Search Results (2,160)

Ultrasound (US) remains the main modality for the differential diagnosis of changes revealed by mammography. However, the US images themselves are subject to various types of noise and artifacts from reflections, which can worsen the quality of their analysis. Deep learning methods have a number of disadvantages, including the often insufficient substantiation of the model, and the complexity of collecting a representative training database. Therefore, it is necessary to develop effective algorithms for the segmentation, classification, and analysis of US images. The aim of the work is to develop a method for the automated detection of pathological lesions in breast US images and their segmentation. A method is proposed that includes two stages of video image processing: (1) searching for a region of interest using a random forest classifier, which classifies normal tissues, (2) selecting the contour of the lesion based on the difference in brightness of image pixels. The test set included 52 ultrasound videos which contained histologically proven suspicious lesions. The average frequency of lesion detection per frame was 91.89%, and the average accuracy of contour selection according to the IoU metric was 0.871. The proposed method can be used to segment a suspicious lesion. Full article

Land use land cover (LULC) changes due to rapid urbanization pose critical challenges to sustainable development, particularly in arid and semi-arid regions like Saudi Arabia, where cities such as Abha are experiencing unprecedented expansion. Urban sprawl is accelerating environmental degradation, affecting key natural resources such as vegetation, water bodies, and barren land. This study introduces an advanced machine learning (ML) and deep learning (DL)-based framework for high-accuracy LULC classification, urban sprawl quantification, and ecosystem service assessment, providing a more precise and scalable approach compared to traditional remote sensing techniques. A hybrid methodology combining ML models—Random Forest, Artificial Neural Networks, Gradient Boosting Machine, and LightGBM—with a 1D Convolutional Neural Network (CNN) was fine-tuned using grid search optimization to enhance classification accuracy. The integration of deep learning improves feature extraction and classification consistency, achieving an AUC of 0.93 for Dense Vegetation and 0.82 for Cropland, outperforming conventional classification methods. The study also applies the Markov transition model to project land cover changes, offering a probabilistic understanding of urban expansion trends and ecosystem dynamics, providing a significant improvement over static LULC assessments by quantifying transition probabilities and predicting future land cover transformations. The results reveal that urban areas in Abha expanded by 120.74 km² between 2014 and 2023, with barren land decreasing by 557.09 km² and cropland increasing by 205.14 km². The peak ecosystem service value (ESV) loss was recorded at USD 125,662.7 between 2017 and 2020, but subsequent land management efforts improved ESV to USD 96,769.5 by 2023. The resilience and recovery of natural land cover types, particularly barren land (44,163 km² recovered by 2023), indicate the potential for targeted restoration strategies. This study advances urban sustainability research by integrating state-of-the-art deep learning models with Markov-based land change predictions, enhancing the accuracy and predictive capability of LULC assessments. The findings highlight the need for proactive land management policies to mitigate the adverse effects of urban sprawl and promote sustainable ecosystem service recovery. The methodological advancements presented in this study provide a scalable and adaptable framework for future urbanization impact assessments, particularly in rapidly developing regions. Full article

Objectives: The accurate prediction of lymph node metastasis (LNM) and lymphovascular invasion (LVI) is crucial for determining treatment strategies for early gastric cancer (EGC). This study aimed to develop and validate a deep learning-based clinical decision support system (CDSS) to predict LNM including LVI in EGC using real-world data. Methods: A deep learning-based CDSS was developed by integrating endoscopic images, demographic data, biopsy pathology, and CT findings from the data of 2927 patients with EGC across five institutions. We compared a transformer-based model to an image-only (basic convolutional neural network (CNN)) model and a multimodal classification (CNN with random forest) model. Internal testing was conducted on 449 patients from the five institutions, and external validation was performed on 766 patients from two other institutions. Model performance was assessed using the area under the receiver operating characteristic curve (AUC), probability density function, and clinical utility curve. Results: In the training, internal, and external validation cohorts, LNM/LVI was observed in 379 (12.95%), 49 (10.91%), 15 (9.09%), and 41 (6.82%) patients, respectively. The transformer-based model achieved an AUC of 0.9083, sensitivity of 85.71%, and specificity of 90.75%, outperforming the CNN (AUC 0.5937) and CNN with random forest (AUC 0.7548). High sensitivity and specificity were maintained in internal and external validations. The transformer model distinguished 91.8% of patients with LNM in the internal validation dataset, and 94.0% and 89.1% in the two different external datasets. Conclusions: We propose a deep learning-based CDSS for predicting LNM/LVI in EGC by integrating real-world data, potentially guiding treatment strategies in clinical settings. Full article

