Physical Sciences and Mathematics Commons^™

Deep Learning Style Transfer For Enhanced Smoke Plume Visibility: A Standardized False Color Composite (Sfcc) In Gems Satellite Imagery, Yemin Jeong, Seung Hee Kim, Menas Kafatos, Jeong-Ah Yu, Kyoung-Hee Sung, Seung-Yeon Kim, Goo Kim, Jae-Jin Kim, Yangwon Lee

Institute for ECHO Articles and Research

Wildfire smoke visualization using geostationary satellite imagery is essential for real-time monitoring and atmospheric analysis; however, inconsistencies in color tone across Geostationary Environment Monitoring Spectrometer (GEMS) images hinder reliable interpretation and model training. This study proposes a Standardized False Color Composite (SFCC) framework based on deep learning style transfer to enhance the visual consistency and interpretability of wildfire smoke scenes. Four tone-standardization methods were compared: the statistical Empirical Cumulative Distribution Function (ECDF) correction and three neural approaches—ReHistoGAN, StyTr2, and Style Injection Diffusion Model (SI-DM). Each model was evaluated visually and quantitatively using six metrics (SSIM, LPIPS, FID, histogram similarity, ArtFID, …

Mapping Post-Rainfall Recovery In Arid Regions Using A Hierarchical U-Net, Xin Hong

All Works

The United Arab Emirates (UAE) experienced an extreme rainfall event between April 15 and 17, 2024, and that resulted in severe flooding in its coastal regions. Dubai was among the most affected regions. This study applies a hierarchical deep learning model on PlanetScope imagery to detect flood inundation, quantify flood extent by land cover, and examine short-term recovery dynamics. While earlier work detailed the methodological development of a hierarchical U-Net model (Hong et al., in press), here we emphasize its application for monitoring resilience trajectories in an arid urban environment. Results show that approximately 22 km² of land was …

Spatio-Temporal Swin Transformer-Based Flow-Solid Coupling Interaction Sequence Image Prediction Network, Changjun Zou, Zhiyu Ge, Chenxi Zhong

Journal of System Simulation

Abstract: To address limitations in modeling long-term dependencies and multi-scale features in fluidstructure interaction scenarios, a spatiotemporal deep learning model (SwinLSTM) integrating ConvLSTM and Swin Transformer is proposed. The model employs a gated spatiotemporal attention mechanism that dynamically embeds Swin Transformer's window-based multi-head self-attention into ConvLSTM's output gate, enabling adaptive temporal-spatial feature coupling, and designs a multi-level ConvLSTM framework to hierarchically capture complex spatiotemporal correlations. Experiments on a self-built fluid-interaction dataset show that our method achieves the highest PSNR and leading SSIM scores, with superior performance in preserving vortex details and boundary consistency. This work provides an efficient solution …

A Robust Deep Learning Ensemble Framework For Waterbody Detection Using High-Resolution X-Band Sar Under Data-Constrained Conditions, Soyeon Choi, Seung Hee Kim, Son V. Nghiem, Menas Kafatos, Minha Choi, Jinsoo Kim, Yangwon Lee

Institute for ECHO Articles and Research

Accurate delineation of inland waterbodies is critical for applications such as hydrological monitoring, disaster response preparedness and response, and environmental management. While optical satellite imagery is hindered by cloud cover or low-light conditions, Synthetic Aperture Radar (SAR) provides consistent surface observations regardless of weather or illumination. This study introduces a deep learning-based ensemble framework for precise inland waterbody detection using high-resolution X-band Capella SAR imagery. To improve the discrimination of water from spectrally similar non-water surfaces (e.g., roads and urban structures), an 8-channel input configuration was developed by incorporating auxiliary geospatial features such as height above nearest drainage (HAND), slope, …

Deep Learning-Based Co-Current Upward Gas-Liquid Two-Phase Flow Regime Identification In An Annular Conduit, Joshua Robert Macomber

Graduate Theses, Dissertations, and Problem Reports (ETD)

Flow regime identification in co-current upward gas-liquid flow through annular conduits remains a significant challenge in petroleum engineering, with major safety and operational implications. It is also important across industries involving the transport of multiphase fluids. Misidentifying flow regimes can introduce major operational risk, yet regime boundaries in annular gas-liquid flow are often visually complex and context dependent.

