Search Results (182)

In response to the problem of complex and variable loads on wind turbine gearbox bearing in working conditions, as well as the limited amount of sound data making fault identification difficult, this study focuses on sound signals and proposes an intelligent diagnostic method using deep learning. By adding the CBAM module in ResNeXt to enhance the model’s attention to important features and combining it with the Arcloss loss function to make the model learn more discriminative features, the generalization ability of the model is strengthened. We used a fine-tuning transfer learning strategy, transferring pre-trained model parameters to the CBAM-ResNeXt50-ArcLoss model and training with an extracted Mel spectrogram of sound signals to extract and classify audio features of the wind turbine gearbox. Experimental validation of the proposed method on collected sound signals showed its effectiveness and superiority. Compared to CNN, ResNet50, ResNeXt50, and CBAM-ResNet50 methods, the CBAM-ResNeXt50-ArcLoss model achieved improvements of 13.3, 3.6, 2.4, and 1.3, respectively. Through comparison with classical algorithms, we demonstrated that the research method proposed in this study exhibits better diagnostic capability in classifying wind turbine gearbox sound signals. Full article

Recently, there has been a rise in skin cancer cases, for which early detection is highly relevant, as it increases the likelihood of a cure. In this context, this work presents a benchmarking study of standard Convolutional Neural Network (CNN) architectures for automated skin lesion classification. A total of 38 CNN architectures from ten families (ConvNeXt, DenseNet, EfficientNet, Inception, InceptionResNet, MobileNet, NASNet, ResNet, VGG, and Xception) were evaluated using transfer learning on the HAM10000 dataset for seven-class skin lesion classification, namely, actinic keratoses, basal cell carcinoma, benign keratosis-like lesions, dermatofibroma, melanoma, melanocytic nevi, and vascular lesions. The comparative analysis used standardized training conditions, with all models utilizing frozen pre-trained weights. Cross-database validation was then conducted using the ISIC 2019 dataset to assess generalizability across different data distributions. The ConvNeXtXLarge architecture achieved the best performance, despite having one of the lowest performance-to-number-of-parameters ratios, with 87.62% overall accuracy and 76.15% F1 score on the test set, demonstrating competitive results within the established performance range of existing HAM10000-based studies. A proof-of-concept multiplatform mobile application was also implemented using a client–server architecture with encrypted image transmission, demonstrating the viability of integrating high-performing models into healthcare screening tools. Full article

Background: Chest X-rays are rapidly gaining prominence as a prevalent diagnostic tool, as recognized by the World Health Organization (WHO). However, interpreting chest X-rays can be demanding and time-consuming, even for experienced radiologists, leading to potential misinterpretations and delays in treatment. Method: The purpose of this research is the development of a RadAI model. The RadAI model can accurately detect four types of lung abnormalities in chest X-rays and generate a report on each identified abnormality. Moreover, deep learning algorithms, particularly convolutional neural networks (CNNs), have demonstrated remarkable potential in automating medical image analysis, including chest X-rays. This work addresses the challenge of chest X-ray interpretation by fine tuning the following three advanced deep learning models: Feature-selective and Spatial Receptive Fields Network (FSRFNet50), ResNext50, and ResNet50. These models are compared based on accuracy, precision, recall, and F1-score. Results: The outstanding performance of RadAI shows its potential to assist radiologists to interpret the detected chest abnormalities accurately. Conclusions: RadAI is beneficial in enhancing the accuracy and efficiency of chest X-ray interpretation, ultimately supporting the timely and reliable diagnosis of lung abnormalities. Full article

Deep learning models such as convolutional neural networks (CNNs) and vision transformers (ViTs) perform well in histological image classification, but often lack interpretability. We introduce a unified framework that adds an attention branch and CAM Fostering, an entropy-based regularizer, to improve Grad-CAM visualizations. Six backbone architectures (ResNet-50, DenseNet-201, EfficientNet-b0, ResNeXt-50, ConvNeXt, CoatNet-small) were trained, with and without our modifications, on five H&E-stained datasets. We measured explanation quality using coherence, complexity, confidence drop, and their harmonic mean (ADCC). Our method increased the ADCC in five of the six backbones; ResNet-50 saw the largest gain (+15.65%), and CoatNet-small achieved the highest overall score (+2.69%), peaking at 77.90% on the non-Hodgkin lymphoma set. The classification accuracy remained stable or improved in four models. These results show that combining attention and entropy produces clearer, more informative heatmaps without degrading performance. Our contributions include a modular architecture for both convolutional and hybrid models and a comprehensive, quantitative explainability evaluation suite. Full article

