Search Results (874)

Flow patterns in vertical wellbores are highly complex and variable. Classical theoretical models for pressure drop prediction frequently yield significant errors when applied to different geological blocks. However, existing correction models suffer from incomplete coverage of flow patterns. Therefore, it is necessary to develop new pressure drop prediction models specifically for gas–liquid two-phase flow in vertical wellbores under various flow patterns. This study conducted physical experiments on gas–liquid two-phase flow in vertical wellbores, successfully reproducing four typical flow patterns—bubbly flow, slug flow, churn flow, and annular flow—and determining their transition boundaries. Based on the experimental data, a systematic comparison was performed among four classic flow pattern discrimination models: Aziz, Beggs–Brill, Mukherjee–Brill, and Ansari. The results indicated that the Aziz model demonstrates superior applicability for identifying vertical flow patterns. To address the substantial prediction errors of the Aziz model in pressure drop calculations, the liquid holdup ratio and friction factor under different flow patterns were manually corrected using the experimental data, yielding a new pressure drop prediction model (Model 1). Furthermore, the particle swarm optimization (PSO) algorithm was introduced to further automatically optimize and fit the model parameters, thereby establishing another new pressure drop prediction model (Model 2) specifically tailored for different flow patterns. Validated against the experimental measured data, the new Model 2 achieved a Mean Absolute Percentage Error (MAPE) of 11.9% and a Root Mean Square Error (RMSE) of 1.9 kPa. Further verified by independent validation experiments outside the calibration dataset, Model 2 achieves an average prediction error of 12.0%, maintaining stable and high prediction accuracy. In comparison, the Aziz model and the new Model 1 yielded MAPE/RMSE values of 50.6%/5.3 kPa and 18.2%/4.9 kPa, respectively. The errors of the new Model 2 are markedly lower than those of the aforementioned models, demonstrating its superior accuracy in calculating pressure drops under various flow patterns. These findings provide a more accurate and reliable theoretical model for pressure drop calculation in gas–liquid two-phase flow within vertical wellbores, thereby laying a solid foundation for numerical simulation history matching and subsequent production forecasting. Full article

Posture transition behavior in sows approaching parturition provides an important physiological cue for farrowing prediction. However, manual monitoring is time-consuming, labor-intensive and difficult to sustain under nighttime production conditions, while existing machine vision approaches remain limited in their ability to represent continuous posture transitions in complex farm environments. Here, we propose an event-level posture transition recognition framework that integrates YOLOv11n with an RGB–Flow cross-modal temporal network. YOLOv11n is first used to detect basic sow postures at the frame level, after which candidate transition events are automatically generated and refined according to temporal state changes. For each event segment, RGB appearance features and optical-flow motion features are extracted to construct dual-branch spatio-temporal representations. We further develop a multi-scale cross-modal attention temporal network (MS-CMATNet) for event-level behavior classification. The network captures local temporal dynamics through a multi-scale module, enhances interactions between RGB and Flow representations through cross-modal attention, and improves feature discriminability and stability by incorporating temporal–channel attention blocks (TCBAM) and an auxiliary cross-modal consistency loss (AuxCross). Experiments show that MS-CMATNet achieves an Accuracy of 88.14%, a Macro-Recall of 84.04%, and a Weighted-F1 score of 87.66% under the fixed training/validation split, outperforming the compared machine learning models, deep temporal models, and representative temporal and cross-modal baselines. Repeated stratified cross-validation and paired t-tests further confirm that MS-CMATNet achieves statistically reliable improvements over most compared baselines, particularly in Macro-F1 and Weighted-F1. These findings demonstrate the potential of the proposed framework for automated farrowing prediction in smart livestock farming. Full article

