Search Results (65)

Ultra-wide field (UWF) fundus image classification is an important part of the entire process of medical screening and decision support. However, the discrimination of various retinal disease classes is difficult due to the similarity between classes, class imbalance, and the indeterminacy of visual patterns. In our research, an explainable neutrosophic knowledge distillation (NKD) model for UWF fundus image classification is proposed. In the proposed model, the teacher model is a ResNet50 architecture that provides the student model with supervisory information that is aware of the indeterminacy of predictions. The proposed model combines the CLAHE-based preprocessing method with the neutrosophic distillation method to enable the student model to learn from the hard labels as well as the teacher model. The experimental results were evaluated using the 5-fold cross-validation method with an additional hold-out evaluation. The experimental results show that the proposed NKD model has a mean accuracy of 84.00%, specificity of 97.33%, precision of 84.99%, recall of 84.00%, and F1-score of 84.02%. The proposed model also has an accuracy of 87.86% with specificity of 97.48% and AUC of 97.48% in the ablation-based full model evaluation. It outperformed classical machine learning baselines based on Local Binary Patterns (LBP), Histogram of Oriented Gradients (HOG), and LBP + HOG features with Support Vector Machines (SVM) classifiers, as well as the baseline student, fuzzy student, and teacher Convolutional Neural Network (CNN) models. For improved interpretability, the Grad-CAM++ technique was used to analyze the proposed NKD model. This analysis showed that the network attended to relevant retinal regions during classification. These results suggest that the proposed model can be an effective tool for UWF fundus image classification. Full article

Extreme class imbalance is a persistent obstacle for machine learning-driven intrusion detection, as rare but high-impact cyberattacks occur far less frequently than benign traffic in training data. In many real-world cybersecurity datasets, this imbalance becomes extreme, with certain attack types containing a handful of samples, effectively placing the problem in a few-shot learning regime. This paper presents a controlled benchmarking study of Generative Adversarial Network (GAN) objectives for synthesizing minority-class cyberattack data. Using the UWF-ZeekData22 network traffic dataset, each MITRE ATT&CK tactic is framed as a separate binary detection task, and tactic-specific GANs are trained solely on minority samples to generate synthetic attack records. Four widely used GAN variants—Vanilla GAN, Conditional GAN (cGAN), Wasserstein GAN (WGAN), and Wasserstein GAN with Gradient Penalty (WGAN-GP)—are compared under unified training steps and fixed augmentation conditions. The utility of generated data is assessed by evaluating downstream detection performance using five traditional classifiers: Logistic Regression, Support Vector Machine, k-Nearest Neighbors, Decision Tree, and Random Forest. The results indicate that GAN augmentation generally strengthens minority-class detection across tactics and models, reducing false negatives and improving recall consistency, while not systematically harming majority-class performance. However, the effectiveness of each GAN objective varies significantly with data sparsity. Specifically, simpler adversarial objectives often outperform more complex architectures by preserving discriminative feature structure, while heavily regularized models may overly smooth minority-class distributions and reduce separability. Wasserstein-based objectives provide improved training stability, but additional regularization does not consistently translate to better detection performance. Overall, the results demonstrate that in extreme-imbalance settings, GAN effectiveness is governed more by data sparsity and structure preservation than by architectural complexity. These findings establish class-specific generative augmentation as a practical strategy for intrusion detection and provide empirical guidance for selecting appropriate GAN objectives for tabular cybersecurity data under highly imbalanced conditions. Full article

