Augmentation Techniques Research Articles

Subcutaneous Lower Pole Release as Double Bubble Prevention in Constricted Base Breasts: The "Plus One" Augmentation Technique.

Breasts with a broad base, constricted inframammary fold (IMF) and a short distance between the nipple and the IMF are predisposed to form a double bubble (DB) deformity. Most publications have focused on the correction of a DB rather than on its prevention and thorough analysis of the IMF. Introduction of a third dissection plane in breast augmentation for preventing or correcting DB deformities. This study is a retrospective analysis conducted by a single surgeon, involving 46 patients with a well-defined constricted IMF who underwent breast augmentation with the 'Plus One' technique between 2019 and 2021. Women who required mastopexy were excluded. All procedures were analyzed for lower pole curvature using visual and graphical photographic analysis. The lower pole breast contour was plotted as a graph for better comparison of outcomes. Breast-Q surveys were conducted before and 3 months after surgery. Follow-ups were done at 2 weeks, 6 months, and 12 months after surgery. The curve of the postoperative lower pole was convex in 96% of the cases. In 4%, the curve tends to straighten out in the lower pole. In one case, the curve became concave at one point indicating a DB deformity, making a DB complication rate of 2%. The mean preoperative satisfaction score was 43±2, and the postoperative satisfaction score was 94±3 on the BREAST-Q scale. The "plus one" method showed stable and satisfying results and is easily reproducible with a low complication rate. This can also be used as either a prophylactic or corrective measure.

Impacted lower third molar classification and difficulty index assessment: comparisons among dental students, general practitioners and deep learning model assistance

BackgroundAssessing the difficulty of impacted lower third molar (ILTM) surgical extraction is crucial for predicting postoperative complications and estimating procedure duration. The aim of this study was to evaluate the effectiveness of a convolutional neural network (CNN) in determining the angulation, position, classification and difficulty index (DI) of ILTM. Additionally, we compared these parameters and the time required for interpretation among deep learning (DL) models, sixth-year dental students (DSs), and general dental practitioners (GPs) with and without CNN assistance.Materials and MethodsThe dataset included cropped panoramic radiographs of 1200 ILTMs. The parameters examined were ILTM angulation, class, and position. The radiographs were randomly split into test datasets, while the remaining images were utilized for training and validation. Data augmentation techniques were applied. Another set of radiographs was used to compare the accuracy between human experts and the top-performing CNN. This dataset was also given to DSs and GPs. The participants were instructed to classify the parameters of the ILTMs both with and without the aid of the best-performing CNN model. The results, as well as the Pederson DI and time taken for both groups with and without CNN assistance, were statistically analyzed.ResultsAll the selected CNN models successfully classified ILTM angulation, class, and position. Within the DS and GP groups, the accuracy and kappa scores were significantly greater when CNN assistance was used. Among the groups, performance tests without CNN assistance revealed no significant differences in any category. However, compared with DSs, GPs took significantly less time for the class and total time, a trend that persisted when CNN assistance was used. With the CNN, the GPs achieved significantly higher accuracy and kappa scores for class classification than the DSs did (p = 0.035 and 0.010). Conversely, the DS group, with the CNN, exhibited higher accuracy and kappa scores for position classification than did the GP group (p < 0.001).ConclusionThe CNN can achieve accuracies ranging from 87 to 96% for ILTM classification. With the assistance of the CNN, both DSs and GPs exhibited significantly higher accuracy in ILTM classification. Additionally, compared with DSs with and without CNN assistance, GPs took significantly less time to inspect the class and overall.

(Semi-)automatic Extraction of Urban Planning Rules in French for Better Management of Land Artificialization

