Electrical and Computer Engineering Commons^™

Lrq-Solver: A Transformer-Based Neural Operator For Fast And Accurate Solving Of Large-Scale 3d Pdes, Peijian Zeng, Guan Wang, Haohao Gu, Xiaoguang Hu, Tiezhu Gao, Zhuowei Wang, Aimin Yang, Xiaoyu Song

Electrical and Computer Engineering Faculty Publications and Presentations

Solving large-scale PDEs on complex three-dimensional geometries remains a central challenge in scientific and engineering computing, often due to expensive pre-processing stages and high computational overhead. We present Low-Rank Query-based PDE Solver (LRQ-Solver), a physics-integrated deep learning framework for efficient CAE simulations of complex three-dimensional geometries in CAD-driven design analysis. Built upon the Parameter-Conditioned Lagrangian Modeling (PCLM) that embeds physical consistency into the learning process and the Low-Rank Query Attention (LR-QA) module that reduces attention complexity from O(N2) to O(NC2+C3) via covariance decomposition, LRQ-Solver supports multi-configuration analysis within iterative design workflows. On two benchmark datasets, it achieves a 28.6% error …

Dynamic Focal Loss Adjustment For Railway Defect Detection, Mehmet Koç, Ridvan Özdemi̇r, Ömer Gerek

Turkish Journal of Electrical Engineering and Computer Sciences

Railway infrastructure is critical to the safe and efficient operation of transportation systems, and the early detection of defects is essential for preventing catastrophic failures. Automated defect detection methods are therefore crucial for maintaining continuous safety while reducing maintenance costs. Although Focal Loss is widely used in object detection under class-imbalanced conditions, its fixed α parameter may limit its effectiveness in detecting rare defects. In this study, we propose an adaptive α-tuned Focal Loss approach that dynamically adjusts class weights based on average precision (AP) values. By iteratively optimizing α without relying on gradient-based optimization, the proposed method improves the …

Deep Multimodal Sensor Fusion For Autonomous Driving: A Real-World Deployment On Little Blue, Raphael T. Pamie-George

Electrical & Computer Engineering Theses & Dissertations

Accurate perception and control systems are essential for autonomous vehicles to safely interpret and navigate complex environments. Individual sensing modalities such as cameras, LiDAR, and inertial measurement units (IMUs) provide valuable environmental and vehicle state information; however, each sensor exhibits inherent limitations when used independently. Camera performance can degrade under varying lighting conditions, LiDAR measurements may be sparse or affected by environmental noise, and IMU measurements are susceptible to drift over time. Little Blue, a research autonomous vehicle platform from ODU (Old Dominion University), previously relied primarily on camera-based data for neural network training, limiting the system’s ability to exploit …

Scalefusion: Hierarchical Feature Aggregation For Unified Multiscale Object Detection, Ayşenur Yaylaci, Berru Kaya, Mehmet Kiliçarslan

Turkish Journal of Electrical Engineering and Computer Sciences

Detecting objects across a wide range of scales, particularly small ones, remains a significant challenge in computer vision. Existing methods often improve small object detection at the cost of performance on larger objects or introduce significant computational overhead through external techniques like image slicing. This paper introduces ScaleFusion, a novel, unified, end-to-end object detection architecture designed to provide robust performance across all scales within a single model. The core of our approach is a hierarchical feature aggregation strategy structured like a tree. ScaleFusion processes an image by running a shared backbone network only on fine-grained patches at the lowest level …

Skinclusive Ai: Towards Equitable Skin Cancer Detection For Deployment On Edge Devices, Joseph Galicinao

Master's Theses

Skin cancer is one of the most prevalent cancers worldwide, yet existing deep-learning models exhibit significant racial disparities because many widely used datasets are heavily skewed toward lighter skin tones. In addition, many approaches are not designed for deployment on resource-constrained devices, which limits accessibility. This work presents a comprehensive evaluation of classical machine learning and deep-learning based models for binary skin lesion classification, identifying the Swin-Tiny transformer architecture as the most effective backbone. To address bias, we curate a skin-tone balanced dataset, and introduce fairness-aware training through adversarial training, and joint distribution oversampling, to improve performance across protected attributes. …

Deep Learning Approaches For Ctenophore Identification And Tracking, Anagha Bharadwaj

Theses

Ctenophores are translucent marine organisms with nearly invisible tentacles and pose significant challenges due to their transparent morphology and ambiguous structural features. This research addresses the classification and tracking of these organisms and evaluates the performance of current computer vision models under sparse-data environments.

