memory (Tsfam): Model For Capturing Surgeon Perspective, Rachel Dzieran, Cihan H. Dagli, Robert J. Marley

Engineering Management and Systems Engineering Faculty Research & Creative Works

AI-driven healthcare decision-making is multi-faceted, requiring complex logic to adapt to evolving policies and societal demands. Effective change implementation by healthcare providers and multidisciplinary organ transplant teams depends on adaptive decision-making. The proposed Transplant Surgeon Fuzzy Associative Memory (TSFAM) model introduces a novel approach to Human-AI Teaming, keeping human expertise central while dynamically adjusting to changing requirements. TSFAM employs fuzzy logic to manage imperfect data and human ambiguity, integrating the transplant surgeon perspective with the AI deep learning decision-making tool, creating a resilient solution in this critical domain. By embedding adaptive capabilities into the architecture, TSFAM exemplifies the adaptability of …

Cyber Forensics With Deep Learning Recurrent Neural Networks, Pfautch Ric, Dagli Cihan, Ashiku Lirim

Engineering Management and Systems Engineering Faculty Research & Creative Works

Detection of anomalies and anti-patterns is essential for adaptive systems with the ability to perform without foreknowledge. Some problems require both classification and regression along with sensitivity tuning and explainability. Some have highly dimensional datasets that are time dependent. This research offers results for Long-Short-Term Memory (LSTM) and Gated Recurrent Units (GRU) algorithms using the BETH dataset. It unpacks metadata attributes and stages a unique approach via Abstract-Feature Analysis (AFA), hyper parameter tuning, and Principal Component Analysis (PCA) within the RNN model. By removing foreknowledge, this research offers insights into RNN anomaly detection performance when an event absent in training …

Lifelong Machine Learning With Adaptive Resonance Theory, Sasha Petrenko

Doctoral Dissertations

"This publication option dissertation is composed of three papers concerning the study of the problem lifelong machine learning with Adaptive Resonance Theory (ART) algorithms. Lifelong learning (L2) is a challenging machine learning paradigm that both encompasses and formalizes the fields of continual learning and incremental learning. The field is concerned with the mitigation of the phenomenon of catastrophic forgetting whereby learning agents that are faced with incrementally novel information deleteriously overwrite previous knowledge if that learning process is not regularized to counteract this consequence. ART algorithms solve this stability-plasticity dilemma by optimally assigning learning to categories or instantiating new knowledge …

A Cost-Effective Nilm Solution With Three-Point Labelling And Non-Causal Convolution Technique, Yanan Zhang, Gan Zhou, Yanjun Feng, Zhan Liu, Li Huang, Zhi Li, Rui Bo

Electrical and Computer Engineering Faculty Research & Creative Works

Although deep learning is increasingly promising in the field of Non-Intrusive Load Monitoring (NILM) these days, the high costs of data recording and labelling represent a significant challenge for the training of supervised models. To address this, a cost-effective sequence-to-points NILM solution is proposed, integrating three-point labelling with non-causal convolution techniques. The approach introduces a semi-automatic labelling framework for obtaining NILM three-point data, which provides a low-cost data collection and labelling solution for large-scale applications. Then, a novel loss function combining coordinate loss and confidence loss is developed to address the positional misalignment and negative sample confusion in sequence-to-points scenario …

Computer Vision-Based Framework For Data Extraction From Heterogeneous Financial Tables: A Comprehensive Approach To Unlocking Financial Insights, Iftakhar Ali Khandokar, Priya Deshpande

Electrical and Computer Engineering Faculty Research and Publications

Information extraction from financial document images is crucial in computer vision and NLP, as financial data often exists in image or PDF format, enabling organizations to analyze and make informed business decisions using OCR advancements. The table contents of financial document images are one of the prominent structures to confine important portions of data of the document and many Deep learning-based methods have been proposed to detect Table regions inside document images. The shortcomings of the current approach are that it is bounded within the detection of the table region and struggles in cases such as handling different layouts and …

Optimizing Ai Language Models: A Study Of Chatgpt-4 Vs. Chatgpt-4o, Md Nurul Absar Siddiky, Muhammad Enayetur Rahman, Md Fayaz Bin Hossen, Muhammad Rezaur Rahman, Md. Shahadat Jaman

Electrical & Computer Engineering Faculty Publications

This paper presents a comparative analysis of OpenAI's GPT-4 and its optimized variant, GPT-4o, focusing on their architectural differences, performance, and real-world applications. GPT-4, built upon the Transformer architecture, has set new standards in natural language processing (NLP) with its capacity to generate coherent and contextually relevant text across a wide range of tasks. However, its computational demands, requiring substantial hardware resources, make it less accessible for smaller organizations and real-time applications. In contrast, GPT-4o addresses these challenges by incorporating optimizations such as model compression, parameter pruning, and memory-efficient computation, allowing it to deliver similar performance with significantly lower computational …