Land artificialization is a significant modern concern, as it is irreversible, diminishes agriculturally suitable land and causes environmental problems. Our project, Hérelles, aims to address this challenge by developing a framework for land artificialization management. In this framework, we associate urban planning rules in text form with clusters extracted from time series of satellite images. To achieve this, it is crucial to understand the planning rules with two key objectives: (1) to verify if the constraints derived from the rules are verifiable on satellite images and (2) to use these constraints to guide the labelling (or semantization) of clusters. The first step in this process involves the automatic extraction of rules from urban planning documents written in the French language. To solve this problem, we propose a method based on the multilabel classification of textual segments and their subsequent summarization. This method includes a special format for representing segments, in which each segment has a title and a subtitle. We then propose a cascade approach to address the hierarchy of class labels. Additionally, we develop several text augmentation techniques for French texts that can improve prediction results. Finally, we reformulate classified segments into concise text portions containing necessary elements for expert rule construction. We adapt an approach based on Meaning Representation (AMR) graphs to generate these portions in the French language and conduct a comparative analysis with ChatGPT. We experimentally demonstrate that the resulting framework correctly classifies each type of segment with more than 90% accuracy. Furthermore, our results indicate that ChatGPT outperforms the AMR-based approach, leading to a discussion of the advantages and limitations of both methods.

Condition assessment of bolted connections in steel structures using deep learning

Steel structure connections are prone to bolt loosening and subsequent loss of strength or stability if not inspected periodically. Use of noncontact sensing and artificial intelligence can substantially increase the safety and efficiency of these inspections; however, the existing defect detection models do not account for variability of defects in both missing and loosened bolt connections. Furthermore, the performance of available deep learning models can be substantially diminished due to the presence of background noise in images of real structures. Finding these defects could be even more difficult in highway steel structures due to the complex and continuously changing nature of background. Additionally, no datasets are available to properly use these models for defect detection. In this paper, Mask RCNN (MRCN), You Only Look Once (YOLO), and Faster RCNN (FRCNN) models were adapted for investigation. These models were trained and tuned on a unique dataset-developed by the Authors comprised of 1100 raw images with connection defects of laboratory-made and in-service structures. A series of image enhancement and augmentation techniques were used to superimpose bolt and nut defects on intact images of in-service ancillary structure and to increase the size in training dataset to 1500. After models achieved satisfactory performance in laboratory images, they were tested on field and lab data (including 200 images with defective bolt). Thermal images were used to develop an efficient way to mask image background in visual images. The result indicated that removing background decreased the false positive rate (FRP) around 65% between the investigated deep learning models on UAS image. Overall accuracy of these models estimated between where 90% and 93%when FRCNN and Mask RCN.

Deep learning-based algorithm for classifying high-resolution computed tomography features in coal workers’ pneumoconiosis

BackgroundCoal workers’ pneumoconiosis is a chronic occupational lung disease with considerable pulmonary complications, including irreversible lung diseases that are too complex to accurately identify via chest X-rays. The classification of clinical imaging features from high-resolution computed tomography might become a powerful clinical tool for diagnosing pneumoconiosis in the future.MethodsAll chest high-resolution computed tomography (HRCT) medical images presented in this work were obtained from 217 coal workers' pneumoconiosis (CWP) patients and dust-exposed workers. We segmented regions of interest according to the diagnostic results, which were evaluated by radiologists. These regions were then classified regions into four categories. We employed an efficient deep learning model and various image augmentation techniques (DenseNet-ECA). The classification performance of the different deep learning models was assessed, and receiver operating characteristic (ROC) curves and accuracy (ACC) were used to determine the optimal algorithm for classifying CWP clinical imaging features obtained from HRCT images.ResultsFour primary clinical imaging features in HRCT images, with a total of more than 1700 regions of interest (ROIs), were annotated, augmented, and used as a training set for tenfold cross-validation to generate the model. We selected DenseNet-Attention Net as the optimal model through assessing the performance of different classification algorithms, which yielded an average area under the ROC curve (AUC) of 0.98, and all clinical imaging features were classified with an AUC greater than 0.92. For the individual classifications, the AUCs were as follows: small miliary opacities, 0.99; nodular opacities, 1.0; interstitial changes, 0.92; and emphysema, 1.0.ConclusionWe successfully applied a data augmentation strategy to develop a deep learning model by combining DenseNet with ECA-Net. We used our novel model to automatically classify CWP clinical imaging features from 2D HRCT images. This successful application of a deep learning-data augmentation algorithm can help clinical radiologists by providing reliable diagnostic information for classification.Trial registration: Chinese Clinical Trial Registry, ChiCTR2100050379. Registered on 27 August 2021, https://www.chictr.org.cn/bin/project/edit?pid=132619.