A dataset from the NJIT Life History Lab consisting of microscopic laboratory videos and photographs of different growth stages is used to train and assess a number of convolutional neural network designs, including VGG16, ResNet, BioCLIP2, YOLO, and DeepLabCut. Additionally, a web-based interface is developed to evaluate expert-labeled ground truth with the model's performance.

The findings …

A Descriptive Analysis Of Plant Leaf Disease Detection Using Machine Learning And Deep Learning Models: A Systematic Review, Arzoo Chamoli, Anuj Kumar

Turkish Journal of Electrical Engineering and Computer Sciences

Plant leaf disease detection (PLDD) is a growing active research area with burgeoning practical applications across various sectors such as agricultural monitoring, food security, and environmental conservation. Accurate segmentation and classification of plant leaf diseases remains a key challenge in the field of plant leaf disease prediction. The challenge demands automated methods for the plant disease identification because it needs to develop better crop management systems, which will boost agricultural production. In this article, we provide a systematic review of various machine learning (ML) and deep learning (DL) methods extensively used for PLDD. The review strategy follows a formal protocol, …

A Platform For Acquiring And Classifying Low-Noise Electrocardiogram Signals For Applications In Cardiovascular Monitoring, Begmamat Berdimurodovich Dushanov, Narzullo Mamatov Dr.

Technical science and innovation

The early screening and continuous monitoring of cardiovascular diseases need effective acquisition and smart processing of electrocardiogram (ECG) signals. In this article, we introduce a compact platform designed for the acquisition of low-noise ECG signals and classification of the signals using a one-dimensional convolutional neural network (1D-CNN). Our compact platform consists of a low-noise analog front-end (AFE), including an instrumentation amplifier and a chain of analog filters, along with a data acquisition component designed to ensure effective suppression of baseline wander and high frequencies. Our compact platform consumes a low amount of power and can therefore be used for continuous …

Multi-Modal Tensor Fusion For Alzheimer’S Disease Recognition, Mason Li, Tiffany Le, Jiajing Huang, Yuxin Wen

Engineering Faculty Articles and Research

Accurate and early diagnosis of Alzheimer’s disease (AD) is critical for effective intervention, disease monitoring, and patient care. Traditional diagnostic approaches rely on a single modality, such as clinical assessments, neuroimaging, or genetic markers, which may fail to capture the complex, multifaceted nature of AD. Multimodal learning has therefore been explored to integrate complementary information across data sources. However, conventional fusion strategies, including early feature concatenation and late decision-level fusion, often model modalities independently and fail to capture high-order cross-modal interactions. To address these limitations, we propose a multimodal tensor fusion network (MTFN) that integrates heterogeneous data sources, including visual …

Machine Learning In Peak Demand Forecasting: Foundations, Trends, And Insights, Shuang Dai, Fanlin Meng, Hongsheng Dai, Qian Wang, Xizhong Chen, Wenlei Bai, Peizhi Shi, Richard Allmendinger, Yuchen Zhang, Jian Liu

Electrical and Computer Engineering Faculty Research & Creative Works

Peak demand forecasting involves predicting the maximum electricity demand within a specific period, which plays a key role in maintaining the efficiency and stability of power systems. The rapid evolution of power systems, driven by advanced metering infrastructure, local energy applications such as electric vehicles, and the increasing adoption of intermittent renewable energy, has introduced greater randomness and reduced predictability in peak demand. Given the pressing need to address more diverse implementation requirements across different contexts, accurate and reliable peak demand forecasting has become increasingly important. To the best of our knowledge, this study is the first to provide a …

Deep Learning Based High-Resolution Electromagnetic Inversion Imaging Using Deep Convolutional Double-Module Structure, He Ming Yao, Shiji Song, Lijun Jiang, Michael Ng