Life skills are essential to human functioning, particularly during the transition into adulthood. This study analyzed the validity of two related measures of life skills (Life Skills Acquisition Questionnaire—LSAQ; and Life Skills Questionnaire—LSQ), which may serve as useful tools for understanding which life skills are learned and how their acquisition progresses. A quantitative cross-sectional study was conducted with a final sample of 1148 high school students who completed LSAQ, LSQ, and a measure of academic achievement expectations (AAEs). Factorial structure, reliability, convergent, discriminant and predictive validity, as well as temporal stability was assessed for both measures. LSAQ results endorsed either a four-factor model or a second-order latent factor, both encompassing key stages of life skills development (i.e., motivation, learning, automatization, and transference). LSQ results supported validity for six life skills (motivation, time management, stress management, communication, teamwork, and leadership). Both instruments showed the predictive validity of AAEs and good temporal stability. Both measures can help practitioners and researchers evaluate whether opportunities such as intervention programs affect the acquisition and diversity of life skills that students gain. They are also useful for testing theoretical models of life skills and for providing insights into how these skills are developed. Full article

Landslide susceptibility mapping (LSM) serves as a fundamental technical support for geohazard prevention and mitigation across mountainous terrains. This research constructs a multi-scale terrain unit integrated modeling framework targeting complex mountainous geomorphic settings, taking Zhenping County as the research object. Multi-resolution digital elevation model (DEM) datasets, multi-source satellite remote sensing imagery (GF-2), geological vector datasets and hydrological survey data are jointly adopted as the basic data source. The r.slopeunits module embedded in GRASS GIS is utilized to automatically segment slope units, and a comprehensive composite index S, coupling slope partition quality indicator F and model prediction accuracy metric R, is proposed to adaptively optimize two critical slope-unit hyperparameters: circular variance (c) and minimum unit area (a). Four DEM spatial resolutions (15 m, 25 m, 50 m, 100 m) are systematically calibrated with 42 groups of c–a parameter combinations to screen out the optimal slope-unit segmentation scheme (c = 0.1, a = 200,000 m²). Twelve landslide predisposing covariates covering topography, hydrology, lithology, human engineering activities and land cover are selected after multicollinearity diagnosis via Variance Inflation Factor and mean utility factor contribution evaluation. Logistic regression tree (LMT), LMT-Adaboost and LMT-Random Subspace are compared by random cross-validation and spatial block cross-validation. Parameter sensitivity analysis is further carried out to quantify the stability of model outputs against DEM resolution and slope-unit parameter perturbations. The LMT-RSM ensemble achieved the highest spatial cross-validation AUC (0.954 ± 0.019), outperforming LMT (0.925 ± 0.023) and AdaBoost-LMT (0.934 ± 0.021). The DeLong test confirmed that LMT-RSM’s superiority over LMT is statistically significant (p < 0.0001). The proportion of landslides in the very high and high susceptibility zones under the LMT-RSM model reached 95.98%, demonstrating relatively excellent spatial discrimination. This study provides an operational framework combining optimized slope units, ensemble learning, and spatially explicit validation for robust LSM in complex terrain, and offers a reproducible technical pathway for landslide risk prevention in mountainous regions. Full article