Class-Wise Combination of Mixture-Based Data Augmentation for Class Imbalance Learning of Focal Liver Lesions in Abdominal CT Images.

In this paper, we propose a method to address the class imbalance learning in the classification of focal liver lesions (FLLs) from abdominal CT images. Class imbalance is a significant challenge in medical image analysis, making it difficult for machine learning models to learn to classify them accurately. To overcome this, we propose a class-wise combination of mixture-based data augmentation (CCDA) method that uses two mixture-based data augmentation techniques, MixUp and AugMix. These are applied at different ratios for each class to adaptively learn features for each class. This method is tailored to handle the unique characteristics of each FLL type by adjusting the augmentation mix for major classes (e.g., cysts and metastases) and minor classes (e.g., hemangiomas). In experiments, our method was validated on the dataset consisted of portal phase CT images from 1290 colorectal cancer patients. The results showed that applying MixUp and AugMix in a class-wise manner could significantly improve the classification performance of minor classes while maintaining or slightly improving the performance of major classes. Quantitative results showed higher F1 scores for minor classes and a more balanced accuracy across classes when CCDA was used compared to other methods.

Integration of Deep Learning Vision Systems in Collaborative Robotics for Real-Time Applications

Collaborative robotics and computer vision systems are increasingly important in automating complex industrial tasks with greater safety and productivity. This work presents an integrated vision system powered by a trained neural network and coupled with a collaborative robot for real-time sorting and quality inspection in a food product conveyor process. Multiple object detection models were trained on custom datasets using advanced augmentation techniques to optimize performance. The proposed system achieved a detection and classification accuracy of 98%, successfully processing more than 600 items with high efficiency and low computational cost. Unlike conventional solutions that rely on ROS (Robot Operating System), this implementation used a Windows-based Python framework for greater accessibility and industrial compatibility. The results demonstrated the reliability and industrial applicability of the solution, offering a scalable and accurate methodology that can be adapted to various industrial applications.

Spatial Cluster Detection Under Dependent Random Environmental Effects

This paper develops a new approach for the detection of spatial clusters in the presence of random environmental effects and covariates when the observed data consist of counts over a regular grid. Such data are frequently overdispersed and spatially dependent. Overdispersion and spatial dependence must be taken into account in the modeling, otherwise the classical scan statistics method may lead to the detection of false clusters. Therefore, we consider that the observed counts are generated by a Cox process, allowing for overdispersion and spatial correlation. The environmental effects here represents unobserved covariates, as opposed to observed covariates whose observations are used via the link function in the model. These random effects are modeled by means of spatial copula with margins distributed according to a Gamma distribution. We then prove that the counts are dependent and negative binomial and propose a spatial cluster detection test based on data augmentation techniques. It is worth noting that our model also includes the case of independent effects for which the counts are independent and negative binomial. An illustration of these spatial scan techniques is provided by a Black Leaf Streak Disease (BLSD) dataset from Martinique, French West Indies. The comparison of our model with Poisson models, with or without covariates, demonstrates the importance of our approach in avoiding false clusters.

Neural Network for Underwater Fish Image Segmentation Using an Enhanced Feature Pyramid Convolutional Architecture

Underwater fish image segmentation is a crucial technique in marine fish monitoring. However, typical underwater fish images often suffer from issues such as color distortion, low contrast, and blurriness, primarily due to the complex and dynamic nature of the marine environment. To enhance the accuracy of underwater fish image segmentation, this paper introduces an innovative neural network model that combines the attention mechanism with a feature pyramid module. After the backbone network processes the input image through convolution, the data pass through the enhanced feature pyramid module, where it is iteratively processed by multiple weighted branches. Unlike conventional methods, the multi-scale feature extraction module that we designed not only improves the extraction of high-level semantic features but also optimizes the distribution of low-level shape feature weights through the synergistic interactions of the branches, all while preserving the inherent properties of the image. This novel architecture significantly boosts segmentation accuracy, offering a new solution for fish image segmentation tasks. To further enhance the model’s robustness, the Mix-up and CutMix data augmentation techniques were employed. The model was validated using the Fish4Knowledge dataset, and the experimental results demonstrate that the model achieves a Mean Intersection over Union (MIoU) of 95.1%, with improvements of 1.3%, 1.5%, and 1.7% in the MIoU, Mean Pixel Accuracy (PA), and F1 score, respectively, compared to traditional segmentation methods. Additionally, a real fish image dataset captured in deep-sea environments was constructed to verify the practical applicability of the proposed algorithm.