The technology of road extraction serves as a crucial foundation for urban intelligent renewal and green sustainable development. Its outcomes can optimize transportation network planning, reduce resource waste, and enhance urban resilience. Deep learning-based approaches have demonstrated outstanding performance in road extraction, particularly excelling in complex scenarios. However, extracting roads from remote sensing data remains challenging due to several factors that limit accuracy: (1) Roads often share similar visual features with the background, such as rooftops and parking lots, leading to ambiguous inter-class distinctions; (2) Roads in complex environments, such as those occluded by shadows or trees, are difficult to detect. To address these issues, this paper proposes an improved model based on Graph Convolutional Networks (GCNs), named FR-SGCN (Hierarchical Depth-wise Separable Graph Convolutional Network Incorporating Graph Reasoning and Attention Mechanisms). The model is designed to enhance the precision and robustness of road extraction through intelligent techniques, thereby supporting precise planning of green infrastructure. First, high-dimensional features are extracted using ResNeXt, whose grouped convolution structure balances parameter efficiency and feature representation capability, significantly enhancing the expressiveness of the data. These high-dimensional features are then segmented, and enhanced channel and spatial features are obtained via attention mechanisms, effectively mitigating background interference and intra-class ambiguity. Subsequently, a hybrid adjacency matrix construction method is proposed, based on gradient operators and graph reasoning. This method integrates similarity and gradient information and employs graph convolution to capture the global contextual relationships among features. To validate the effectiveness of FR-SGCN, we conducted comparative experiments using 12 different methods on both a self-built dataset and a public dataset. The proposed model achieved the highest F1 score on both datasets. Visualization results from the experiments demonstrate that the model effectively extracts occluded roads and reduces the risk of redundant construction caused by data errors during urban renewal. This provides reliable technical support for smart cities and sustainable development. Full article

Wildfire detection in power transmission corridors is essential for providing timely warnings and ensuring the safe and stable operation of power lines. However, this task faces significant challenges due to the large number of smoke-like samples in the background, the complex and diverse target morphologies, and the difficulty of detecting small-scale smoke and flame objects. To address these issues, this paper proposed an improved Oriented R-CNN model enhanced with metric learning for wildfire detection in power transmission corridors. Specifically, a multi-center metric loss (MCM-Loss) module based on metric learning was introduced to enhance the model’s ability to differentiate features of similar targets, thereby improving the recognition accuracy in the presence of interference. Experimental results showed that the introduction of the MCM-Loss module increased the average precision (AP) for smoke targets by 2.7%. In addition, the group convolution-based network ResNeXt was adopted to replace the original backbone network ResNet, broadening the channel dimensions of the feature extraction network and enhancing the model’s capability to detect flame and smoke targets with diverse morphologies. This substitution led to a 0.6% improvement in mean average precision (mAP). Furthermore, an FPN-CARAFE module was designed by incorporating the content-aware up-sampling operator CARAFE, which improved multi-scale feature representation and significantly boosted performance in detecting small targets. In particular, the proposed FPN-CARAFE module improved the AP for fire targets by 8.1%. Experimental results demonstrated that the proposed model achieved superior performance in wildfire detection within power transmission corridors, achieving a mAP of 90.4% on the test dataset—an improvement of 6.4% over the baseline model. Compared with other commonly used object detection algorithms, the model developed in this study exhibited improved detection performance on the test dataset, offering research support for wildfire monitoring in power transmission corridors. Full article