Electrical and Computer Engineering Faculty Research & Creative Works

In this paper, a novel deep learning (DL) approach has been proposed to realize high-resolution electromagnetic (EM) inversion imaging. The newly proposed approach is based on the deep convolutional double-module structure (DCDMS), consisting of the pixel-interpolating module and the corresponding quality-improving module. While the pixel-interpolating module roughly increases the 'resolution' of the initial input, the following quality-improving module realizes quantitative EM imaging in high resolution. The input of the proposed DCDMS adopts the mixed input scheme, consisting of the received EM scattered field and the initial reconstruction in much low resolution computed from Gauss-Newton method. The output of the proposed …

Deep Learning Frameworks For Functional Genomics: Lncrna–Mirna Interactions, Dose-Specific Graph Modeling, And Complete Graph-Based Lncrna Functional Annotation Using Cross-Layer Attention, Sachit Satyal

Computer Science and Engineering Dissertations

Functional genomics seeks to understand how genes and regulatory elements orchestrate biological processes and adapt under diverse conditions. Two critical challenges in this field are deciphering the regulatory roles of long noncoding RNAs (lncRNAs) and modeling cellular transcriptional dynamics under therapeutic perturbations. While lncRNAs are increasingly recognized as key regulators in health and disease, their functions remain incompletely characterized. Concurrently, advances in single-cell transcriptomics reveal how gene and pathway activities rewire across drug dosage gradients, highlighting the need for computational frameworks that are predictive, interpretable, and capable of integrating molecular interactions with dynamic cellular states. This dissertation develops a unified …

Code-Net++: An Attention-Guided Deep Learning Framework With Grad-Cam-Based Explainability For Covid-19 Detection Using Chest X-Ray Images, Fareesa Amina, Dr Krishnanaik Vankdoth

Mansoura Engineering Journal

Chest radiograph imaging has emerged as a practical and scalable diagnostic modality for respiratory diseases, including COVID-19. However, accurate discrimination of COVID-19 manifestations from other pulmonary abnormalities remains challenging because of low contrast, imaging noise, and overlapping radiographic patterns. This work presents CODE-NET++, an enhanced attention-guided deep learning framework with Grad-CAM-based explainability for reliable COVID-19 detection using chest X-ray images. The proposed framework integrates adaptive trilateral filtering for image enhancement, Reverse Edge Attention Network (RE-Net) for lesion-aware segmentation, and an Enhanced LinkNet architecture with dilated convolutions for multiscale feature extraction and classification. Grad-CAM-based explainable artificial intelligence visualization is incorporated to …

Development Of Feature Tokenizer Deep Learning Model For Fault Diagnosis In Marine Propulsion System, Pratik Anand Deshpande, J. Preetha Roselyn, Prabha Sundaravadivel

Electrical Engineering Faculty Publications and Presentations

The fault diagnostics in Brushless Direct Current (BLDC) motor drive system is critical for operational safety and system lifespan in propulsion system applications. However, signature parameters such as currents, voltages, speed, and torque have provided nonlinear behavior, which limits the usefulness of traditional model-based approaches. This research provides a deep learning based intelligent system to monitor the failures in marine propulsion system. Each signal feature is represented as a structured token, with a specific class token used to collect global contextual information. The proposed model captures both local temporal dynamics and global inter-feature interdependence multi-layer self-attention processes, allowing for the …

Physics-Informed Temperature Prediction Of Lithium-Ion Batteries Using Decomposition-Enhanced Lstm And Bilstm Models, Seyed Saeed Madani, Yasmin Shabeer, Michael Fowler, Satyam Panchal, Carlos Ziebert, Hicham Chaoui, François Allard

Electrical & Computer Engineering Faculty Publications

Accurately forecasting the operating temperature of lithium-ion batteries (LIBs) is essential for preventing thermal runaway, extending service life, and ensuring the safe operation of electric vehicles and stationary energy-storage systems. This work introduces a unified, physics-informed, and data-driven temperature-prediction framework that integrates mathematically governed preprocessing, electrothermal decomposition, and sequential deep learning architectures. The methodology systematically applies the governing relations to convert raw temperature measurements into trend, seasonal, and residual components, thereby isolating long-term thermal accumulation, reversible entropy-driven oscillations, and irreversible resistive heating. These physically interpretable signatures serve as structured inputs to machine learning and deep learning models trained on temporally …