The objective of this study was to evaluate the utility of convolutional neural network (CNN) classifiers for flow regime identification. The CNN was trained using annular flow image dataset published by Texas A&M University. The dataset consists of approximately 947 RGB images …

Multi-Grade Deep Learning, Yuesheng Xu

Mathematics & Statistics Faculty Publications

Deep learning requires solving a nonconvex optimization problem of a large size to learn a deep neural network (DNN). The current deep learning model is of a single-grade, that is, it trains a DNN end-to-end, by solving a single nonconvex optimization problem. When the layer number of the neural network is large, it is computationally challenging to carry out such a task efficiently. The complexity of the task comes from learning all weight matrices and bias vectors from one single nonconvex optimization problem of a large size. Inspired by the human education process which arranges learning in grades, we …

Deep Learning-Based Quantification Of Tall Fescue Abundance In Pastures, Rose E. Binkley, Samuel R. Revolinski, Echo Elizabeth Gotsick, Ray Smith, Zeya Wang, Katsutoshi Mizuta

Plant and Soil Sciences Faculty Publications

Accurate and rapid measurement of tall fescue abundance is essential for efficient forage management and mitigating livestock exposure to potential endophyte-related toxicity. Traditional visual estimation methods are labor-intensive and are subject to change depending on the observer doing the calculations, which limits their scalability and consistency. This study explores the application of deep learning techniques to automate and improve the classification of tall fescue abundance across pasture systems in Kentucky. Ground-truth abundance classes were evaluated using one of the traditional methods with occupancy grid and compared against estimates derived from red-green-blue images. Two convolutional neural network architectures, YouOnlyLookOnce (YOLO) and …

Ai For Life Sciences: From Geometric Protein Modeling To Multimodal Drug Design, Feng Jiang

Computer Science and Engineering Dissertations

Predicting biomolecular interactions, from immune recognition to drug–target binding, is a central problem in the life sciences and computational drug discovery. Deep learning has advanced this area, yet three challenges persist: the topology of large, highly imbalanced interaction networks; structural noise in computationally predicted protein models; and the integration of multimodal information such as functional text and taxonomic annotations. This dissertation develops a coherent set of models spanning immune complex prediction and small-molecule drug design: graph learning that addresses network topology and severe class imbalance; a noise-tolerant method that fuses predicted structures with evolutionary sequence features; and multimodal representation learning …

A Deep Learning Approach For Mapping Shrubs, Wet Tundra And Surface Water In Arctic Tundra With Very High Resolution Satellite Imagery, Darko Radakovic

Theses, Dissertations and Culminating Projects

Arctic shrub expansion threatens to accelerate permafrost thaw through complex feedbacks, yet whether shrubs primarily indicate or drive degradation remains unresolved. This dissertation integrates deep learning analysis of two decades of satellite imagery with LiDAR canopy structure and radar soil moisture data to reveal that shrubs play a dual role: young, expanding shrubs signal active permafrost thaw, while mature, tall shrubs stabilize underlying permafrost through insulation. By demonstrating that vertical canopy structure predicts thaw depth better than cover extent alone, this work establishes a scalable framework for monitoring permafrost vulnerability across the rapidly changing Arctic. Arctic shrub expansion is accelerating …

Toward Interpretable Multi-Omics Multimodal Biomedical Artificial Intelligence, Yanjun Lyu

Computer Science and Engineering Dissertations

The complexity of human disease arises from biological processes that unfold across multiple scales, from molecular variation through cellular function, tissue organisation, brain phenotypes, each of which is associated with distinct measurement modalities, regularities, and characteristic. Contemporary biomedical artificial intelligence has brought the opportunity to reveal the complexity with in; however, its methodological default, in which models are trained on most readily available modality, does not adequately engage with the multi-scale connected structure by which biological meaning is constituted. The research area of multi-omics and multi-modal AI for biomedicine remains at an early exploratory stage, and the work presented in …

Forecasting Precipitation In Cuba Using Graph Based Deep Learning, Taufiqul Islam

Earth & Environmental Sciences Theses

Daily precipitation forecasting remained a challenging problem in regions characterized by strong spatial heterogeneity, nonlinear atmospheric dynamics, and intermittent rainfall behavior. Cuba represented a particularly complex case due to the combined influence of tropical cyclones, easterly waves, mesoscale convective systems, and orographic effects, which produced highly variable rainfall patterns in both space and time. Conventional statistical and machine-learning models typically treated stations independently and therefore overlooked spatial dependencies that strongly influenced rainfall variability across the island.