Generative adversarial networks (GANs) are increasingly applied to mitigate extreme class imbalance in intrusion detection systems, yet reported improvements often obscure role augmentation intensity and adversarial stability. This paper presents a controlled ablation study that isolates the impact of adversarial objective choice, augmentation ratio, and training duration on GAN-based minority data augmentation for highly imbalanced tabular cybersecurity data. Using the UWF-ZeekData22 dataset, nine MITRE ATT&CK tactic-versus-benign classification tasks are evaluated under augmentation ratios of 0.25 and 0.50 and training durations of 400 and 800 epochs. Four GAN variants—Vanilla GAN, Conditional GAN (cGAN), WGAN, and WGAN-GP—are assessed using stratified cross-validation and five classical classifiers representing diverse inductive biases. The results reveal consistent structural patterns. Moderate augmentation (r = 0.25) with controlled training (400 epochs) yields the most stable and reliable improvement in minority recall. Wasserstein-based objectives demonstrate superior stability under aggressive augmentation and prolonged training, while conditional GANs frequently exhibit recall collapse in ultra-sparse regimes. Increasing augmentation volume does not uniformly improve performance and may introduce distributional overlaps that degrade linear and margin-based classifiers. Tree-based classifiers remain largely invariant once sufficient minority density is achieved. These findings demonstrate that adversarial calibration is more important than architectural complexity for improving the detection of rare attacks. The study provides practical guidance for designing robust GAN-based augmentation pipelines under extreme cybersecurity class imbalance. Full article

Intrusion detection systems (IDS) often struggle to detect rare but high-impact attack behaviors due to severe class imbalance in real-world network traffic. This work proposes a class-specific GAN-based augmentation framework that explicitly targets sparsity in the minority-class in structured cybersecurity datasets. Unlike prior GAN-based approaches that employ global augmentation or anomaly-driven synthesis, separate Generative Adversarial Networks (GANs) are trained independently for each MITRE ATT&CK tactic using only real minority-class samples, enabling focused distribution learning without contamination from benign traffic. Using a relatively new network traffic dataset, UWF-ZeekData22, the proposed framework augments minority classes under conditions of extreme sample sparsity, where traditional classifiers and interpolation-based oversampling methods are ineffective or statistically unreliable. Five traditional classifiers—Logistic Regression, Support Vector Machine (SVM), k-Nearest Neighbors (KNN), Decision Tree, and Random Forest—are evaluated before and after augmentation using stratified 5-fold cross-validation. Experimental results show that class-specific GAN augmentation consistently improves recall and F1-score for rare attack tactics, with the largest gains observed under extreme sparsity where pre-augmentation evaluation was infeasible. Notably, false-negative rates are substantially reduced without degrading majority-class performance, demonstrating that the proposed approach enhances minority-class separability rather than inflating evaluation metrics. These findings demonstrate that class-specific GAN-based augmentation is a practical and robust data-level strategy for improving the detection of rare MITRE ATT&CK-aligned attack behaviors in machine-learning-based IDSs. Full article

Background: Ultra-widefield (UWF) images are frequently used for fundus examinations during medical screening. Optos^® generates pseudo-color images using only red and green lasers, which may reduce the visibility of retinal interface lesions. In contrast, Clarus™ incorporates blue light, suggesting potential superiority in epiretinal membrane (ERM) detection. Methods: This retrospective study included 233 patients (408 eyes; 816 UWF images per device) who underwent simultaneous Optos^® and Clarus™ imaging plus optical coherence tomography (OCT) at our institution from March to April 2019. Ten blinded ophthalmologists assessed only the UWF images for ERM presence or absence. Diagnosis was confirmed by fundus examination and OCT. McNemar’s test compared detection accuracy. Results: Clarus™ consistently outperformed Optos^®, with superior sensitivity [median 49% (range 42–70) vs. 14% (4–47); p = 0.002], correct judgment rate [85% (82–90) vs. 78% (44–88); p = 0.010], and lower unassessed rate [6% (2–13) vs. 13% (3–52); p = 0.002]. This superiority held across ERM stages, lens status, and ophthalmologist experience levels. Conclusions: This study demonstrated that Clarus™ significantly outperformed Optos^® in ERM detection accuracy. These results suggest that true-color UWF systems like Clarus™ may be more useful for macular screening in routine practice and health examinations. Full article