Adversarial Robustness for Deep Learning-Based Wildfire Prediction Models

Rapidly growing wildfires have recently devastated societal assets, exposing a critical need for early warning systems to expedite relief efforts. Smoke detection using camera-based Deep Neural Networks (DNNs) offers a promising solution for wildfire prediction. However, the rarity of smoke across time and space limits training data, raising model overfitting and bias concerns. Current DNNs, primarily Convolutional Neural Networks (CNNs) and transformers, complicate robustness evaluation due to architectural differences. To address these challenges, we introduce WARP (Wildfire Adversarial Robustness Procedure), the first model-agnostic framework for evaluating wildfire detection models’ adversarial robustness. WARP addresses inherent limitations in data diversity by generating adversarial examples through image-global and -local perturbations. Global and local attacks superimpose Gaussian noise and PNG patches onto image inputs, respectively; this suits both CNNs and transformers while generating realistic adversarial scenarios. Using WARP, we assessed real-time CNNs and Transformers, uncovering key vulnerabilities. At times, transformers exhibited over 70% precision degradation under global attacks, while both models generally struggled to differentiate cloud-like PNG patches from real smoke during local attacks. To enhance model robustness, we proposed four wildfire-oriented data augmentation techniques based on WARP’s methodology and results, which diversify smoke image data and improve model precision and robustness. These advancements represent a substantial step toward developing a reliable early wildfire warning system, which may be our first safeguard against wildfire destruction.

Enhancing waste classification accuracy with Channel and Spatial Attention-Based Multiblock Convolutional Network.

Municipal waste classification is significant for effective recycling and waste management processes that involve the classification of diverse municipal waste materials such as paper, glass, plastic, and organic matter using diverse techniques. Yet, this municipal waste classification process faces several challenges, such as high computational complexity, more time consumption, and high variability in the appearance of waste caused by variations in color, type, and degradation level, which makes an inaccurate waste classification process. To overcome these challenges, this research proposes a novel Channel and Spatial Attention-Based Multiblock Convolutional Network for accurately classifying municipal waste that utilizes a unique attention mechanism for enhancing feature learning and waste classification accuracy. In this research, the data augmentation technique is utilized to improve the size and diversity of the images, which creates a new municipal waste image from the existing image. After the augmentation process, the data preprocessing is performed through normalization, resizing, and dividing the images into smaller patches. In the feature extraction phase, each image patch's detailed representation is created by integrating and extracting the image's relevant features from the embedding space. Finally, the proposed Channel and Spatial Attention-Based Multiblock Convolutional Network predicts the types of municipal waste that are represented in each image patch by classifying the input images into diverse kinds of waste categories. The experimental validation exposed that the proposed Channel and Spatial Attention-Based Multiblock Convolutional Network effectively classifies the municipal waste images and achieves a higher accuracy of 98.73%, lower mean absolute error of 0.048, and lower root mean square error of 0.087 when compared to existing municipal waste classification strategies. These results prove that the proposed Channel and Spatial Attention-Based Multiblock Convolutional Network framework is more accurate, reliable, and well-suited to real-time municipal waste classification.

Enhanced brain tumor detection and segmentation using densely connected convolutional networks with stacking ensemble learning.