This study developed a spatiotemporal deep-learning framework for daily precipitation forecasting across 40 spatial nodes in Cuba using data from 1979 to 2023. The …

A Hybrid Cnn-Lstm Surrogate Model For Hyper-Resolution Spatiotemporal Flood Forecasting In Norfolk, Virginia, Yidi Wang, Jonathan L. Goodall, Chetan Kumar, Diana Mcspadden, Sergio A. Barbosa, Binata Roy, Ali Shahabi, Navid Tahvildari

Data Science Faculty Publications

Study region

Norfolk, Virginia, United States

Study focus

Accurate and timely flood forecasting is essential for enhancing resilience in coastal urban areas in the context of increasing frequency and intensity of rainfall, sea level rise and urbanization. This study presents a hybrid deep learning-based surrogate model that integrates Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks to enable real-time spatiotemporal flood forecasting. The model leverages CNN to capture spatial features from inputs such as elevation and Topographic Wetness Index (TWI), while LSTM processes time-series inputs of rainfall and tide data to capture temporal features.

New hydrologic insights for …

Hybrid Model For Phishing Website Detection Using Transfer Learning, Atul Dubal, Mansi Subhedar, Santosh Dhamala, Manasi Patil

ASEAN Journal on Science and Technology for Development

The rapid digitization of human activities has intensified reliance on internet-based platforms, creating fertile ground for cybercriminal exploits such as phishing. Despite advancements in detection mechanisms, phishing attacks continue to evolve, leveraging sophisticated visual mimicry to deceive users. This paper proposes a robust vision-based phishing detection system using ensemble deep learning to analyse webpage screenshots. The framework integrates transfer learning with pre-trained VGG16 and DenseNet121 models, extracting complementary low-level texture features (edges, gradients) and high-level hierarchical patterns (logos, layouts). These features are fused through a custom classifier with dropout regularization to mitigate overfitting. A balanced dataset of 3,000 webpage screenshots …

Attention-Based Geo–Textual Fusion Network For Disaster Risk Prediction, Mohammad Shafat Ahsan, Mst Sanjida Alam, Syed Sajjad Ahmed, Md Tanzimul Islam, Hashibul Ahsan Shoaib, M.F. Mridha, Md. Jakir Hossen

Student Publications [Scholarly]

Natural disasters pose recurring threats to human life and infrastructure, demanding intelligent systems that can process heterogeneous data streams and provide actionable insights in real time. Existing approaches often treat textual signals from social media and emergency communications separately from spatial hazard attributes, limiting their effectiveness in capturing the full complexity of evolving crises. This paper proposes an AI-driven geo–textual intelligence framework that integrates disaster-related text with GIS-based hazard features for real-time risk prediction and evacuation planning. The framework employs contextual text encoders and a neural GIS encoder, fused through an attention mechanism that dynamically weights cross-modal signals. Experiments on …

Machine Learning For Wearable Sensor-Based Human Movement Rehabilitation: A Five-Year Systematic Review, Yassine Benachour, Farid Flitti, Lina Maloukh, Aicha Beya Far, Elhocine Boutellaa, Mohamed Bentoumi, Marwa Chendeb El Rai, Nour Aburaed, Khaled Ali, Moez Rehman, Sultan Mosleh, Rania Dghaim, Sadok Bouamama

All Works

Wearable-sensor-based human movement analysis is an increasingly important component of digital health and rehabilitation, enabling objective monitoring and data-driven personalization of therapy. In parallel, machine learning (ML) methods have rapidly expanded for interpreting multimodal movement signals, yet the evidence base remains heterogeneous and difficult to benchmark. This PRISMA-guided systematic review synthesizes recent ML approaches for wearable human motion analysis in rehabilitation-oriented health applications. We searched IEEE Xplore, PubMed, and Scopus for English-language studies published from 2021 to 2025 and extracted information on sensor modalities, ML task formulations and model families, dataset characteristics, validation protocols, and reported performance metrics, together with …

Adaptive Self-Attention For Enhanced Segmentation Of Adult Gliomas In Multi-Modal Mri, Evan P. Savaria, Jiangwen Sun

Computer Science Faculty Publications

Every year there are an estimated 80,000–90,000 new glioma cases, highlighting the need for reliable imaging-based decision support. Although deep learning has improved tumor sub-region segmentation, many state-of-the-art models fail to fully capture complementary information across T1, T1Gd, T2, and FLAIR MRI modalities and often operate as “black boxes,” limiting physician trust when precise delineation is critical for surgical planning, radiation targeting, and treatment monitoring. To address these limitations, we propose AIMS, an Adaptive Integrated Multi-Modal Segmentation framework that maintains modality-specific feature streams and employs adaptive self-attention within a hierarchical CNN-Transformer architecture to prioritize and fuse multi-modal MRI features. We …