Stabilized Multi-Objective Optimization For Camouflage Attack In Remote Sensing, Omid Rajabi Rostami, Kazi Aminul Islam, Liuwan Zhu, Rui Ning, Chungsheng Xin, Hongyi Wu, Jiang Li

Electrical & Computer Engineering Faculty Publications

We investigate the vulnerability of multi-task maritime surveillance systems in which object detection and semantic segmentation operate concurrently. We propose Stabilized Multi-Objective Optimization (SMO), a framework that jointly targets Mask R-CNN and U-Net with a single universal adversarial texture in a digital white-box setting, with additional cross-model transfer evaluation. SMO combines a logarithmic-inversion loss transformation, feature inconsistency, and a systematic comparison of six optimization strategies for seven heterogeneous objectives. The loss transformation controls loss-dependent gradient scaling, while a U-Net generator supplies a spatially coherent texture and a hull-aligned application function accommodates target geometry without explicit Expectation over Transformation (EoT) sampling. …

Deep Learning Approach For Microwave Imaging Based On Deep Convolutional Asymmetric Encoder-Decoder Structure And Physics-Induced Loss, He Ming Yao, Shiji Song, Michael Kwok Po Ng, Lijun Jiang

Electrical and Computer Engineering Faculty Research & Creative Works

In this paper, we introduce an innovative deep learning (DL) methodology designed for real-time quantitative microwave imaging (MWI). Our approach is centered around the utilization of a deep convolutional asymmetric encoder-decoder structure (DCAEDS), which requires only a single-frequency far-field measurement of the electromagnetic (EM) scattered field as input and subsequently predicts the contrasts (permittivities) of the target materials. During the offline training process, we incorporate an EM forward solver specifically crafted to compute the EM scattered field generated by the predicted target contrasts (permittivities) produced by the DCAEDS. The DCAEDS is seamlessly integrated with this EM forward solver to optimize …

Stabilized Multi-Objective Optimization For Camouflage Attack In Remote Sensing, Omid Rajabi Rostami, Kazi Aminul Islam, Liuwan Zhu, Rui Ning, Chunsheng Xin, Hongyi Wu, Jiang Li

Electrical & Computer Engineering Faculty Publications

We investigate the vulnerability of multi-task maritime surveillance systems in which object detection and semantic segmentation operate concurrently. We propose Stabilized Multi-Objective Optimization (SMO), a framework that jointly targets Mask R-CNN and U-Net with a single universal adversarial texture in a digital white-box setting, with additional cross-model transfer evaluation. SMO combines a logarithmic-inversion loss transformation, feature inconsistency, and a systematic comparison of six optimization strategies for seven heterogeneous objectives. The loss transformation controls loss-dependent gradient scaling, while a U-Net generator supplies a spatially coherent texture and a hull-aligned application function accommodates target geometry without explicit Expectation over Transformation (EoT) sampling. …

Digital Twin Technologies For Battery Systems: Advancements, Applications, And Future Directions, Seyed Saeed Madani, Yasmin Shabeer, Michael Fowler, Satyam Panchal, Carlos Ziebert, Hicham Chaoui, François Allard

Electrical & Computer Engineering Faculty Publications

The relationships among deep learning, edge computing, artificial intelligence (AI), and the most recent advancements in digital twin (DT) technology for battery energy storage systems are discussed in this paper. The study highlights the need for improved cloud-edge coordination, AI model development, and stronger cybersecurity features by demonstrating real-world applications of digital twin technology in electric vehicles (EVs), aircraft, and grid storage. It also described DT-based structures for fault detection, real-time monitoring, and optimization through standardization and battery management system (BMS) fusion. Because DT-based solutions for distributed energy resources (DERs) offer improved energy management systems, various studies have been conducted …

Skeleton-Based Human Action Recognition Using Spatio-Temporal Latent Features With A Gcn Model, Avazjon Marakhimov, Kabul Khudaybergenov, Mominov Zakhriddin

Chemical Technology, Control and Management

Owing to its resilience to visual noise and viewpoint variations, skeleton-based analysis has become a cornerstone of human action recognition research. Despite its practical significance, existing methodologies often suffer from a reliance on single-stream skeletal representations, which fail to encompass the full complexity of action features. This study introduces Latent Features for Human Action Recognition (LFHAR), a novel architecture designed to overcome these limitations by utilizing diverse spatio-temporal latent representations for improved feature extraction. The approach applies graph-based transformations to individual skeletal frames in temporal sequences, then arranges the derived graph features into spatio-temporal matrices. Evaluation of standard datasets demonstrates …