Land Target Detection Algorithm In Remote Sensing Images Based On Deep Learning, Wenyi Hu, Xiaomeng Jiang, Jiawei Tian, Shitong Ye, Shan Liu

Electrical & Computer Engineering Faculty Publications

Remote sensing technology plays a crucial role across various sectors, such as meteorological monitoring, city planning, and natural resource exploration. A critical aspect of remote sensing image analysis is land target detection, which involves identifying and classifying land-based objects within satellite or aerial imagery. However, despite advancements in both traditional detection methods and deep-learning-based approaches, detecting land targets remains challenging, especially when dealing with small and rotated objects that are difficult to distinguish. To address these challenges, this study introduces an enhanced model, YOLOv5s-CACSD, which builds upon the YOLOv5s framework. Our model integrates the channel attention (CA) mechanism, CARAFE, and …

Ai-Based Steganography Method To Enhance The Information Security Of Hidden Messages In Digital Images, Nhi Do Ngoc Huynh, Jiajun Jiang, Chung-Hao Chen, Wen-Chao Yang

Electrical & Computer Engineering Faculty Publications

With the increasing sophistication of Artificial Intelligence (AI), traditional digital steganography methods face a growing risk of being detected and compromised. Adversarial attacks, in particular, pose a significant threat to the security and robustness of hidden information. To address these challenges, this paper proposes a novel AI-based steganography framework designed to enhance the security of concealed messages within digital images. Our approach introduces a multi-stage embedding process that utilizes a sequence of encoder models, including a base encoder, a residual encoder, and a dense encoder, to create a more complex and secure hiding environment. To further improve robustness, we integrate …

Source Detection And Automatic Modulation Classification For Modern Antenna Array Processing, Jayakrishnan Vijayamohanan

Electrical and Computer Engineering ETDs

Source detection and automatic modulation classification are two of the most important steps in any array processing task. In this research a novel deep learning model referred to as RadioNet, is proposed that is focused on solving both these problems by reformulating them as a multi-label classification problem. Traditional approaches to both these topics face challenges in scenarios with noise, interference, fewer number of snapshots, and high number of sources. The limitations of the conventional models are investigated and overcome by the proposed solution. RadioNet is also compared with other existing state-of-the-art machine learning based solutions. The introduced model is …

Practical And Lightweight Defense Against Website Fingerprinting, Colman Mcguan, Chansu Yu, Kyoungwon Suh

Electrical and Computer Engineering Faculty Publications

Website fingerprinting is a passive network traffic analysis technique that enables an adversary to identify the website visited by a user despite encryption and the use of privacy services such as Tor. Several website fingerprinting defenses built on top of Tor have been proposed to guarantee a user's privacy by concealing trace features that are important to classification. However, some of the best defenses incur a high bandwidth and/or latency overhead. To combat this, new defenses have sought to be both lightweight - i.e., introduce a small amount of bandwidth overhead - and zero-delay to real network traffic. This work …

Dual-Channel Side Channel Attack: Improved Aes Key Decryption By Combining Power And Electromagnetic Side Channels With Convolutional Neural Networks, Sean P. O'Neill

Theses and Dissertations

This research introduces a novel DL approach for SCA that combines power consumption and EM signals to enhance encryption key deduction by leveraging a dual-channel CNN architecture. A new dataset, consisting of simultaneous power and EM signal collections during 128-bitAES encryption, was developed to train and evaluate the model’s effectiveness. The combined approach achieved an 88% reduction in traces needed, from 50 traces to 6, for encryption key classification, outperforming traditional methods such as random forest, DPA, DEMA,and individual side channel CNN models. These findings highlight the potential of integrating multiple side channels in SCA to improve performance without the …

Developing Linguistic Patterns To Mitigate Inherent Human Bias In Offensive Language Detection, Toygar Tanyel, Besher Alkurdi, Serkan Ayvaz

Turkish Journal of Electrical Engineering and Computer Sciences

With the proliferation of social media, there has been a sharp increase in offensive content, particularly targeting vulnerable groups, exacerbating social problems such as hatred, racism, and sexism. Detecting offensive language use is crucial to prevent offensive language from being widely shared on social media. However, the accurate detection of irony, implication, and various forms of hate speech on social media remains a challenge. Natural language-based deep learning models require extensive training with large, comprehensive, and labeled datasets. Unfortunately, manually creating such datasets is both costly and error-prone. Additionally, the presence of human-bias in offensive language datasets is a major …

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

Faculty Publications

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

Combined Machine Learning And Differential Evolution For Optimal Design Of Electric Aircraft Propulsion Motors, David R. Stewart, Matin Vatani, Rosemary E. Alden, Donovin D. Lewis, Pedram Asef, Dan M. Ionel

Electrical and Computer Engineering Graduate Research

Electric aircraft propulsion requires highly efficient and power-dense fault-tolerant electric motors optimized for specific flight profile operation. State-of-the-art design of electric motors involves substantial computational resources and combines electromagnetic finite element analysis (FEA) and optimization techniques. This paper proposes a new approach using a physics-based machine learning (ML) multi-input univariate meta-model trained on FEA and differential evolution (DE) optimization results to predict electromagnetic torque output. Hundreds of individual designs, generated through multiple generations of a DE algorithm, are analyzed by 3D FEA to create a database, which is then employed for the training and satisfactory validation of the ML model. …