Forests play a key role in carbon sequestration and oxygen production. They significantly contribute to carbon peaking and carbon neutrality goals. Accurate estimation of forest carbon stocks is essential for a precise understanding of the carbon sequestration capacity of forest ecosystems. Remote sensing technology, with its wide observational coverage, strong timeliness, and low cost, is essential for carbon stock estimation research. However, challenges in data acquisition and processing include data variability, signal saturation in dense forests, and environmental limitations. These factors hinder accurate carbon stock estimation. This review summarizes the current state of research on forest carbon stock estimation from two aspects, namely remote sensing data and estimation methods, highlighting both the advantages and the limitations of various data sources and models. It also explores technological innovations and cutting-edge research in the field, focusing on deep learning techniques, optical vegetation thickness estimation methods, and the impact of forest–climate interactions on carbon stock estimation. Finally, the review discusses the current challenges in the field, including issues related to remote sensing data quality, model adaptability, forest stand complexity, and uncertainties in the estimation process. Based on these challenges, the paper looks ahead to future trends, proposing potential technological breakthroughs and pathways. The aim of this study is to provide theoretical support and methodological guidance for researchers in related fields. Full article

In the digital age, the rapid proliferation of misinformation and disinformation poses a critical challenge to societal trust and the integrity of public discourse. This study presents a comprehensive machine learning framework for fake news detection, integrating advanced natural language processing techniques and deep learning architectures. We rigorously evaluate a diverse set of detection models across multiple content types, including social media posts, news articles, and user-generated comments. Our approach systematically compares traditional machine learning classifiers (Naïve Bayes, SVMs, Random Forest) with state-of-the-art deep learning models, such as CNNs, LSTMs, and BERT, while incorporating optimized vectorization techniques, including TF-IDF, Word2Vec, and contextual embeddings. Through extensive experimentation across multiple datasets, our results demonstrate that BERT-based models consistently achieve superior performance, significantly improving detection accuracy in complex misinformation scenarios. Furthermore, we extend the evaluation beyond conventional accuracy metrics by incorporating the Matthews Correlation Coefficient (MCC) and Receiver Operating Characteristic–Area Under the Curve (ROC–AUC), ensuring a robust and interpretable assessment of model efficacy. Beyond technical advancements, we explore the ethical implications of automated misinformation detection, addressing concerns related to censorship, algorithmic bias, and the trade-off between content moderation and freedom of expression. This research not only advances the methodological landscape of fake news detection but also contributes to the broader discourse on safeguarding democratic values, media integrity, and responsible AI deployment in digital environments. Full article