During transformer operation, long-term vibration causes the winding to loosen axially. When hit by a short-circuit, the winding deforms to different extents. Thus, identifying early looseness faults in transformer windings is vital for power systems’ stability. To address issues including scarce vibration data across multiple load conditions for transformer winding looseness faults, inadequate extraction of two-dimensional spectrogram features, and the inability to boost recognition accuracy caused by overfitting during fault recognition model training, this study constructed a 10 kV power transformer vibration test platform. It measured the vibration signals on the box surface under various winding looseness conditions and built a time–frequency-domain vibration spectrum library for different load currents. Then, a fault identification model based on vibration spectra and ConvNeXt was constructed, and model verification and analysis were carried out. The results indicate that after training, the fault recognition accuracy of the spectrum containing three load conditions is comparable to that of a single load condition. The average recognition accuracy at six box-surface measuring points reaches 97.9%. Moreover, the ConvNeXt model outperforms the traditional ResNet50 by 1.2%. This new model effectively addresses overfitting and offers strong technical support for detecting different transformer winding looseness faults. Full article

Beef carcass grading plays a pivotal role in determining market value and consumer preferences. While traditional visual inspection by experts remains the industry standard, it suffers from subjectivity and inconsistencies, particularly in high-throughput slaughterhouse environments. To address these limitations, we propose a one-stage automated grading model based on EfficientViT, a lightweight vision transformer architecture. Unlike conventional two-stage methods that require prior segmentation of the loin region, our model directly predicts beef quality grades from raw RGB images, significantly simplifying the pipeline and reducing computational overhead. We evaluate the proposed model against representative convolutional neural networks (VGG-16, ResNeXt-50, DenseNet-121) as well as two-stage combinations of segmentation and classification models. Experiments were conducted on a publicly available beef carcass dataset consisting of over 77,000 labeled images. EfficientViT achieves the highest accuracy (98.46%) and F1-score (0.9867) among all evaluated models while maintaining low inference latency (3.92 ms) and compact parameter size (36.4 MB). In particular, it outperforms CNNs in predicting the top grade (1++), where global visual patterns such as marbling distribution are crucial. Furthermore, we employ Grad-CAM and attention map visualizations to analyze the model’s focus regions and demonstrate that EfficientViT captures holistic contextual features better than CNNs. The model also exhibits robustness across varying loin area proportions. Our findings suggest that EfficientViT is not only accurate but also efficient and interpretable, making it a strong candidate for real-time industrial applications in beef quality grading. Full article

Multi-peg-hole assembly is a fundamental process in robotic manufacturing, particularly for circular aviation electrical connectors (CAECs) that require precise axial alignment. However, CAEC assembly poses significant challenges due to small apertures, posture disturbances, and the need for high error tolerance. This paper proposes a dual-stream Siamese network (DSSN) framework that fuses visual and tactile modalities to achieve accurate position identification in six-degree-of-freedom robotic connector assembly tasks. The DSSN employs ConvNeXt for visual feature extraction and SE-ResNet-50 with integrated attention mechanisms for tactile feature extraction, while a gated attention module adaptively fuses multimodal features. A bidirectional long short-term memory (Bi-LSTM) recurrent neural network is introduced to jointly model spatiotemporal deviations in position and orientation. Compared with state-of-the-art methods, the proposed DSSN achieves improvements of approximately 7.4%, 5.7%, and 5.4% in assembly success rates after 1, 5, and 10 buckling iterations, respectively. Experimental results validate that the integration of multimodal adaptive fusion and sequential spatiotemporal learning enables robust and precise robotic connectors assembly under high-tolerance conditions. Full article

Machine learning models often face challenges in bridge inspections, especially in handling complex surface features and overlapping defects that make accurate classification difficult. These challenges are common for image-based monitoring, which has become increasingly popular for inspecting and assessing the structural condition of reinforced concrete bridges with automated possibilities. Despite advances in defect detection using convolutional neural networks (CNNs), although challenges such as overlapping defects, complex surface textures, and data imbalance remain difficult, full fine-tuning of deep learning models helps them better adapt to these conditions by updating all the layers for domain-specific learning. The aim of this study is to demonstrate how effective the fine-tuning of several deep learning architectures for bridge damage classification allows for robust performance and the best utilization value of the methods. Six CNN architectures, ResNet-18, ResNet-50, ResNet-101, ResNeXt-50, ResNeXt-101 and EfficientNet-B3, were fine-tuned using the CODEBRIM dataset. Their performance was evaluated using Precision, Recall, F1 Score, Balanced Accuracy and AUC-ROC metrics to ensure a robust evaluation framework. This indicates that the EfficientNet-B3 and ResNeXt-101 models outperformed the other models and achieved the highest classification accuracy in all the error categories. EfficientNet-B3 showed the best-balanced Precision (0.935) and perfect Recall (1.000) in background classification, indicating its ability to distinguish defect-free areas from structural damage. These results highlight the potential of these models to improve automated bridge inspection systems and thus increase accuracy and efficiency in real-world applications, as well as provide guidance for the selection of methods based on whether accuracy or overall consistency is more important for a specific application. Full article