Diabetic macular edema (DME) is a leading cause of vision loss, and predicting patients’ response to anti-vascular endothelial growth factor (anti-VEGF) therapy remains a clinical challenge. In this study, we developed an interpretable deep learning model for treatment prediction and biomarker analysis. We retrospectively analyzed 402 eyes from 371 patients with DME. The proposed DME-Receptance Weighted Key Value (RWKV) integrates optical coherence tomography (OCT) and ultra-widefield (UWF) imaging using Causal Attention Learning (CAL), curriculum learning, and global completion (GC) loss to enhance microlesion detection and structural consistency. The model achieved a Dice coefficient of 71.91 ± 8.50% for OCT biomarker segmentation and an AUC of 84.36% for predicting anti-VEGF response, outperforming state-of-the-art methods. By mimicking clinical reasoning with multimodal integration, DME-RWKV demonstrated strong interpretability and robustness, providing a promising AI framework for precise and explainable prediction of anti-VEGF treatment outcomes in DME. Full article

This work focuses on finding frequent patterns in continuous flow network traffic Big Data using incremental frequent pattern mining. A newly created Zeek Conn Log MITRE ATT&CK framework labeled dataset, UWF-ZeekData24, generated using the Cyber Range at The University of West Florida, was used for this study. While FP-Growth is effective for static datasets, its standard implementation does not support incremental mining, which poses challenges for applications involving continuously growing data streams, such as network traffic logs. To overcome this limitation, a staged incremental FP-Growth approach is adopted for this work. The novelty of this work is in showing how incremental FP-Growth can be used efficiently on continuous flow network traffic, or streaming network traffic data, where no rebuild is necessary when new transactions are scanned and integrated. Incremental frequent pattern mining also generates feature subsets that are useful for understanding the nature of the individual attack tactics. Hence, a detailed understanding of the features or feature subsets of the seven different MITRE ATT&CK tactics is also presented. For example, the results indicate that core behavioral rules, such as those involving TCP protocols and service associations, emerge early and remain stable throughout later increments. The incremental FP-Growth framework provides a structured lens through which network behaviors can be observed and compared over time, supporting not only classification but also investigative use cases such as anomaly tracking and technique attribution. And finally, the results of this work, the frequent itemsets, will be useful for intrusion detection machine learning/artificial intelligence algorithms. Full article

We aimed to validate the feasibility of combining ultra-widefield (UWF) fundus photography with targeted swept-source optical coherence tomography (SS-OCT) for clinical decision-making regarding a prophylactic laser therapy. For this purpose we enrolled 119 patients (135 eyes) who, basis on fundus examination, were eligible for prophylactic photocoagulation of degenerative retinal lesions. Eyes were classified into two groups: (1) justified laser, when SS-OCT confirmed vitreoretinal traction and/or subretinal fluid beneath the neurosensory retina; and (2) non-justified laser, when SS-OCT did not confirm these criteria. Using this SS-OCT-guided UWF approach, we found that 25.1% of eyes that initially qualified for laser based on clinical examination did not meet the SS-OCT criteria. Patients in the justified laser group were significantly younger than those in the non-justified group. Horseshoe retinal tears, lattice degeneration and snail-track degenerations, multiple lesions, and lesions located in the far and mid-periphery were significantly more frequent in the justified laser group than in the non-justified group. By contrast, the prevalence of operculated holes, bilateral lesions, and degenerative lesions in patients with a retinal detachment in the fellow eye did not differ between groups. Our findings suggest the SS-OCT-guided UWF imaging may refine patient selection for prophylactic laser therapy. Full article