The Qinghai–Tibet Plateau (QTP), one of China’s most snow-rich regions, has an extremely fragile ecosystem, with drought being the primary driver of ecological degradation. Given that the water resources in this region predominantly exist in the form of snow, high-spatiotemporal-resolution snow mapping is essential for understanding snow distribution and managing snow water resources effectively. However, although FY-4A/AGRI is capable of obtaining wide-area remote sensing data, only the first to third bands have a resolution of 1 km, which greatly limits its ability to produce high-resolution snow maps. This study proposes U-SwinFusionNet (USFNet), a deep learning-based snow cover retrieval algorithm that leverages the multi-scale advantages of FY-4A/AGRI remote sensing data in the shortwave infrared and visible bands. By integrating 1 km and 2 km resolution remote sensing imagery with auxiliary terrain information, USFNet effectively enhances snow cover mapping accuracy. The proposed model innovatively combines Swin Transformer and convolutional neural networks (CNNs) to capture both global contextual information and local spatial details. Additionally, an Attention Feature Fusion Module (AFFM) is introduced to align and integrate features from different modalities through an efficient attention mechanism, while the Feature Complementation Module (FCM) facilitates interactions between the encoded and decoded features. As a result, USFNet produces snow cover maps with a spatial resolution of 1 km. Experimental comparisons with Artificial Neural Networks (ANNs), Random Forest (RF), U-Net, and ResNet-FSC demonstrate that USFNet exhibits superior robustness, enhanced snow cover continuity, and lower error rates. The model achieves a correlation coefficient of 0.9126 and an R² of 0.7072. Compared to the MOD10A1 snow product, USFNet demonstrates an improved sensitivity to fragmented and low-snow-cover areas while ensuring more natural snow boundary transitions. Full article

Mass spectrometry (MS) data present challenges for machine learning (ML) classification due to their high dimensionality, complex feature distributions, batch effects, and intensity discrepancies, often hindering model generalization and efficiency. To address these issues, this study introduces the Efficient Quick 1D Lite Convolutional Neural Network (CNN) Ensemble Classifier (EQLC-EC), integrating 1D convolutional networks with reshape layers and dual voting mechanisms for enhanced feature representation and classification performance. Validation was performed on five publicly available MS datasets, each featured in high-impact publications. EQLC-EC underwent comprehensive evaluation against classical machine learning (ML) models (e.g., support vector machine (SVM), random forest) and the leading deep learning methods reported in these studies. EQLC-EC demonstrated dataset-specific improvements, including enhanced classification accuracy (1–5% increase) and reduced standard deviation (1–10% reduction). Performance differences between soft and hard voting mechanisms were negligible (<1% variation in accuracy and standard deviation). EQLC-EC presents a powerful and efficient tool for MS data analysis with potential applications across metabolomics and proteomics. Full article

Intelligent fault diagnosis (IFD) plays a crucial role in reducing maintenance costs and enhancing the reliability of safety-critical energy systems (SCESs). In recent years, deep learning-based IFD methods have achieved high fault diagnosis accuracy extracting implicit higher-order correlations between features. However, the excessive long training time of deep learning models conflicts with the requirements of real-time analysis for IFD, hindering their further application in practical industrial environments. To address the aforementioned challenge, this paper proposes an innovative IFD method for SCES that combines the particle swarm optimization (PSO) algorithm and the ensemble broad learning system (EBLS). Specifically, the broad learning system (BLS), known for its low time complexity and high classification accuracy, is adopted as an alternative to deep learning for fault diagnosis in SCES. Furthermore, EBLS is designed to enhance model stability and classification accuracy with high-dimensional small samples by incorporating the random forest (RF) algorithm and an ensemble strategy into the traditional BLS framework. In order to reduce the computational cost of the EBLS, which is constrained by the selection of its hyperparameters, the PSO algorithm is employed to optimize the hyperparameters of the EBLS. Finally, the model is validated through simulated data from a complex nuclear power plant (NPP). Numerical experiments reveal that the proposed method significantly improved the diagnostic efficiency while maintaining high accuracy. In summary, the proposed approach shows great promise for boosting the capabilities of the IFD models for SCES. Full article