Prostate cancer is a leading cause of cancer-related morbidity and mortality worldwide, with diagnostic challenges magnified in underrepresented regions like sub-Saharan Africa. This study introduces a novel application of ConvNeXt, an advanced convolutional neural network architecture, for multi-class classification of prostate histopathological images into normal, benign, and malignant categories. The dataset, sourced from a tertiary healthcare institution in Nigeria, represents a typically underserved African population, addressing critical disparities in global diagnostic research. We also used the ProstateX dataset (2017) from The Cancer Imaging Archive (TCIA) to validate our result. A comprehensive pipeline was developed, leveraging advanced data augmentation, Grad-CAM for interpretability, and an ablation study to enhance model optimization and robustness. The ConvNeXt model achieved an accuracy of 98%, surpassing the performance of traditional CNNs (ResNet50, 93%; EfficientNet, 94%; DenseNet, 92%) and transformer-based models (ViT, 88%; CaiT, 86%; Swin Transformer, 95%; RegNet, 94%). Also, using the ProstateX dataset, the ConvNeXt model recorded 87.2%, 85.7%, 86.4%, and 0.92 as accuracy, recall, F1 score, and AUC, respectively, as validation results. Its hybrid architecture combines the strengths of CNNs and transformers, enabling superior feature extraction. Grad-CAM visualizations further enhance explainability, bridging the gap between computational predictions and clinical trust. Ablation studies demonstrated the contributions of data augmentation, optimizer selection, and learning rate tuning to model performance, highlighting its robustness and adaptability for deployment in low-resource settings. This study advances equitable health care by addressing the lack of regional representation in diagnostic datasets and employing a clinically aligned three-class classification approach. Combining high performance, interpretability, and scalability, this work establishes a foundation for future research on diverse and underrepresented populations, fostering global inclusivity in cancer diagnostics. Full article

The gastrointestinal (GI) tract, an integral part of the digestive system, absorbs nutrients from ingested food, starting from the mouth to the anus. GI tract cancer significantly impacts global health, necessitating precise treatment methods. Radiation oncologists use X-ray beams to target tumors while avoiding the stomach and intestines, making the accurate segmentation of these organs crucial. This research explores various combinations of encoders and decoders to segment the small bowel, large bowel, and stomach in MRI images, using the UW-Madison GI tract dataset consisting of 38,496 scans. Encoders tested include ResNet50, EfficientNetB1, MobileNetV2, ResNext50, and Timm_Gernet_S, paired with decoders UNet, FPN, PSPNet, PAN, and DeepLab V3+. The study identifies ResNet50 with DeepLab V3+ as the most effective combination, assessed using the Dice coefficient, Jaccard index, and model loss. The proposed model, a combination of DeepLab V3+ and ResNet 50, obtained a Dice value of 0.9082, an IoU value of 0.8796, and a model loss of 0.117. The findings demonstrate the method’s potential to improve radiation therapy for GI cancer, aiding radiation oncologists in accurately targeting tumors while avoiding healthy organs. The results of this study will assist healthcare professionals involved in biomedical image analysis. Full article

