Search Results (538)

Tea cultivation faces significant threats from red spider mite (RSM: Oligonychus coffeae) infestations, which reduce yields and economic viability in major tea-producing regions. Current automated detection methods rely on supervised deep learning models requiring extensive labeled data, limiting scalability for smallholder farmers. This article proposes AIM-Net (AI-based Infestation Mapping Network) by evaluating SwAV (Swapping Assignments between Views), a self-supervised learning framework, for classifying RSM infestation severity (Mild, Moderate, Severe) using a geo-referenced, field-acquired dataset of RSM infested tea-leaves, Cam-RSM. The methodology combines SwAV pre-training on unlabeled data with fine-tuning on labeled subsets, employing multi-crop augmentation and online clustering to learn discriminative features without full supervision. Comparative analysis against a fully supervised ResNet-50 baseline utilized 5-fold cross-validation, assessing accuracy, F1-scores, and computational efficiency. Results demonstrate SwAV’s superiority, achieving 98.7% overall accuracy (vs. 92.1% for ResNet-50) and macro-average F1-scores of 98.3% across classes, with a 62% reduction in labeled data requirements. The model showed particular strength in Mild_RSM-class detection (F1-score: 98.5%) and computational efficiency, enabling deployment on edge devices. Statistical validation confirmed significant improvements (p < 0.001) over baseline approaches. These findings establish self-supervised learning as a transformative tool for precision pest management, offering resource-efficient solutions for early infestation detection while maintaining high accuracy. Full article

To address the challenges of unstable vibration signals, indistinct fault features, and difficulties in feature extraction during rolling bearing operation, this paper presents a novel fault diagnosis method based on the fusion of PSR-CRP and DenseNet. The Phase Space Reconstruction (PSR) method transforms one-dimensional bearing vibration data into a three-dimensional space. Euclidean distances between phase points are calculated and mapped into a Color Recurrence Plot (CRP) to represent the bearings’ operational state. This approach effectively reduces feature extraction ambiguity compared to RP, GAF, and MTF methods. Fault features are extracted and classified using DenseNet’s densely connected topology. Compared with CNN and ViT models, DenseNet improves diagnostic accuracy by reusing limited features across multiple dimensions. The training set accuracy was 99.82% and 99.90%, while the test set accuracy is 97.03% and 95.08% for the CWRU and JNU datasets under five-fold cross-validation; F1 scores were 0.9739 and 0.9537, respectively. This method achieves highly accurate diagnosis under conditions of non-smooth signals and inconspicuous fault characteristics and is applicable to fault diagnosis scenarios for precision components in aerospace, military systems, robotics, and related fields. Full article

This study presents a U-Net-based automatic segmentation framework for quantitative analysis of surface morphology in a PEEK-based composite following tribological testing. Controlled Pin-on-Disc tests were conducted to characterize tribological performance, worn surfaces were captured by laser scanning microscopy to acquire optical images and height maps, and the model produced pixel-level segmentation masks distinguishing different regions, enabling high-throughput, objective analysis of worn surface morphology. Sixty-three manually annotated image sets—with labels for fiber, third-body patch, and matrix regions—formed the training corpus. A 70-layer U-Net architecture with four-channel input was developed and rigorously evaluated using five-fold cross-validation. To enhance performance on the challenging patch and fiber classes, the top five model instances were ensembled through Bayesian-optimized weighted voting, achieving significant improvements in class-specific F1 metrics. Segmentation outputs on unseen data confirmed the method’s robustness and generalizability across complex surface topographies. This approach establishes a scalable, accurate tool for automated morphological analysis, with potential extensions to real-time monitoring and other composite systems. Full article