Natural gas, as a sustainable and cleaner energy source, still holds a crucial position in the energy transition stage. In shale gas exploration, total organic carbon (TOC) content plays a crucial role, with log data proving beneficial in predicting total organic carbon content in shale reservoirs. However, in complex coal-bearing layers like the marine–continental transitional Shanxi Formation, traditional prediction methods exhibit significant errors. Therefore, this study proposes an advanced, cost- and time-saving deep learning approach to predict TOC in marine–continental transitional shale. Five well log records from the study area were used to evaluate five machine learning models: K-Nearest Neighbors (KNNs), Random Forest (RF), Gradient Boosting Decision Tree (GBDT), Extreme Gradient Boosting (XGB), and Deep Neural Network (DNN). The predictive results were compared with conventional methods for accurate TOC predictions. Through K-fold cross-validation, the ML models showed superior accuracy over traditional models, with the DNN model displaying the lowest root mean square error (RMSE) and mean absolute error (MAE). To enhance prediction accuracy, δR was integrated as a new parameter into the ML models. Comparative analysis revealed that the improved DNN-R model reduced MAE and RMSE by 57.1% and 70.6%, respectively, on the training set, and by 59.5% and 72.5%, respectively, on the test set, compared to the original DNN model. The Williams plot and permutation importance confirmed the reliability and effectiveness of the enhanced DNN-R model. The results indicate the potential of machine learning technology as a valuable tool for predicting crucial parameters, especially in marine–continental transitional shale reservoirs lacking sufficient core samples and relying solely on basic well-logging data, signifying its importance for effective shale gas assessment and development. Full article

Background: Cardiovascular disease (CVD) is a prominent determinant of mortality, accounting for 17 million lives lost across the globe each year. This underscores its severity as a critical health issue. Extensive research has been undertaken to refine the forecasting of CVD in patients using various supervised, unsupervised, and deep learning approaches. Methods: This study presents HeartEnsembleNet, a novel hybrid ensemble learning model that integrates multiple machine learning (ML) classifiers for CVD risk assessment. The model is evaluated against six classical ML classifiers, including support vector machine (SVM), gradient boosting (GB), decision tree (DT), logistic regression (LR), k-nearest neighbor (KNN), and random forest (RF). Additionally, we compare HeartEnsembleNet with Hybrid Random Forest Linear Models (HRFLM) and ensemble techniques including stacking and voting. Results: Employing a dataset of 70,000 cardiac patients with 12 clinical attributes, our proposed model achieves a notable accuracy of 92.95% and a precision of 93.08%. Conclusions: These results highlight the effectiveness of hybrid ensemble learning in enhancing CVD risk prediction, offering a promising framework for clinical decision support. Full article

This study addresses the urgent need for effective methods to monitor and conserve Araucaria angustifolia, a critically endangered species of immense ecological and cultural significance in southern Brazil. Using high-resolution satellite images from Google Earth, we apply the YOLOv7x deep learning model to detect this species in two distinct urban contexts in Curitiba, Paraná: isolated trees across the urban landscape and A. angustifolia individuals within forest remnants. Data augmentation techniques, including image rotation, hue and saturation adjustments, and mosaic augmentation, were employed to increase the model’s accuracy and robustness. Through a 5-fold cross-validation, the model achieved a mean Average Precision (AP) of 90.79% and an F1-score of 88.68%. Results show higher detection accuracy in forest remnants, where the homogeneous background of natural landscapes facilitated the identification of trees, compared to urban areas where complex visual elements like building shadows presented challenges. To reduce false positives, especially misclassifications involving palm species, additional annotations were introduced, significantly enhancing performance in urban environments. These findings highlight the potential of integrating remote sensing with deep learning to automate large-scale forest inventories. Furthermore, the study highlights the broader applicability of the YOLOv7x model for urban forestry planning, offering a cost-effective solution for biodiversity monitoring. The integration of predictive data with urban forest maps reveals a spatial correlation between A. angustifolia density and the presence of forest fragments, suggesting that the preservation of these areas is vital for the species’ sustainability. The model’s scalability also opens the door for future applications in ecological monitoring across larger urban areas. As urban environments continue to expand, understanding and conserving key species like A. angustifolia is critical for enhancing biodiversity, resilience, and addressing climate change. Full article