- Brain tumors (BT), both benign and malignant, pose a substantial impact on human health and need precise and early detection for successful treatment. Analysing magnetic resonance imaging (MRI) image is a common method for BT diagnosis and segmentation, yet misdiagnoses yield effective medical responses, impacting patient survival rates. Recent technological advancements have popularized deep learning-based medical image analysis, leveraging transfer learning to reuse pre-trained models for various applications. BT segmentation with MRI remains challenging despite advancements in image acquisition techniques. Accurate detection and segmentation are essential for proper diagnosis and treatment planning. This study aims to enhance BT detection and segmentation accuracy and effectiveness of categorization through the implementation of an advanced stacking ensemble learning (SEL) approach. This study explores the efficiency of SEL architecture in augmenting the precision of BT segmentation. SEL, a prominent approach within the machine learning paradigm, combines the predictions of base-level models and improves the overall performance of predictions in order to reduce the errors and biases of each model. The proposed approach involves designing a stacked DenseNet201 as the meta-model called SEL-DenseNet201, complemented by six diverse base models such as mobile network version 3 (MobileNet-v3), 3-dimensional convolutional neural network (3D-CNN), visual geometry group network with 16 and 19 layers (VGG-16 and VGG-19), residual network with 50 layers (ResNet50), and Alex network (AlexNet). The strengths of the base models are calculated to capture distinct aspects of the BT MRI, aiming for enhanced segmentation performance. The proposed SEL-DenseNet201 is trained using BT MRI datasets. The augmentation techniques are applied to MRI scans to balance and enhance the model performance through the application of image enhancement and segmentation techniques. The proposed SEL-DenseNet201 achieves impressive results with an accuracy of 99.65% and a dice coefficient of 97.43%. These outcomes underscore the superiority of the proposed model over existing approaches. This study holds the potential to be an initial screening approach for early BT detection, with a high success rate.

Leveraging Deep Learning in Remote Sensing: A Novel Approach for Agricultural Greenhouse Detection and Innovation Management

Innovation management plays a pivotal role in harnessing advanced technologies to drive progress across diverse fields. In this context, integrating deep learning models within remote sensing technologies presents transformative potential for monitoring, change detection, analysis, and decision-making in fields such as agriculture, urban planning, and environmental studies. This study examines the role of sophisticated deep learning approaches in analyzing high-resolution satellite imagery to improve the detection of agricultural greenhouses. Using MMSegmentation (DeepLabv3Plus) with multispectral data at 0.7-meter resolution, the research addresses the limitations of traditional methods by substantially enhancing detection accuracy and efficiency. To address data scarcity and increase model robustness, advanced data augmentation techniques—such as rotations, scaling, and flipping - expand dataset diversity, fostering adaptability and performance under diverse conditions. The study also assesses the impact of environmental factors, including seasonal variations and weather, on model performance. Suggested improvements include expanding the dataset to encompass a wider variety of greenhouse types and conditions, incorporating high-resolution or hyperspectral imagery for finer details, and building multi-temporal datasets to capture dynamic environmental changes. The findings underscore the importance of advanced innovation management in enhancing remote sensing applications, offering actionable insights for agricultural management in Albania and similar regions. This research contributes to the broader field of innovation management by showcasing how deep learning can revolutionize practical applications in agriculture

RTACompensator: Leveraging AraBERT and XGBoost for Automated Road Accident Compensation

Road traffic accidents (RTAs) are a significant public health and safety concern, resulting in numerous injuries and fatalities. The growing number of cases referred to traffic accident rooms in courts has underscored the necessity for an automated solution to determine victim indemnifications, particularly given the limited number of specialized judges and the complexity of cases involving multiple victims. This paper introduces RTACompensator, an artificial intelligence (AI)-driven decision support system designed to automate indemnification calculations for road accident victims. The system comprises two main components: a calculation module that determines initial compensation based on factors such as age, salary, and medical assessments, and a machine learning (ML) model that assigns liability based on police accident reports. The model uses Arabic bidirectional encoder representations from transformer (AraBERT) embeddings to generate contextual vectors from the report, which are then processed by extreme gradient boosting (XGBoost) to determine responsibility. The model was trained on a purpose-built Arabic corpus derived from real-world legal judgments. To expand the dataset, two data augmentation techniques were employed: multilingual bidirectional encoder representations from transformers (BERT) and Gemini, developed by Google DeepMind. Experimental results demonstrate the model’s effectiveness, achieving accuracy scores of 97% for the BERT-augmented corpus and 97.3% for the Gemini-augmented corpus. These results underscore the system’s potential to improve decision-making in road accident indemnifications. Additionally, the constructed corpus provides a valuable resource for further research in this domain, laying the groundwork for future advancements in automating and refining the indemnification process.