M3t-Lm: A Multi-Modal Multi-Task Learning Model For Jointly Predicting Patient Length Of Stay And Mortality, Junde Chen, Qing Li, Feng Liu, Yuxin Wen

Engineering Faculty Articles and Research

Ensuring accurate predictions of inpatient length of stay (LoS) and mortality rates is essential for enhancing hospital service efficiency, particularly in light of the constraints posed by limited healthcare resources. Integrative analysis of heterogeneous clinic record data from different sources can hold great promise for improving the prognosis and diagnosis level of LoS and mortality. Currently, most existing studies solely focus on single data modality or tend to single-task learning, i.e., training LoS and mortality tasks separately. This limits the utilization of available multi-modal data and prevents the sharing of feature representations that could capture correlations between different tasks, ultimately …

Two-Dimensional Quantum Material Identification Via Self-Attention And Soft-Labeling In Deep Learning, Xuan Bac Nguyen, Apoorva Bisht, Benjamin Thompson, Hugh O.H. Churchill, Khoa Luu, Samee U. Khan

Electrical Engineering and Computer Science Faculty Publications and Presentations

Detecting two-dimensional (2D) materials in silicon chips presents a significant challenge in the field of quantum machines due to the difficulty of data collection. Specifically, among thousands of flakes, not all flakes are useful or well-annotated, resulting in noisy and hard samples within the dataset, which challenges the deep neural network (DNN) to learn. To address this problem, we propose a novel method for identifying quantum 2D flakes even when there is a high rate of missing annotations in the input images. In particular, we first propose a new mechanism for automatically detecting false negative flakes that are missing annotations. …

Denoising And Super-Resolution Of In-Vitro 4e Flow Mri In A Stenotic Phantom Model Using Physics-Informed Neural Networks., Shrouk M. Wally

Electronic Theses and Dissertations

In recent years, the use of 4D flow MRI has revolutionized cardiovascular imag- ing by providing comprehensive data on blood flow dynamics over time. However, the limited spatial and temporal resolution of this imaging modality can hinder the accurate assessment of complex hemodynamic phenomena. This thesis explores the application of Physics-Informed Neural Networks (PINNs) to enhance the resolution of 4D flow MRI data, thereby improving its clinical utility. PINNs are a class of neural networks that integrate physical laws into their training process. By embedding these physics equations, PINNs can discover the underlying physics of fluid dynamics to produce more …

Reinforcement Learning Assisted Communication Resources Optimization In Advanced Air Mobility., Ruixuan Han

Electronic Theses and Dissertations

Advanced air mobility (AAM), which envisages a safe and efficient aviation transportation system, has drawn significant attention to support the increasing mobility demand in metropolitan areas. Communication services for AAM aerial vehicles (AVs) are crucial for ensuring flight safety. This dissertation explores three research topics on communication resource allocation problems in AAM applications. The first topic, addressed in Chapter II, investigates the joint velocity selection and spectrum allocation problem for AAM applications to enhance spectrum utilization efficiency (SUE). In the AAM scenario, multiple AVs travel along predefined paths for passenger and cargo deliveries. Given that AAM aims to provide fast …

Multi-Label Voice Disorder Classification Using Raw Waveforms, Gökay Di̇şken

Turkish Journal of Electrical Engineering and Computer Sciences

Automated voice disorder systems that distinguish pathological voices from healthy ones have been developed with the aid of machine learning methods. Both clinicians and patients can benefit from these systems as they provide many advantages, compared to the invasive techniques. These systems can produce binary (healthy/pathological) or multi-class (healthy/selected pathologies) decisions. However, multiple disorders might exist in an individual’s voice. Multi-label classification should be considered in such cases. By this time, only a single report is available on this topic, where hand-crafted features were used, and a data augmentation technique was utilized to overcome class imbalances. In this study, a …

Enrichment Of Turkish Question Answering Systems Using Knowledge Graphs, Okan Çi̇ftçi̇, Fati̇h Soygazi̇, Selma Teki̇r

Turkish Journal of Electrical Engineering and Computer Sciences

Recent capabilities of large language models (LLMs) have transformed many tasks in Natural Language Processing (NLP), including question answering. The state-of-the-art systems do an excellent job of responding in a relevant, persuasive way but cannot guarantee factuality. Knowledge graphs, representing facts as triplets, can be valuable for avoiding errors and inconsistencies with real-world facts. This work introduces a knowledge graph-based approach to Turkish question answering. The proposed approach aims to develop a methodology capable of drawing inferences from a knowledge graph to answer complex multihop questions. We construct the Beyazperde Movie Knowledge Graph (BPMovieKG) and the Turkish Movie Question Answering …