Attention-Based Multi-Omics Fusion For Drug Synergy Prediction, Kusal Debnath, Pratip Rana, Preetam Ghosh

Computer Science Faculty Publications

Drug combination therapy in disease management gained popularity in the last few decades. Computational modeling of such combinations is an active area of research in the drug discovery domain. While earlier approaches solely emphasized on the structural features of participating drugs for designing synergistic models, they lack other crucial factors directly linked with drug administration - omics expressions. As differential omics expression is a downstream consequence of the administered drug combinations, utilizing such expressions while designing synergistic models promises robust and dynamic modeling. In this work, we propose SynergyLM that fuses multi-omics features with drug embeddings to build an omics-aware …

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. …

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 …

Multimodal Machine Learning For Alzheimer's Disease Classification Using Adni Biomarker Fusion, Hesameddin Mostaghimi, Hamid R. Okhravi, Bahar Niknejad, Daniel A. Cohen, Michel A. Audette, Alzheimer's Disease Neuroimaging Initiative

Electrical & Computer Engineering Faculty Publications

Despite ongoing advances, accurate diagnosis of Alzheimer’s disease (AD) remains challenging due to its multifactorial nature, comorbidities, and clinical heterogeneity. Accordingly, approaches that combine multimodal data may improve AD classification by integrating complementary information. To investigate this, we evaluated classification performance using a preprocessed ADNI-3 dataset comprising a shared set of clinical/cognitive features along with four imaging modality-based cohorts: trimodal (MRI + amyloid PET + tau PET), MRI + amyloid PET, MRI + tau PET, and MRI-only. We trained a range of supervised machine learning (ML) and deep learning (DL) classifiers using stratified five-fold cross-validation and evaluated performance using accuracy, …

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 …

Srgan-Based Deep Learning Framework For Wind Turbine Damage Detection From Sentinel-2 Imagery, Kübra Çakir, Onur Elma, Murat Kuzlu

Engineering Technology Faculty Publications

The operational reliability of wind turbines is critical for sustainable energy production in smart grids. This study proposes a remote monitoring approach using perceptually enhanced satellite imagery. Sentinel-2 multispectral data (10 m resolution) has been processed with a Super-Resolution Generative Adversarial Network (SRGAN) to improve visual quality to a perceptual resolution of 30 cm. Although true spatial refinement is not achieved, the sharper structural details enhance classification accuracy. The data set comprises 15,000 images—10,000 SRGAN-enhanced and 5000 augmented through rotation, zoom in, increasing brightness, noise addition, and blurring. A custom Convolutional Neural Network (CNN) has been trained to classify turbines …

Computational Methods For Single-Cell And Multi-Omic Data Integration And Regulatory Network Inference, Jianlan Ren

Dissertations

Single-cell and multi-omic technologies have transformed the dissection of cellular heterogeneity and regulatory dynamics in health and disease. However, the high dimensionality, technical variability, and biological complexity of these datasets present significant challenges for integration, annotation, and interpretation. In this dissertation, a suite of computational approaches is introduced to address key problems in single-cell and multi-omic data analysis through model-based innovations and applied statistical frameworks.

First, a constrained deep learning framework for single-cell data integration, label transfer, and clustering is proposed. By incorporating biologically motivated constraints into the training process, robust performance is achieved across simulated and benchmark datasets spanning …

Enhanced Generative Convolutional Networks: A Hybrid Algorithm For Refinement Video Classification, Dalal Thair Mahjoub, Hala Bahjat Abdulwahab, Kesra Nermend

Journal of Soft Computing and Computer Applications

Video classification is a vital area of research due to the growing volume of video content in various applications. Accurate category across various resolutions poses challenges, which include adapting to scaling, resizing, and compression. Therefore, this paper introduces an innovative Generative Convolutional Network (GCN) set of rules tailored for multi-resolution video classes. The proposed GCN model utilizes Convolutional Neural Networks (CNNs) combined with generative modeling to enhance the extraction of functions across varying video resolutions, which is crucial for maintaining class robustness in the face of common video adjustments, such as scaling, resizing, and compression. In contrast, traditional fashions frequently …

Review Of Video Steganography By Using Deep Learning Methods: Datasets, Techniques, And Evaluations, Noor Fahem Sahib, Soukaena Hassan Hashem, Ekhlas Falih Naser