Alzheimer’s disease (AD) involves the accumulation of amyloid-β (Aβ) plaques, whose quantification plays a central role in understanding disease progression. Automated segmentation of Aβ deposits in histopathological micrographs enables large-scale analyses but is hindered by the high cost of detailed pixel-level annotations. Weakly supervised learning offers a promising alternative by leveraging coarse or indirect labels to reduce the annotation burden. We evaluated a weakly supervised approach to segment and analyze thioflavin-S-positive parenchymal amyloid pathology in AD and age-matched brains. Our pipeline integrates three key components, each designed to operate under weak supervision. First, robust preprocessing (including retrospective multi-image illumination correction and gradient-based background estimation) was applied to enhance image fidelity and support training, as models rely more on image features. Second, class activation maps (CAMs), generated by a compact deep classifier SqueezeNet, were used to identify, and coarsely localize amyloid-rich parenchymal regions from patch-wise image labels, serving as spatial priors for subsequent refinement without requiring dense pixel-level annotations. Third, a patch-based convolutional neural network, U-Net, was trained on synthetic data generated from micrographs based on CAM-derived pseudo-labels via an extensive object-level augmentation strategy, enabling refined whole-image semantic segmentation and generalization across diverse spatial configurations. To ensure robustness and unbiased evaluation, we assessed the segmentation performance of the entire framework using patient-wise group k-fold cross-validation, explicitly modeling generalization across unseen individuals, critical in clinical scenarios. Despite relying on weak labels, the integrated pipeline achieved strong segmentation performance with an average Dice similarity coefficient (≈0.763) and Jaccard index (≈0.639), widely accepted metrics for assessing segmentation quality in medical image analysis. The resulting segmentations were also visually coherent, demonstrating that weakly supervised segmentation is a viable alternative in histopathology, where acquiring dense annotations is prohibitively labor-intensive and time-consuming. Subsequent morphometric analyses on automatically segmented Aβ deposits revealed size-, structural complexity-, and global geometry-related differences across brain regions and cognitive status. These findings confirm that deposit architecture exhibits region-specific patterns and reflects underlying neurodegenerative processes, thereby highlighting the biological relevance and practical applicability of the proposed image-processing pipeline for morphometric analysis. Full article

In an era where online interactions increasingly shape social dynamics, the pervasive issue of cyberbullying poses a significant threat to the well-being of individuals, particularly among vulnerable groups. Despite extensive research on text-based cyberbullying detection, the rise of visual content on social media platforms necessitates new approaches to address cyberbullying using images. This domain has been largely overlooked. In this paper, we present a novel dataset specifically designed for the detection of visual cyberbullying, encompassing four distinct classes: abuse, curse, discourage, and threat. The initial prepared dataset (cyberbullying visual indicators dataset (CVID)) comprised 664 samples for training and validation, expanded through data augmentation techniques to ensure balanced and accurate results across all classes. We analyzed this dataset using several advanced deep learning models, including VGG16, VGG19, MobileNetV2, and Vision Transformer. The proposed model, based on DenseNet201, achieved the highest test accuracy of 99%, demonstrating its efficacy in identifying the visual cues associated with cyberbullying. To prove the proposed model’s generalizability, the 5-fold stratified K-fold was also considered, and the model achieved an average test accuracy of 99%. This work introduces a dataset and highlights the potential of leveraging deep learning models to address the multifaceted challenges of detecting cyberbullying in visual content. Full article

Background/Objectives: Accurate segmentation of brain stroke lesions from MRI images is a critical task in medical image analysis that is essential for timely diagnosis and treatment planning. Methods: This paper presents a novel approach for segmenting brain stroke lesions using a deep learning model based on the U-Net neural network architecture. We enhanced the traditional U-Net by integrating a transformer-based backbone, specifically the Mix Vision Transformer (MiT), and compared its performance against other commonly used backbones such as ResNet and EfficientNet. Additionally, we implemented a 2.5D method, which leverages 2D networks to process three-dimensional data slices, effectively balancing the rich spatial context of 3D methods and the simplicity of 2D methods. The 2.5D approach captures inter-slice dependencies, leading to improved lesion delineation without the computational complexity of full 3D models. Utilizing the 2015 ISLES dataset, which includes MRI images and corresponding lesion masks for 20 patients, we conducted our experiments with 4-fold cross-validation to ensure robustness and reliability. To evaluate the effectiveness of our method, we conducted comparative experiments with several state-of-the-art (SOTA) segmentation models, including CNN-based UNet, nnU-Net, TransUNet, and SwinUNet. Results: Our proposed model outperformed all competing methods in terms of Dice Coefficient and Intersection over Union (IoU), demonstrating its robustness and superiority. Our extensive experiments demonstrate that the proposed U-Net with the MiT Backbone, combined with 2.5D data preparation, achieves superior performance metrics, specifically achieving DICE and IoU scores of 0.8153 ± 0.0101 and 0.7835 ± 0.0079, respectively, outperforming other backbone configurations. Conclusions: These results indicate that the integration of transformer-based backbones and 2.5D techniques offers a significant advancement in the accurate segmentation of brain stroke lesions, paving the way for more reliable and efficient diagnostic tools in clinical settings. Full article