Background: Cardiovascular diseases (CVDs) are among the leading causes of death globally. In order to treat CVDs successfully in the early stages, it is crucial to diagnose them in time. The ECG is one of the most common and non-invasive methods to detect heart rhythms and to diagnose arrhythmias. However, the analysis of ECG recordings manually requires a lot of time and experience because the morphology of ECG signals and the characteristics of their waveforms are very complex and show large overlaps between different types of arrhythmias. So far, various approaches for automated analysis of ECG signals have been developed, mostly based on deep learning (DL). In general, these methods are able to analyze ECG signals automatically and to detect different types of arrhythmias. Most approaches, however, are based on a purely data-driven feature learning and do not pay attention to the morphology-sensitive temporal structure of ECG signals, which is important for a discriminative diagnosis of arrhythmias. Methods: In this paper, we propose an Attention-Based Morphology-Aware (ABMA) framework to leverage multilead ECG signals in conjunction with automatically computed physiological features using a hybrid deep learning architecture. ABMA leverages multi-scale convolutional neural networks to learn local morphology features, and bidirectional long short-term memory (BiLSTM) networks to model temporal rhythms in ECG signals. We designed an ABMA module that incorporates a morphology scoring network (MSN) in order to (1) estimate the morphology-aware importance of different ECG segments and (2) learn the temporal importance of ECG features. The learned attention weights enable learning to focus on key sections of ECG signals without predefined boundaries or manual annotation of fiducial points. To understand the contribution of each individual component of the framework, we performed an extensive ablation study, where we removed the handcrafted feature branch, the ABMA module, the MSN, and the multi-head attention mechanism, one at a time, and compared the results against a fixed set of experimental configurations. Results: To assess the performance of the proposed framework in three-class classification between sinus rhythm (SA), atrial fibrillation (AFIB), and ventricular tachycardia (VT), we employed a stratified 10-fold cross-validation protocol. Our approach achieved a mean accuracy of 95.18 ± 1.18%, followed by a corresponding weighted F1-score of 95.19 ± 1.18% and a macro F1-score of 94.66 ± 1.35%. Notably, the performance of the proposed complete ABMA framework considerably outperformed the baseline CNN–BiLSTM architecture. Furthermore, in the primary evaluation metrics (i.e., accuracy, F1-score), the complete framework showed statistically significant improvements against the baseline through paired two-sided t-tests (p < 0.001). The ablation study indicated that each architectural component contributed positively to the overall classification performance, with the complete ABMA framework outperforming all reduced variants. Conclusions: The framework was evaluated by stratified cross-validation on a publicly available dataset. Our framework outperformed the baseline CNN–BiLSTM model as well as the respective ablation models in terms of classification performance. The findings from the current study are based on a retrospective analysis and therefore future studies using an independent external dataset, from multiple centers, or as part of a prospective clinical study are necessary in order to establish the generalizability and clinical utility of the proposed framework. The ABMA framework is currently viewed as a very promising research framework for intelligent ECG analysis, but it is not yet a clinically validated diagnostic tool. Full article

Automatic classification of remote sensing images for land use and land cover (LULC) applications encounter numerous challenges because of multi-resolution data, heterogeneous appearance and multi-spectral complexity. Existing deep learning models, especially conventional CNNs, struggle to include inherent features of objects because of their limited ability in modeling the long-range dependency and global contextual information. To address these limitations, this paper proposes a novel Heterogeneous Dual-Path Wide Residual Network (HDP-WRN) model for enhanced LULC classification. The initial feature extraction is performed using a post-activation residual block and two parallel paths using different convolutional operators with different attention mechanisms. Branch A integrates standard convolutions and Efficient Channel Attention (ECA) to extract fine-grained local textures, and Branch B merges Ghost convolutions and Convolutional Block Attention Module (CBAM) to boost global spatial channel feature extraction effectively and their complementary representations are fused for obtaining discriminative joint feature space effectively. Extensive experiments show that HDP-WRN achieves competitive performance on multiple benchmark datasets, with accuracy of 98.67% on EuroSAT, 95.11% on RSSCN, 96.13% on SIRI-WHU, and 97.24% on UC-Merced. Under our experimental setup, the proposed model outperforms the reported results of several existing methods, though direct comparisons should be interpreted with caution due to differences in training protocols across studies. Results verify the model for accurate and robust LULC classification for diverse spatial resolutions and remote sensing images. Full article

Background/Objectives: Cardiac auscultation is an important method for identifying cardiovascular abnormalities, but conventional methods are limited by examiner-dependent variability and sensitivity. The automatic classification of phonocardiogram (PCG) has the potential to be applied for standardized cardiac screening, but still has to deal with signal non-stationarity and the extraction of discriminative features. This investigation develops a computational framework integrating wavelet analysis with entropy-based features for distinguishing normal and abnormal heart sounds. Methods: The study employs the PhysioNet Computing in Cardiology Challenge 2016 database. Signal processing includes resampling, zero-phase Butterworth band-pass filtering (20–800 Hz), and median absolute deviation normalization. Time–frequency representations are generated through continuous wavelet transform (CWT) and synchrosqueezed CWT using analytic Morlet wavelets. Multiple entropy measures including Shannon, Rényi, Tsallis, spectral, permutation, and sample entropies are computed globally and across four physiologically motivated frequency bands (20–80, 80–200, 200–400, 400–800 Hz). A regularized multi-layer perceptron with dropout performs classification. Evaluation employs stratified 5-fold cross-validation with recording-level partitioning to prevent data leakage. Results: The best configuration using standard CWT with 800 Hz bandwidth achieved test-set AUROC of 0.972, balanced accuracy of 0.915, and 96% sensitivity maintained at 90% specificity. Contrary to expectations, standard CWT outperformed synchrosqueezed CWT with AUROC advantage of +0.038. Also, the band-specific entropy analysis provided the largest performance contribution with +4.1% to AUROC, confirming frequency-localized pathological signatures. Conclusions: This methodology demonstrates how the conventional wavelet analysis integrated with entropy engineering achieves state-of-the-art performance. Also, it maintains computational efficiency (1.2 s extraction and classification) and interpretability, offering practical potential for point-of-care cardiac screening in resource-limited settings. Full article