An Audio Data-Driven Roadway Digital Twin And Its Underlying Framework For A Digitized Transportation Construction Environment, Anisha Deria, Pedro J. Chacon Dominguez, Yong-Cheol Lee, Jin W. Choi

Michigan Tech Publications

The increasing need to build and maintain transportation systems has led project managers to manage multiple projects simultaneously. Roadway projects often entail several miles of job site, making it difficult to keep track of progress and maintenance activities. To improve the situation, this study proposes an audio data-driven roadway digital twin framework for real-time and remote monitoring of construction projects. The latent characteristics of a digital twin required for establishing a digitized work environment were investigated. As a primary method of seamlessly linking virtual and physical environments, audio data classified and analyzed by deep neural network (DNN) has been employed …

Lstm Network-Based Scheme For Automatic Characterization Of Power Quality Disturbances, Akram Elmitwally, Mohamed Nader

Mansoura Engineering Journal

Recognition of power quality (PQ) troubles is a critical task in the electrical power industry. Most previous works solve the classification problem using separate feature extraction phase and classification phase. Each phase has its own techniques, and consumes a computation time. This study proposes to utilize the long short-term memory (LSTM) network as a deep learning model to classify the PQ events in one shot. The LSTM network uses its particular processing to classify a PQ event signal directly by reading its time-sequence data. Then, a dedicated post-classification algorithm (PCA) extracts start time, end time, duration, amplitude, and total harmonic …

A Feature-Free Deep Learning Approach For Midair Hand Gesture Recognition From Surface Electromyogram (Semg) Data, Yasir Altaf, Abdul Wahid, Mudasir Manzoor Kirmani

Turkish Journal of Electrical Engineering and Computer Sciences

Midair hand gesture recognition plays a crucial role in applications such as sign language recognition and human-computer interaction, particularly for supporting individuals with partial or complete hearing loss. However, recognizing gestures in midair remains challenging due to the rapid and complex nature of hand movements. To address this, noninvasive techniques like surface electromyography (sEMG)—which captures muscle activity through sensors placed on the skin—have gained attention. sEMG provides rich time-series data that reflect both spatial and temporal muscle dynamics. In this study, we propose a deep learning architecture that combines convolutional neural networks (CNNs) and recurrent neural networks (RNNs) to classify …

Design Optimization And Scaling Of Coreless Afpm Machines Using Hybrid Fea-Based Differential Evolution And Machine Learning, Matin Vatani, David R. Stewart, Donovin D. Lewis, Dan M. Ionel

Electrical and Computer Engineering Graduate Research

This paper presents a machine learning (ML) based design framework for the fast and accurate optimization of coreless axial flux permanent magnet (AFPM) machines. Although the absence of magnetic cores eliminates material nonlinearity, the design process remains highly nonlinear due to the complex influence of geometric parameters. To overcome the computational challenges of finite element analysis (FEA)-based optimization, a series of multi-objective differential evolution (MODE) optimizations were conducted across various machine sizes at constant power output. The resulting design data was used to train an artificial neural network (ANN), enabling rapid prediction of machine performance without the need for repeated …

Application Of Neural Networks For Intelligent Processing Of Sensor Signals In The Control Of Technological Process Parameters, N.R. Yusupbekov, Yu.Sh. Avazov, G.Kh. Rashidov

Chemical Technology, Control and Management

This scientific article investigates the problem of analyzing technological process parameters in the fields of chemistry, energy, and metallurgy based on sensor data and applying intelligent signal processing methods. The main objective is to evaluate the effectiveness of artificial intelligence and deep learning models for intelligent analysis, forecasting, and anomaly detection of data obtained from sensors. Time-series data collected from industrial sensors were analyzed using LSTM (Long Short-Term Memory) and Autoencoder neural networks, as well as the Kalman filter. At the first stage of the study, sensor signals were denoised and their true state was estimated using the Kalman filter. …