As marine heatwaves increase in frequency, more rapid means of documenting their impacts are needed. Herein, several thousand coral reef photos were captured before, during, and/or after high-temperature-induced bleaching events in the Central Red Sea, with a pre-existing artificial intelligence (AI), CoralNet, trained to recognize corals and other reef-dwelling organisms. The AI-annotated images were then used to estimate coral cover and bleaching prevalence at 22 and 11 sites in the Saudi Arabian and Egyptian Red Sea, respectively. Mean healthy coral cover values of 12 and 9%, respectively, were documented, with some sites experiencing >60% bleaching during a summer 2024 heatwave that was associated with 21–22 and 25 degree-heating weeks at the Saudi Arabian and Egyptian reefs, respectively. As a result of this mass bleaching event, coral cover at the survey sites has declined over the past 5–10 years by upwards of 6-fold in the most severely impacted regions. Although some recovery is likely, these Central Red Sea sites do not appear to constitute “climate refugia,” as may be the case for some reefs farther north. Full article

A reliable estimation of protein requirements in lactating dairy cows is necessary for formulating nutritionally adequate diets, improving feed efficiency, and minimizing nitrogen excretion. This study aimed to develop machine learning-based models to predict net protein requirements for maintenance (NPm) and lactation (NPl) using random forest regression (RFR) and support vector regression (SVR). A total of 1779 observations were assembled from 436 peer-reviewed publications and open-access databases. Predictor variables included farm-ready variables such as milk yield, dry matter intake, days in milk, body weight, and dietary crude protein content. NPm was estimated based on the National Academies of Sciences, Engineering, and Medicine (NASEM, 2021) equations, while NPl was derived from milk true protein yield. The model adequacy was evaluated using 10-fold cross-validation. The RFR model demonstrated higher predictive performance than SVR for both NPm (R² = 0.82, RMSEP = 22.38 g/d, CCC = 0.89) and NPl (R² = 0.82, RMSEP = 95.17 g/d, CCC = 0.89), reflecting its capacity to model the rule-based nature of the NASEM equations. These findings suggest that RFR may provide a valuable approach for estimating protein requirements with fewer input variables. Further research should focus on validating these models under field conditions and exploring hybrid modeling frameworks that integrate mechanistic and machine learning approaches. Full article

Background: The ability of Graph Neural Networks (GNNs) to analyse brain structural patterns in various kinds of neurodegenerative diseases, including Parkinson’s disease (PD), has drawn a lot of interest recently. One emerging technique in this field is brain age prediction, which estimates biological age to identify ageing patterns that may serve as biomarkers for such disorders. However, a significant problem with most of the GNNs is their depth, which can lead to issues like oversmoothing and diminishing gradients. Methods: In this study, we propose SAGEFusionNet, a GNN architecture specifically designed to enhance brain age prediction and assess PD-related brain ageing patterns using T1-weighted structural MRI (sMRI). SAGEFusionNet learns important ROIs for brain age prediction by incorporating ROI-aware pooling at every layer to overcome the above challenges. Additionally, it incorporates multi-layer feature fusion to capture multi-scale structural information across the network hierarchy and auxiliary supervision to enhance gradient flow and feature learning at multiple depths. The dataset utilised in this study was sourced from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database. It included a total of 580 T1-weighted sMRI scans from healthy individuals. The brain sMRI scans were parcellated into 56 regions of interest (ROIs) using the LPBA40 brain atlas in CAT12. The anatomical graph was constructed based on grey matter (GM) volume features. This graph served as input to the GNN models, along with GM and white matter (WM) volume as node features. All models were trained using 5-fold cross-validation to predict brain age and subsequently tested for performance evaluation. Results: The proposed framework achieved a mean absolute error (MAE) of $4.24\pm 0.38$ years and a mean Pearson’s Correlation Coefficient (PCC) of $0.72\pm 0.03$ during cross-validation. We also used 215 PD patient scans from the Parkinson’s Progression Markers Initiative (PPMI) database to assess the model’s performance and validate it. The initial findings revealed that out of 215 individuals with Parkinson’s disease, 213 showed higher and 2 showed lower predicted brain ages than their actual ages, with a mean MAE of 13.36 years (95% confidence interval: 12.51–14.28). Conclusions: These results suggest that brain age prediction using the proposed method may provide important insights into neurodegenerative diseases. Full article