The development of reliable computer vision systems for poultry slaughterhouses requires robust segmentation methods capable of handling challenging industrial conditions. This study evaluated the structural behavior, computational performance, and consistency of three segmentation pipelines for broiler chicken carcass inspection: (i) an edge-based approach using Canny detection and morphological operations, (ii) a threshold-based method using global binarization and contour extraction, and (iii) a deep learning-based approach for automatic background removal implemented with the rembg library. A dataset of 587 RGB images acquired in commercial slaughterhouses was analyzed. Segmentation performance was assessed using Intersection over Union, Dice coefficient, Overlap Error, Structural Similarity Index, Edge Preservation Index, and Fisher Discriminant Ratio, complemented by qualitative analyses of discordance maps and Sobel edge visualizations. Results showed that overlap-based metrics alone were insufficient, as high IoU and Dice values often concealed important boundary differences. Classical methods exhibited lower computational cost and processing times compatible with real-time applications but presented limitations in contour stability. The deep learning-based approach generated more continuous and structurally coherent boundaries, although at higher computational cost. These findings demonstrate that segmentation methods produce distinct structural representations that can directly affect the reliability of artificial intelligence systems for poultry inspection. Full article

The steel–concrete interface in steel–concrete composite structures is susceptible to interfacial void defects during both casting and service, posing a significant threat to structural load-bearing capacity. For early-stage micro-voids exceeding 2 mm in height, signal variations are weak and exhibit response characteristics similar to dense states, leading to feature ambiguity when using conventional criteria based on time-domain amplitude and attenuation or frequency-domain peak values and resulting in a high risk of missed detections. To address this limitation for early warning purposes, this study proposes a high-sensitivity identification method integrating an impact elastic wave response feature system with a feature-attention gated multi-layer perceptron (Feature-attention MLP). Based on full-scale model experiments from an engineering project, the temporal and spectral evolution patterns of impact elastic wave responses under varying dense conditions were analyzed. A comprehensive feature system, including time-domain statistical descriptors, spectral peaks, and sub-band energy distributions, was constructed, with Random Forest used for feature importance ranking and Top-K selection. An MLP classifier was then developed for automatic discrimination of dense states. A feature-level attention gating mechanism was introduced to enable adaptive weighting across feature dimensions, enhancing sensitive features while suppressing noise and structural variability. The final lightweight classifier contains 4052 trainable parameters, enabling rapid execution with an average CPU inference time of approximately 1.24 ms per sample. The average CPU inference time was approximately 1.24 ms per sample. Under the original train–validation split, the recall-prioritized operating point achieved a Void recall of 0.978 and a weighted F1-score of 0.780, accompanied by a non-negligible false-positive screening burden. Stratified five-fold internal validation yielded a balanced accuracy of 0.682 ± 0.021 and a Void recall of 0.845 ± 0.035 under the inner-validation-optimized threshold. These results demonstrate the preliminary potential of the proposed lightweight framework for engineering-oriented micro-void screening under the investigated full-scale conditions. Full article