Comparison of Neural Network Structures for Identifying Shockable Rhythm During Cardiopulmonary Resuscitation

Background/Objectives: Minimizing interruptions in chest compressions is very important when resuscitating patients with cardiac arrest. Recently, research has analyzed electrocardiograms (ECGs) during chest compressions using convolutional neural networks (CNNs). This study aimed to compare the accuracy of deeper neural networks and more advanced structures. Methods: ECGs with chest compression artifacts were obtained from patients who visited the emergency department of Korea University Ansan Hospital from September 2019 to February 2024. We compared the accuracy of a deeper CNN, long short-term memory (LSTM), and a CNN with an attention mechanism and residual block against a reference model. The input of the model was 5 s ECG segments with compression artifacts, and the output was the probability that the ECG with the artifacts was a shockable rhythm. Results: A total of 1889 ECGs with compression artifacts from 172 patients were included in this study. There were 969 ECGs annotated as shockable and 920 as non-shockable. The area under the receiver operating characteristic curve (AUROC) of the reference model was 0.8672. The AUROCs of the deeper CNN for five and seven layers were 0.7374 and 0.6950, respectively. The AUROCs of LSTM and bidirectional LSTM were 0.7719 and 0.8287, respectively. The AUROC of the CNN with the attention mechanism and residual block was 0.7759. Conclusions: CNNs with deeper layers or those incorporating attention mechanisms, residual blocks, and LSTM architectures did not exhibit better accuracy. To improve the model accuracy, a larger dataset or advanced augmentation techniques may be required, rather than complicating the structure of the model.

BabyFM: Towards accurate 3D baby facial models using spectral decomposition and asymmetry swapping.

In this paper, we present the first publicly available 3D statistical facial shape model of babies, the Baby Face Model (BabyFM). Constructing a model of the facial geometry of babies entails specific challenges, such as occlusions, extreme and uncontrollable expressions, and data shortage. We address these challenges by proposing (1) a non-template dependent method that jointly estimates a 3D facial baby-specific template and the point-to-point correspondences; (2) a novel method to establish correspondences based on the spectral decomposition of the Laplace Beltrami Operator, which provides a more robust theoretical foundation than state-of-the-art methods; and (3) an asymmetry-swapping strategy to alleviate the shortage of large scale datasets by decoupling the identity-related and the asymmetry-related shape deformation fields. The latter leads to a data augmentation technique that we integrate within the Gaussian Process Morphable Model framework, providing a simple way of combining synthetic or sample covariance functions. We exhaustively evaluate each stage of our method and demonstrate that (1) when aiming at the 3D facial geometry of a baby, a specific model of babies is needed, since the pre-built publicly available models constructed with adults or older children are not able to accurately represent the facial shape of babies; (2) our spectral approach improves correspondences accuracy with respect to state-of-the-art-methods; and (3) the proposed data augmentation technique enhances the robustness of the BabyFM.

Data Augmentation in Earth Observation: A Diffusion Model Approach

High-quality Earth Observation (EO) imagery is essential for accurate analysis and informed decision making across sectors. However, data scarcity caused by atmospheric conditions, seasonal variations, and limited geographical coverage hinders the effective application of Artificial Intelligence (AI) in EO. Traditional data augmentation techniques, which rely on basic parameterized image transformations, often fail to introduce sufficient diversity across key semantic axes. These axes include natural changes such as snow and floods, human impacts like urbanization and roads, and disasters such as wildfires and storms, which limits the accuracy of AI models in EO applications. To address this, we propose a four-stage data augmentation approach that integrates diffusion models to enhance semantic diversity. Our method employs meta-prompts for instruction generation, vision–language models for rich captioning, EO-specific diffusion model fine-tuning, and iterative data augmentation. Extensive experiments using four augmentation techniques demonstrate that our approach consistently outperforms established methods, generating semantically diverse EO images and improving AI model performance.