Evaluation Of Deep Learning Techniques In Road Sign Recognition, Latafat Abbas Gardashova, Haji Fakhraddin Hajiyev

Chemical Technology, Control and Management

Deep learning has transformed the computer vision field and greatly improved the performance and efficiency of road sign recognition systems. This research compares different deep learning methods, such as Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and hybrid models, in terms of their ability to effectively detect and classify road signs under various conditions. The study compares performance measures such as accuracy, processing speed, and robustness to environmental conditions like low lighting, occlusion, and adverse weather. The results show that CNN-based methods, especially those with transfer learning and ensemble techniques, have better performance in real-time scenarios. Problems like computational …

An Audio Data-Driven Roadway Digital Twin And Its Underlying Framework For A Digitized Transportation Construction Environment, Anisha Deria, Pedro J. Chacon Dominguez, Yong-Cheol Lee, Jin W. Choi

Michigan Tech Publications

The increasing need to build and maintain transportation systems has led project managers to manage multiple projects simultaneously. Roadway projects often entail several miles of job site, making it difficult to keep track of progress and maintenance activities. To improve the situation, this study proposes an audio data-driven roadway digital twin framework for real-time and remote monitoring of construction projects. The latent characteristics of a digital twin required for establishing a digitized work environment were investigated. As a primary method of seamlessly linking virtual and physical environments, audio data classified and analyzed by deep neural network (DNN) has been employed …

A Deep Learning Approach For Semantic Segmentation And Its Application On Ctc., Samir Farag Harb

Electronic Theses and Dissertations

This dissertation explores the modeling and analysis of medical images, focusing on the intricate task of colon segmentation and subsequent 3D reconstruction, which are critical steps in Computed Tomography Colonography (CTC) systems. The primary objective of this research is to develop precise segmentation approaches to enhance the accuracy of colon identification and reconstruction from abdominal CT scans. Three distinct segmentation approaches are proposed and evaluated: a Markov Random Field (MRF)-based approach, a convolutional neural network (CNN)-based deep learning (DL) approach, and a sequential episodic training with dual contrastive learning Approach (G-SET-DCL) that has a flavor of few-shot learning (FSL). To …

A Deep-Learning-Based Dehazing Framework For Non-Homogenous Scenes, Shimaa Mohammed Abd Elghany, Doaa A. Altantawy, Hossam El-Din Moustafa Moustafa

Mansoura Engineering Journal

The advancement of single-image dehazing techniques has been rapid in recent years. Several existing algorithms that are based on deep learning have shown remarkable efficiency for dealing with homogeneous hazing-free issues, but convolutional neural networks (CNNS) frequently fail on non-homogeneous dehazing datasets. Meanwhile, dehaze results from dense haze regions are often blurry because the information of these regions is typically unknown and difficult to estimate. To address these issues, an efficient image enhancement dehazing algorithm that utilizes deep learning techniques, and a non-uniform atmospheric scattering model had been proposed. Unlike the majority of existing dehazing methods, the medium transmission function …

الأمن السيبراني والذكاء الاصطناعي: حلول لإدارة أزمات البنية التحتية الرقمية, عبدالله سعد الغامدي

Journal of the Association of Arab Universities for Research in Higher Education مجلة اتحاد الجامعات العربية للبحوث في التعليم العالي

في ظل التحول الرقمي المتسارع، أصبحت إدارة الأزمات التقنية تحديًا استراتيجيًا يستوجب تبني حلول مبتكرة للحفاظ على استمرارية الأعمال وحماية البنية التحتية الرقمية. ناقشت هذه الورقة دور الأمن السيبراني والذكاء الاصطناعي في تعزيز قدرات المنظمات والجهات على التنبؤ بالأزمات والاستجابة لها بفعالية ، وتعتمد على منهجية تحليلية تجمع بين دراسة الحالات الواقعية وتحليل البيانات باستخدام تقنيات التعلم العميق Deep Learning ونظم الأمن السيبراني المتقدمة مثل SIEM وSOAR ومدى الاستفادة من دمج هذه التقنيات لتحسين زمن الاستجابة وتقليل معدل الهجمات الناجحة، مع التدليل على أمثلة من المملكة العربية السعودية والتي سجلت أكثر من 38 مليون محاولة هجوم سيبراني في عام 2024. …