Objectives: The aim of this study was to determine which color imaging facilitated easier detection of the persistent avascular retina (PAR) in ultra-widefield (UWF) fundus imaging in children undergoing retinopathy of prematurity (ROP). Methods: A total of 20 eyes of 10 children aged between 6 and 9 who underwent diagnostic and therapeutic procedures for ROP were included. Fundus images were obtained using Optos confocal scanning laser ophthalmoscopy (cSLO; Optos PLC, Daytona, Dunfermline, UK). The images were divided and recorded into three groups as original imaging (composite), red reflectance imaging, and green reflectance imaging. These images were prepared as a slideshow for 10 ophthalmology specialists and they were surveyed to determine in which color imaging the peripheral avascular area was more easily detected. The results were evaluated. Results: The rate of detecting the PAR in green reflectance imaging by the participants included in the study was found to be statistically higher compared to other colors of imaging (composite 0.63 ± 0.09 (0.5–0.8), red 0.12 ± 0.05 (0.05–0.2), and green 0.94 ± 0.06 (0.85–1), p < 0.0001). All respondents reported that the boundaries of the peripheral avascular area were more clearly defined in the UWF (Optos PLC, Daytona, Dunfermline, UK) green reflectance imaging. Conclusions: Each color imaging used in UWF fundus imaging helps to visualize different layers of the retina. Our study showed that retinal vascular endings appear more distinct due to the lower penetration of the green laser into the choroidal vessels. Based on these findings, we believe that UWF fundus green reflectance imaging is more useful for detecting and monitoring PAR. Full article

As vehicle-centric perception struggles with occlusion and dense traffic, vehicle-infrastructure cooperative perception (VICP) offers a viable route to extend sensing coverage and robustness. This study proposes a feature-level VICP framework that fuses vehicle- and roadside-derived visual features via V2X communication. The model integrates four components: regional feature reconstruction (RFR) for transferring region-specific roadside cues, context-driven channel attention (CDCA) for channel recalibration, uncertainty-weighted fusion (UWF) for confidence-guided weighting, and point sampling voxel fusion (PSVF) for efficient alignment. Evaluated on the DAIR-V2X-C benchmark, our method consistently outperforms state-of-the-art feature-level fusion baselines, achieving improved ${AP}_{3D}$ and ${AP}_{BEV}$ (reported settings: 16.31% and 21.49%, respectively). Ablations show RFR provides the largest single-module gain +3.27% ${AP}_{3D}$ and +3.85% ${AP}_{BEV}$, UWF yields substantial robustness gains, and CDCA offers modest calibration benefits. The framework enhances occlusion handling and cross-view detection while reducing dependence on explicit camera calibration, supporting more generalizable cooperative perception. Full article

To address the gaps in cyber range survey research, this entry develops and applies a structured classification taxonomy to support the comparison, evaluation, and design of cyber ranges. The entry will address the following question: What are the objectives and key features of current cyber ranges, and how can they be classified into a comprehensive taxonomy? The entry synthesizes existing frameworks and analyzes and classifies a variety of documented cyber ranges to find similarities and gaps in the current classification methods. The findings indicate recurring design elements across ranges, persistent gaps in standardization, and demonstrate how the University of West Florida (UWF) Cyber Range exemplifies the taxonomy application in practice. The goal is to facilitate informed decision-making by cybersecurity professionals when choosing platforms and to support academic research in cybersecurity education. Pulling information from studies about other cyber ranges to compare with the UWF Cyber Range, this taxonomy aims to contribute to the documentation of cyber ranges by providing a clear understanding of the current cyber range landscape. Full article

Retinal breaks are critical lesions that can cause retinal detachment and vision loss if not detected and treated early. Automated, accurate delineation of retinal breaks in ultra-widefield fundus (UWF) images remains challenging. In this study, we developed and validated a deep learning segmentation model based on the PraNet architecture to localize retinal breaks in break-positive cases. We trained and evaluated the model using a dataset comprising 34,867 UWF images of 8083 cases. Performance was assessed using image-level segmentation metrics, including accuracy, precision, recall, Intersection over Union (IoU), dice score, and centroid distance score. The model achieved an accuracy of 0.996, precision of 0.635, recall of 0.756, IoU of 0.539, dice score of 0.652, and centroid distance score of 0.081. To our knowledge, this is the first study to present pixel-level segmentation of retinal breaks in UWF images using deep learning. The proposed PraNet-based model showed high accuracy and robust segmentation performance, highlighting its potential for clinical application. Full article