DGA-Based Fault Diagnosis Using Self-Organizing Neural Networks with Incremental Learning

Power transformers are vital components of electrical power systems, ensuring reliable and efficient energy transfer between high-voltage transmission and low-voltage distribution networks. However, they are prone to various faults, such as insulation breakdowns, winding deformations, partial discharges, and short circuits, which can disrupt electrical service, incur significant economic losses, and pose safety risks. Traditional fault diagnosis methods, including visual inspection, dissolved gas analysis (DGA), and thermal imaging, face challenges such as subjectivity, intermittent data collection, and reliance on expert interpretation. To address these limitations, this paper proposes a novel distributed approach for multi-fault diagnosis of power transformers based on a self-organizing neural network combined with data augmentation and incremental learning techniques. The proposed framework addresses critical challenges, including data quality issues, computational complexity, and the need for real-time adaptability. Data cleaning and preprocessing techniques improve the reliability of input data, while data augmentation generates synthetic samples to mitigate data imbalance and enhance the recognition of rare fault patterns. A two-stage classification model integrates unsupervised and supervised learning, with k-means clustering applied in the first stage for initial fault categorization, followed by a self-organizing neural network in the second stage for refined fault diagnosis. The self-organizing neural network dynamically suppresses inactive nodes and optimizes its training parameter set, reducing computational complexity without sacrificing accuracy. Additionally, incremental learning enables the model to continuously adapt to new fault scenarios without modifying its architecture, ensuring real-time performance and adaptability across diverse operational conditions. Experimental validation demonstrates the effectiveness of the proposed method in achieving accurate, efficient, and adaptive fault diagnosis for power transformers, outperforming traditional and conventional machine learning approaches. This work provides a robust framework for integrating advanced machine learning techniques into power system monitoring, paving the way for automated, real-time, and reliable transformer fault diagnosis systems.

SCAGAN: Wireless Capsule Endoscopy Lesion Image Generation Model Based on GAN

The wireless capsule endoscope (WCE) has been utilized for human digestive tract examinations for over 20 years. Given the complex environment of the digestive tract and the challenge of detecting multi-category lesion images, enhancing model generalization ability is crucial. However, traditional data augmentation methods struggle to generate sufficiently diverse data. In this study, we propose a novel generative adversarial network, Special Common Attention Generative Adversarial Network (SCAGAN), to generate lesion images for capsule endoscopy. The SCAGAN model can adaptively integrate both the internal features and external global dependencies of the samples, enabling the generator to not only accurately capture the key structures and features of capsule endoscopic images, but also enhance the modeling of lesion complexity. Additionally, SCAGAN incorporates global context information to improve the overall consistency and detail of the generated images. To further enhance adaptability, self-modulation normalization is used, along with the Structural Similarity Index (SSIM) loss function to ensure structural authenticity. The Differentiable Data Augmentation (DiffAug) technique is employed to improve the model’s performance in small sample environments and balance the training process by adjusting learning rates to address issues of slow learning due to discriminator regularization. Experimental results show that SCAGAN significantly improves image quality and diversity, achieving state-of-the-art (SOTA) performance in the Frechet Inception Distance (FID) index. Moreover, when the generated lesion images were added to the dataset, the mean average precision (mAP) of the YOLOv9-based lesion detection model increased by 1.495%, demonstrating SCAGAN’s effectiveness in optimizing lesion detection. SCAGAN effectively addresses the challenges of lesion image generation for capsule endoscopy, improving both image quality and detection model performance. The proposed approach offers a promising solution for enhancing the training of lesion detection models in the context of capsule endoscopy.

AquaPile-YOLO: Pioneering Underwater Pile Foundation Detection with Forward-Looking Sonar Image Processing

Underwater pile foundation detection is crucial for environmental monitoring and marine engineering. Traditional methods for detecting underwater pile foundations are labor-intensive and inefficient. Deep learning-based image processing has revolutionized detection, enabling identification through sonar imagery analysis. This study proposes an innovative methodology, named the AquaPile-YOLO algorithm, for underwater pile foundation detection. Our approach significantly enhances detection accuracy and robustness by integrating multi-scale feature fusion, improved attention mechanisms, and advanced data augmentation techniques. Trained on 4000 sonar images, the model excels in delineating pile structures and effectively identifying underwater targets. Experimental data show that the model can achieve good target identification results in similar experimental scenarios, with a 96.89% accuracy rate for underwater target recognition.