Modern energy storage systems for both power and transportation are highly related to lithium-ion batteries (LIBs). However, their safety depends on a potentially hazardous failure mode known as thermal runaway (TR). Predicting and classifying TR causes can widely enhance the safety of power and transportation systems. This paper presents an advanced machine learning method for forecasting and classifying the causes of TR. A generative model for synthetic data generation was used to handle class imbalance in the dataset. Hyperparameter optimization was conducted using Optuna for four classifiers: Support Vector Machine (SVM), Multi-Layer Perceptron (MLP), tabular network (TabNet), and Extreme Gradient Boosting (XGBoost). A three-fold cross-validation approach was used to guarantee a robust evaluation. An open-source database of LIB failure events is used for model training and testing. The XGBoost model outperforms the other models across all TR categories by achieving 100% accuracy and a high recall (1.00). Model results were interpreted using SHapley Additive exPlanations analysis to investigate the most significant factors in TR predictors. The findings show that important TR indicators include energy adjusted for heat and weight loss, heater power, average cell temperature upon activation, and heater duration. These findings guide the design of safer battery systems and preventive monitoring systems for real applications. They can help experts develop more efficient battery management systems, thereby improving the performance and longevity of battery-operated devices. By enhancing the predictive knowledge of temperature-driven failure mechanisms in LIBs, the study directly advances thermal analysis and energy storage safety domains. Full article

Air pollution source tracing is vital for effective pollution prevention and control, yet traditional methods often require large amounts of manual data, have limited cross-regional generalizability, and present challenges in capturing complex pollutant interactions. This study introduces AirTrace-SA (Air Pollution Tracing for Source Attribution), a novel hybrid deep learning model designed for the accurate identification and quantification of air pollution sources. AirTrace-SA comprises three main components: a hierarchical feature extractor (HFE) that extracts multi-scale features from chemical components, a source association bridge (SAB) that links chemical features to pollution sources through a multi-step decision mechanism, and a source contribution quantifier (SCQ) based on the TabNet regressor for the precise prediction of source contributions. Evaluated on real air quality datasets from five cities (Lanzhou, Luoyang, Haikou, Urumqi, and Hangzhou), AirTrace-SA achieves an average $R^2$ of 0.88 (ranging from 0.84 to 0.94 across 10-fold cross-validation), an average mean absolute error ($MAE$) of 0.60 (ranging from 0.46 to 0.78 across five cities), and an average root mean square error ($RMSE$) of 1.06 (ranging from 0.51 to 1.62 across ten pollution sources). The model outperforms baseline models such as 1D CNN and LightGBM in terms of stability, accuracy, and cross-city generalization. Feature importance analysis identifies the main contributions of source categories, further improving interpretability. By reducing the reliance on labor-intensive data collection and providing scalable, high-precision source tracing, AirTrace-SA offers a powerful tool for environmental management that supports targeted emission reduction strategies and sustainable development. Full article

Glaucoma is a leading cause of irreversible blindness worldwide, yet early detection can prevent vision loss. This paper proposes a novel deep learning approach that combines two ophthalmic imaging modalities, fundus photographs and optical coherence tomography scans, as paired images from the same eye of each patient for automated glaucoma detection. We develop separate convolutional neural network models for fundus and optical coherence tomography images and a fusion model that integrates features from both modalities for each eye. The models are trained and evaluated on a private clinical dataset (Bangladesh Eye Hospital and Institute Ltd.) consisting of 216 healthy eye images (108 fundus, 108 optical coherence tomography) from 108 patients and 200 glaucomatous eye images (100 fundus, 100 optical coherence tomography) from 100 patients. Our methodology includes image preprocessing pipelines for each modality, custom convolutional neural network/ResNet-based architectures for single-modality analysis, and a two-branch fusion network combining fundus and optical coherence tomography feature representations. We report the performance (accuracy, sensitivity, specificity, and area under curve) of the fundus-only, optical coherence tomography-only, and fusion models. In addition to a fixed test set evaluation, we perform five-fold cross-validation, confirming the robustness and consistency of the fusion model across multiple data partitions. On our fixed test set, the fundus-only model achieves 86% accuracy (AUC 0.89) and the optical coherence tomography-only model, 84% accuracy (AUC 0.87). Our fused model reaches 92% accuracy (AUC 0.95), an absolute improvement of 6 percentage points and 8 percentage points over the fundus and OCT baselines, respectively. McNemar’s test on pooled five-fold validation predictions (b = 3, c = 18) yields ${\chi }^2=10.7$ (p = 0.001), and on optical coherence tomography-only vs. fused (b_o = 5, c_o = 20) ${\chi }_o^2=9.0$ (p = 0.003), confirming that the fusion gains are significant. Five-fold cross-validation further confirms these improvements (mean AUC $0.952\pm 0.011$. We also compare our results with the existing literature and discuss the clinical significance, limitations, and future work. To the best of our knowledge, this is the first time a novel deep learning model has been used on a fusion of paired fundus and optical coherence tomography images of the same patient for the detection of glaucoma. Full article