Data preprocessing is usually necessary before running most machine learning classifiers. This work compares three different preprocessing techniques, minimal preprocessing, Principal Components Analysis (PCA), and Linear Discriminant Analysis (LDA). The efficiency of these three preprocessing techniques is measured using the Support Vector Machine (SVM) classifier. Efficiency is measured in terms of statistical metrics such as accuracy, precision, recall, the F-1 measure, and AUROC. The preprocessing times and the classifier run times are also compared using the three differently preprocessed datasets. Finally, a comparison of performance timings on CPUs vs. GPUs with and without the MapReduce environment is performed. Two newly created Zeek Connection Log datasets, collected using the Security Onion 2 network security monitor and labeled using the MITRE ATT&CK framework, UWF-ZeekData22 and UWF-ZeekDataFall22, are used for this work. Results from this work show that binomial LDA, on average, performs the best in terms of statistical measures as well as timings using GPUs or MapReduce GPUs. Full article

This paper presents a comprehensive model for detecting and addressing concept drift in network security data using the Isolation Forest algorithm. The approach leverages Isolation Forest’s inherent ability to efficiently isolate anomalies in high-dimensional data, making it suitable for adapting to shifting data distributions in dynamic environments.Anomalies in network attack data may not occur in large numbers, so it is important to be able to detect anomalies even with small batch sizes. The novelty of this work lies in successfully detecting anomalies even with small batch sizes and identifying the point at which incremental retraining needs to be started. Triggering retraining early also keeps the model in sync with the latest data, reducing the chance for attacks to be successfully conducted. Our methodology implements an end-to-end workflow that continuously monitors incoming data and detects distribution changes using Isolation Forest, then manages model retraining using Random Forest to maintain optimal performance. We evaluate our approach using UWF-ZeekDataFall22, a newly created dataset that analyzes Zeek’s Connection Logs collected through Security Onion 2 network security monitor and labeled using the MITRE ATT&CK framework. Incremental as well as full retraining are analyzed using Random Forest. There was a steady increase in the model’s performance with incremental retraining and a positive impact on the model’s performance with full model retraining. Full article

Background/Objectives: This study evaluates whether ultrawide-field optical coherence tomography angiography (UWF-OCTA) can guide navigated laser therapy for non-perfused areas (NPAs) in branch retinal vein occlusion (BRVO). It further explores whether the laser spots can be accurately placed according to plan, considering that the retina is three-dimensional (3D), while UWF-OCTA provides two-dimensional (2D) images. Methods: UWF-OCTA images from three devices—VG200, Xephilio OCT-S1, and Bmizar—guided the treatments. These images were superimposed onto NAVILAS^® system images to guide NPA treatments. Pre-treatment planning was strategically designed to avoid normal and collateral vessels, with immediate post-laser OCTA and en face images assessing the efficacy of the laser spots in avoiding these vessels as planned. The accuracy of navigated laser therapy was further analyzed by comparing the intended laser locations with the actual spots. Results: All montaged OCTA images from the three devices were seamlessly integrated into the navigated laser system without registration errors. All patients received treatments targeting the NPAs as planned. However, not all collateral or normal vessels were successfully avoided by the laser spots. A further analysis revealed that the actual locations of the laser spots deviated slightly from the planned locations, particularly in the mid-periphery areas. Conclusions: UWF-OCTA-guided navigated laser photocoagulation is feasible and precise for treating NPAs in BRVO. Nonetheless, minor deviations between planned and actual locations were observed. This discrepancy, particularly important when treating diseases of the macular area, should be carefully considered when employing OCTA-guided navigated laser photocoagulation. Full article