This study explores the application of time series, machine learning (ML), and deep learning (DL) models to predict the prices and performance of covered call ETFs. Utilizing historical data from major covered call ETFs like QYLD, XYLD, JEPI, JEPQ, and RYLD, the research assesses the predictive accuracy and reliability of different forecasting approaches. It compares traditional time series methods, including ARIMA and Heterogeneous Autoregressive Model (HAR), with advanced ML techniques such as Random Forests (RF) and Support Vector Regression (SVR), as well as DL models like Recurrent Neural Networks (RNN) and Convolutional Neural Networks (CNN). Model performance is evaluated using metrics such as Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), Akaike Information Criterion (AIC), and Bayesian Information Criterion (BIC). Results indicate that the DL models are effective at identifying the nonlinear patterns and temporal dependencies in the price movements of covered call ETFs, outperforming both traditional time series and ML techniques. These findings enhance the existing financial forecasting literature and offer valuable insights for investors and portfolio managers aiming to improve their strategies using covered call ETFs. Full article

Capacity fade in lithium-ion batteries (LIBs) poses challenges for various industries. Predicting and preventing this fade is crucial, and hybrid methods for estimating remaining useful life (RUL) have become prevalent and achieved significant advancements. In this paper, we introduce a hybrid voting ensemble that combines Gradient Boosting, Random Forest, and K-Nearest Neighbors to forecast the fading capacity trend and knee point. We conducted extensive experiments using the CALCE CS2 datasets. The results indicate that our proposed approach outperforms single deep learning methods for RUL prediction and accurately identifies the knee point. Beyond prediction, this innovative method can potentially be integrated into real-world applications for broader use. Full article

Background/Objectives: Falls among the older adult population represent a significant public health concern, often leading to diminished quality of life and serious injuries that escalate healthcare costs, and they may even prove fatal. Accurate fall risk prediction is therefore crucial for implementing timely preventive measures. However, to date, there is no definitive metric to identify individuals with high risk of experiencing a fall. To address this, the present study proposes a novel approach that transforms biomechanical time-series data, derived from gait analysis, into visual representations to facilitate the application of deep learning (DL) methods for fall risk assessment. Methods: By leveraging convolutional neural networks (CNNs) and Siamese neural networks (SNNs), the proposed framework effectively addresses the challenges of limited datasets and delivers robust predictive capabilities. Results: Through the extraction of distinctive gait-related features and the generation of class-discriminative activation maps using Grad-CAM, the random forest (RF) machine learning (ML) model not only achieves commendable accuracy (83.29%) but also enhances explainability. Conclusions: Ultimately, this study underscores the potential of advanced computational tools and machine learning algorithms to improve fall risk prediction, reduce healthcare burdens, and promote greater independence and well-being among the older adults. Full article

The exponential growth of patent datasets poses a significant challenge in filtering relevant documents for research and innovation. Traditional semantic search methods based on keywords often fail to capture the complexity and variability in multidisciplinary terminology, leading to inefficiencies. This study addresses the problem by systematically evaluating supervised and unsupervised machine learning (ML) techniques for document relevance filtering across five technology domains: solid-state batteries, electric vehicle chargers, connected vehicles, electric vertical takeoff and landing aircraft, and light detecting and ranging (LiDAR) sensors. The contributions include benchmarking the performance of 10 classical models. These models include extreme gradient boosting, random forest, and support vector machines; a deep artificial neural network; and three natural language processing methods: latent Dirichlet allocation, non-negative matrix factorization, and k-means clustering of a manifold-learned reduced feature dimension. Applying these methods to more than 4200 patents filtered from a database of 9.6 million patents revealed that most supervised ML models outperform the unsupervised methods. An average of seven supervised ML models achieved significantly higher precision, recall, and F1-scores across all technology domains, while unsupervised methods show variability depending on domain characteristics. These results offer a practical framework for optimizing document relevance filtering, enabling researchers and practitioners to efficiently manage large datasets and enhance innovation. Full article