Background: Accurate upfront risk stratification in suspected clinically significant prostate cancer (csPCa) may reduce unnecessary prostate biopsies. Integrating clinical and Magnetic Resonance Imaging (MRI) variables using deep learning could improve prediction. Methods: We retrospectively analysed 538 men who underwent MRI and biopsy between April 2019-September 2024. A fully connected neural network was trained using 5-fold cross-validation. Model 1 included clinical features (age, prostate-specific antigen [PSA], PSA density, digital rectal examination, family history, prior negative biopsy, and ongoing therapy). Model 2 used MRI-derived Prostate Imaging Reporting and Data System (PI-RADS) categories. Model 3 used all previous variables as well as lesion size, location, and prostate volume as determined on MRI. Results: Model 3 achieved the highest area under the receiver operating characteristic curve (AUC = 0.822), followed by Model 2 (AUC = 0.778) and Model 1 (AUC = 0.716). Sensitivities for detecting clinically significant prostate cancer (csPCa) were 87.4%, 91.6%, and 86.8% for Models 1, 2, and 3, respectively. Although Model 3 had slightly lower sensitivity than Model 2, it showed higher specificity, reducing false positives and avoiding 43.4% and 21.2% more biopsies compared to Models 1 and 2. Decision curve analysis showed M2 had the highest net benefit at risk thresholds ≤ 20%, while M3 was superior above 20%. Conclusions: Model 3 improved csPCa risk stratification, particularly in biopsy-averse settings, while Model 2 was more effective in cancer-averse scenarios. These models support personalized, context-sensitive biopsy decisions. Full article

The neural network-based classification of endoscopy images plays a key role in diagnosing gastrointestinal diseases. However, current models for estimating ulcerative colitis (UC) severity still lack high performance, highlighting the need for more advanced and accurate solutions. This study aims to apply a state-of-the-art hybrid neural network architecture—combining convolutional neural networks (CNNs) and transformer models—to classify intestinal endoscopy images, utilizing the largest publicly available annotated UC dataset. A 10-fold cross-validation is performed on the LIMUC dataset using CoAtNet models, combined with the Class Distance Weighted Cross-Entropy (CDW-CE) loss function. The best model is compared against pure CNN and transformer baselines by evaluating performance metrics, including quadratically weighted kappa (QWK) and macro F1, for full Mayo score classification, and kappa and F1 scores for remission classification. The CoAtNet models outperformed both pure CNN and transformer models. The most effective model, CoAtNet_2, improved classification accuracy by $1.76\%$ and QWK by $1.46\%$ over the previous state-of-the-art models on the LIMUC dataset. Other metrics, including F1 score, also showed clear improvements. Experiments show that the CoAtNet model, which integrates convolutional and transformer components, improves UC assessment from endoscopic images, enhancing AI’s role in computer-aided diagnosis. Full article

Abundant large organic aggregates, which form mucous webs up to a few decimeters in length, have been observed in Baía de Todos os Santos (BTS), northeastern Brazil. This communication presents preliminary results from field (February 2015) and laboratory (June 2015) experiments that aimed to determine preliminary values for respiration and near-maximum photosynthesis and the impact of macroaggregates on respiration rates. The experiments included the determination of respiration in controls, with the mechanical removal and addition of macroaggregates. The field experiment during a flood tide presented the lowest respiration rate (−7.0 ± 0.7 µM L⁻¹ d⁻¹), average net primary production (8.9 ± 4.5 µM L⁻¹ d⁻¹), and gross primary production (16.0 ± 10 µM L⁻¹ d⁻¹), with a ratio of gross primary production to respiration of 2.3. The control experiments during an ebb tide showed a mean respiration rate of 8.7 ± 2.3 µM L⁻¹ d⁻¹, whereas, after macroaggregate removal, this was 9.5 ± 4.5 µM L⁻¹ d⁻¹. In the laboratory experiments, the control sample respiration rate of 18.4 ± 1.4 µM L⁻¹ d⁻¹ was slightly increased to 20.6 ± 0.1 µM L⁻¹ d⁻¹ after aggregate removal. The addition of aggregates to the control sample increased the respiration rate by approximately 3-fold, to 56.5 ± 4.8 µM L⁻¹ d⁻¹. These results indicate that macroaggregates could have an important role in pelagic and benthic respiration, as well as in the whole bay’s metabolism. Full article