Journal of Soft Computing and Computer Applications

The growing prevalence of cyber threats, including fraud and attacks, has intensified the demand for secure methods of safeguarding confidential information exchanged between users. As telecommunications increasingly rely on multimedia data, video steganography has become a prominent technique to address these concerns. By embedding sensitive data within video files, this approach enhances protection against unauthorized access and common internet-based attacks, offering a robust layer of security in an era of escalating digital risks. With the introduction of Deep Learning (DL) steganography methods recently, video steganography can be defined as a rapidly developing subject within information security. This study provides a …

Research On Infrared And Visible Light Fusion Method Based On Resnet-50 And Laplacian Filtering, Xiao Wang, Xiangyang Li, Feng Liang, Zhili Zhang

Journal of System Simulation

Abstract: In order to solve the problem that existing infrared and visible light image fusion techniques often suffer from artifacts caused by insufficient contrast, spectral distortion, and high computational complexity, a fusion framework based on ResNet-50 and Laplacian filtering was proposed. ResNet-50 was used to extract shallow and deep features, followed by multi-scale feature fusion. Laplacian filtering was applied to optimize feature information, and an automatic discriminator was introduced to further improve the fusion effect. Simulation results show that, compared with comparison algorithms, the proposed method achieves an average increase of 2.71% and 2.16% in information entropy, 5.98% and …

Coal Body Structure Identification Method Based On Bayesian-Optimized Cnn-Bilstm-Attention, Bian Huiyuan, Ji Jiajun, Duan Chaowei, Zhou Jun, Li Kun, Ma Yuhan

Coal Geology & Exploration

Background Coal-bearing basins contain primary and tectonically deformed coals due to multistage tectonic deformations. However, the gas-bearing properties of coal seams differ significantly due to varying pore and fracture densities, permeability, and mechanical properties. This makes coal structure assessment critical to coalbed methane (CBM) exploration and production. Objective and Method To enhance the accuracy and intelligence of coal structure identification, this study constructed a CNN-BiLSTM-Attention hybrid model that integrated a Bayesian optimization strategy. This model allowed for efficient fusion and representation of multi-scale log data by combining the local feature extraction capability of the convolutional neural network (CNN), the temporal …

Construction And Application Of Knowledge Graph For Quality Management In Bridge Pile Engineering, Fang Xiaofeng, Dong Runhao, Gu Yanke, Pan Yanran

Journal of China & Foreign Highway

To enhance the efficiency of quality management in bridge pile foundation construction,this study constructed a knowledge graph applicable to the construction field of bridge pile foundation engineering to enable systematic representation and intelligent organization of knowledge.A methodology combining top-down design and bottom-up design was adopted to develop a framework for constructing a knowledge graph for the quality management of bridge pile foundation construction that encompasses both the schema layer and the data layer.The schema layer was established through ontology modeling,clarifying the concept categories,hierarchical structure,and their attribute relationships.The data layer employed a bidirectional long short-term memory (BiLSTM ) network integrated with …

Bridge Damage Detection And Bim Localization Methods Based On Image Recognition, Li Yu, Guo Hongjun

Journal of China & Foreign Highway

To overcome insufficient information of 2D detection data in traditional bridge maintenance,which hinders precise decision-making,this study proposed an automated method based on deep learning and structure from motion (SfM ) technology,which realized the complete process from image recognition to the accurate mapping of damage information in a building information model (BIM ).First,the YOLOv 8 deep learning model was used to automatically detect bridge surface damage.Second,the SfM technology was applied for the local 3D reconstruction of the damage area and to determine the 3D coordinates of the damage.Then,the least squares method was used to align the local coordinate system with the …

Multi-Satellite Image Matching And Deep Learning Segmentation For Detection Of Daytime Sea Fog Using Gk2a Ami And Gk2b Goci-Ii, Jonggu Kang, Hiroyuki Miyazaki, Seung Hee Kim, Menas Kafatos, Daesun Kim, Jinsoo Kim, Yangwon Lee

Institute for ECHO Articles and Research

Traditionally, sea fog detection technologies have relied primarily on in situ observations. However, point-based observations suffer from limitations in extensive monitoring in marine environments due to the scarcity of observation stations and the limited nature of measurement data. Satellites effectively address these issues by covering vast areas and operating across multiple spectral channels, enabling precise detection and monitoring of sea fog. Despite the increasing adoption of deep learning in this field, achieving further improvements in accuracy and reliability necessitates the simultaneous use of multiple satellite datasets rather than relying on a single source. Therefore, this study aims to achieve higher …