Contactless fingerprint recognition systems offer a hygienic, user-friendly, and efficient alternative to traditional contact-based methods. However, their accuracy heavily relies on precise fingertip detection and segmentation, particularly under challenging background conditions. This paper introduces TipSegNet, a novel deep learning model that achieves state-of-the-art performance in segmenting fingertips directly from grayscale hand images. TipSegNet leverages a ResNeXt-101 backbone for robust feature extraction, combined with a Feature Pyramid Network (FPN) for multi-scale representation, enabling accurate segmentation across varying finger poses and image qualities. Furthermore, we employ an extensive data augmentation strategy to enhance the model’s generalizability and robustness. This model was trained and evaluated using a combined dataset of 2257 labeled hand images. TipSegNet outperforms existing methods, achieving a mean intersection over union (mIoU) of 0.987 and an accuracy of 0.999, representing a significant advancement in contactless fingerprint segmentation. This enhanced accuracy has the potential to substantially improve the reliability and effectiveness of contactless biometric systems in real-world applications. Full article

Purpose: To develop deep learning models for predicting the pathologic complete response (pCR) to neoadjuvant systemic therapy (NAST) in patients with triple-negative breast cancer (TNBC) based on pretreatment multiparametric breast MRI and clinicopathological data. Methods: The prospective institutional review board-approved study [NCT02276443] included 282 patients with stage I–III TNBC who had multiparametric breast MRI at baseline and underwent NAST and surgery during 2016–2021. Dynamic contrast-enhanced MRI (DCE), diffusion-weighted imaging (DWI), and clinicopathological data were used for the model development and internal testing. Data from the I-SPY 2 trial (2010–2016) were used for external testing. Four variables with a potential impact on model performance were systematically investigated: 3D model frameworks, tumor volume preprocessing, tumor ROI selection, and data inputs. Results: Forty-eight models with different variable combinations were investigated. The best-performing model in the internal testing dataset used DCE, DWI, and clinicopathological data with the originally contoured tumor volume, the tight bounding box of the tumor mask, and ResNeXt50, and achieved an area under the receiver operating characteristic curve (AUC) of 0.76 (95% CI: 0.60–0.88). The best-performing models in the external testing dataset achieved an AUC of 0.72 (95% CI: 0.57–0.84) using only DCE images (originally contoured tumor volume, enlarged bounding box of tumor mask, and ResNeXt50) and an AUC of 0.72 (95% CI: 0.56–0.86) using only DWI images (originally contoured tumor volume, enlarged bounding box of tumor mask, and ResNet18). Conclusions: We developed 3D deep learning models based on pretreatment data that could predict pCR to NAST in TNBC patients. Full article

The lack of extensive, varied, and thoroughly annotated datasets impedes the advancement of artificial intelligence (AI) for medical applications, especially colorectal cancer detection. Models trained with limited diversity often display biases, especially when utilized on disadvantaged groups. Generative models (e.g., DALL-E 2, Vector-Quantized Generative Adversarial Network (VQ-GAN)) have been used to generate images but not colonoscopy data for intelligent data augmentation. This study developed an effective method for producing synthetic colonoscopy image data, which can be used to train advanced medical diagnostic models for robust colorectal cancer detection and treatment. Text-to-image synthesis was performed using fine-tuned Visual Large Language Models (LLMs). Stable Diffusion and DreamBooth Low-Rank Adaptation produce images that look authentic, with an average Inception score of 2.36 across three datasets. The validation accuracy of various classification models Big Transfer (BiT), Fixed Resolution Residual Next Generation Network (FixResNeXt), and Efficient Neural Network (EfficientNet) were 92%, 91%, and 86%, respectively. Vision Transformer (ViT) and Data-Efficient Image Transformers (DeiT) had an accuracy rate of 93%. Secondly, for the segmentation of polyps, the ground truth masks are generated using Segment Anything Model (SAM). Then, five segmentation models (U-Net, Pyramid Scene Parsing Network (PSNet), Feature Pyramid Network (FPN), Link Network (LinkNet), and Multi-scale Attention Network (MANet)) were adopted. FPN produced excellent results, with an Intersection Over Union (IoU) of $0.64$, an F1 score of $0.78$, a recall of $0.75$, and a Dice coefficient of 0.77. This demonstrates strong performance in terms of both segmentation accuracy and overlap metrics, with particularly robust results in balanced detection capability as shown by the high F1 score and Dice coefficient. This highlights how AI-generated medical images can improve colonoscopy analysis, which is critical for early colorectal cancer detection. Full article