Fine-grained commodity detection is a key visual task in intelligent retail, automatic checkout, and warehouse management. Compared with general object detection, commodity detection is more sensitive to subtle packaging differences, similar colors, local text patterns, and class-dependent appearance variations. These factors lead to unstable recognition for weak classes when a conventional detector is trained directly on a limited product dataset. To address this problem, this study proposes WCA-Det, a weak-class-aware dual-attention enhancement method for fine-grained commodity detection. The detector is built on a YOLO11-based framework and combines efficient multi-scale spatial attention with lightweight channel attention to strengthen discriminative product features. In addition, a weak-class augmentation strategy is introduced during training to improve the robustness of categories with lower mAP50-95, without increasing inference parameters or GFLOPs. Experiments on a self-built 12-class commodity dataset show that the proposed method achieves 0.98640 mAP50 and 0.85535 mAP50-95 at an input size of 640. Compared with YOLO11_EMA, mAP50-95 is improved from 0.84334 to 0.85535, corresponding to a 1.20 percentage-point gain. On the self-built dataset, the final model also outperforms representative YOLO-series detectors, including YOLOv5su, YOLOv8s, YOLOv8m, YOLOv9s, YOLOv10s, and YOLOv10m, while maintaining a compact computational cost. These results indicate that weak-class-aware feature enhancement is effective for fine-grained commodity recognition under practical intelligent retail conditions. Full article

Operational crop mapping requires classifiers capable of robust generalization across years. While feature importance is routinely used for model optimization, its temporal stability has rarely been systematically investigated, creating a critical gap in deploying reliable monitoring systems. This study moves beyond identifying “most important” features to systematically evaluate and quantify their inter-annual stability for enabling automated classification. Using six agricultural years (2018, 2019, 2020, 2023, 2024 and 2025) of Sentinel-1 and Sentinel-2 data over Morocco, we extracted 156 multi-sensor features across 12 monthly composites and analyzed their importance stability through statistical metrics, clustering, and novel composite indices: the Reliability Index (RI) and Automatic Selection Score (AuSS). This framework automates feature selection by ranking features with RI and AuSS and then applying Pareto optimization to identify a minimal stable feature set—without requiring annual retraining or expert intervention. Our analysis confirms a fundamental tension: the most discriminative features (e.g., NDVI, VH, VV) are also the most volatile, while stable features (e.g., NDRE, MSI, NDMI) offer modest predictive power. Hierarchical clustering revealed four behavioral typologies (Dominant Stable, Performant Volatile, Stable Minor, and Noise), guiding strategic feature management. Crucially, a Pareto analysis demonstrated that a refined portfolio of 6 indices (VH, VV, NDVI, NDRE, GCVI, RVI) captures 57.2% of cumulative predictive importance, filtering out inter-annual noise while preserving discriminative signal. The Voting Ensemble leveraging this Stable Portfolio maintained consistent high accuracy (87.4% accuracy, 87.2% F1-score) with minimal performance degradation during temporal transfer, while models based on volatile top features exhibited significant drops. Entropy analysis confirmed that all features in the Stable Portfolio provide consistent informational certainty, indicating that stability-driven selection does not increase model uncertainty. We conclude that feature stability is not merely a diagnostic metric but a foundational criterion for operational design. We propose a practical, metrics-driven framework for constructing automated crop classification systems that are more resilient to inter-annual climate variability. Full article

We present an interpretable evolutionary-fuzzy feature extraction framework for high-dimensional electroencephalography (EEG) classification. The proposed method combines an evolution strategy (ES) optimizer with fuzzy membership encoding to automatically discover compact, nonlinear feature representations from raw EEG signals. Applied to a chemosensory experiment distinguishing nasal breathing conditions during taste perception (N = 10 between-subjects participants, 1600 trials, 612 raw features), the framework achieves 89.50% cross-validated accuracy, equivalent to or exceeding all 25-feature baselines, while reducing dimensionality by 95.9% (from 612 to 25 features). The method produces fully interpretable fuzzy rules, enabling neuroscientists to inspect the decision logic rather than relying on nontransparent classifiers. A comprehensive validation including noise robustness analysis (0–30% Gaussian noise) and between-subjects generalization assessment is provided. Due to the between-subjects design, this study focuses on demonstrating the within-dataset discriminative capacity and the interpretability of the feature extraction pipeline, rather than claiming true subject-independent generalization. Full article

Tomato, as a globally vital economic crop, relies heavily on accurate disease recognition to safeguard food security. However, tomato leaf disease identification constitutes a classic fine-grained visual classification task characterized by minimal inter-class variance, spatially sparse lesion features, and complex background interference. These challenges hinder conventional deep learning models from precisely localizing critical discriminative regions. In response to the aforementioned challenges, we introduce EA-HFA, an innovative framework based on deep neural networks that synergistically integrates an Entropy Attention mechanism alongside a Hierarchical Feature Alignment component. Specifically, the Entropy Attention module leverages information-theoretic entropy to quantify pixel-wise predictive uncertainty, adaptively selecting high-confidence pixels to automatically focus the network on sparse yet highly discriminative lesion features. Concurrently, the Hierarchical Feature Alignment module imposes KL-divergence constraints on the temperature-scaled probability distributions across adjacent network layers, enforcing cross-scale consistency in the localization of discriminative regions. Evaluations conducted on the PlantVillage and AI Challenger 2018 benchmarks reveal that EA-HFA achieves Top-1 accuracies of 99.29% and 97.82%, respectively, yielding performance comparable to established deep learning architectures while maintaining a reasonable computational footprint. Furthermore, qualitative analyses indicate that the model tends to attend to minute lesion-relevant areas, providing a certain level of interpretability for its decision-making process. Thus, EA-HFA holds practical potential as an alternative solution for automated plant disease monitoring in precision farming. Full article

Manual classification of rice grain defects remains a persistent challenge in the Peruvian rice industry, as it relies heavily on human inspection, leading to variability, inconsistency, and reduced efficiency when processing large volumes of product. This study evaluates the effectiveness of transfer learning and convolutional neural networks (CNNs) for the automatic classification of four rice grain categories relevant to quality assessment: Whole, Stained, Broken, and Chalky. A dataset comprising 6599 RGB images was employed. To ensure a reliable evaluation protocol, the dataset was first partitioned into training (70%), validation (15%), and test (15%) subsets, after which data augmentation was independently applied within each partition to balance class distributions. Five pretrained CNN architectures were evaluated: MobileNetV2, EfficientNetB0, ResNet50, DenseNet121, and InceptionV3, all of which share a common classification head. Models were trained using transfer learning and early stopping based on validation loss. Performance was assessed using accuracy, precision, recall, F1-score, confusion matrices, 95% confidence intervals, and pairwise McNemar statistical tests. The results showed that ResNet50 achieved the highest classification accuracy (84.71%), followed by EfficientNetB0 (83.60%) and DenseNet121 (83.20%). Statistical analysis indicated that performance differences among the top-performing architectures were relatively small, with significant differences observed only for selected model pairs. Across all evaluated models, the discrimination between Whole and Chalky grains remained the most challenging classification task due to their high visual similarity. Overall, the findings demonstrate that transfer learning-based CNNs provide an effective and scalable approach for automated rice grain defect identification and quality assessment in agricultural environments. Full article

This paper investigates human–AI collaboration through explainable AI where we interpret the results of barefoot print clustering using unsupervised machine learning. This can be used to identify the number of individuals from barefoot prints on the ground as a tool in forensics or anti-poaching. A self-supervised vision transformer, DINOv2, is used to automatically extract feature embeddings from localized barefoot-print regions to identify trails belonging to an individual on soil substrate. Furthermore, we introduce an Embedding Spatial Attribution Module (ESAM) to generate spatial attribution heatmaps, enabling visualization of discriminative regions that contribute to individual-specific trail identification and improving model explainability. The proposed method is named XTrail-ID, an explainable human footprint trail identification framework with two variants, OBB-XTrail-ID (oriented bounding box-based), and SEG-XTrail-ID (segmentation-based). We quantify embedding similarity using three complementary metrics: cosine similarity, Pearson correlation coefficient, and Spearman rank correlation. Twenty adults (ten males, ten females) participated, with a total of 1000 trail images extracted from UAV imagery. SEG-XTrail-ID using cosine similarity yielded the highest performance, with (3.21) discriminability and (94.2%) accuracy, while OBB-XTrail-ID using cosine similarity achieved (2.54) discriminability and (91.5%) accuracy. In addition, the latter exhibited reduced consistency in footprint grouping when more than three individuals were present within a single frame. Full article