Search Results (866)

Maintaining consistent part quality remains a critical challenge in industrial additive manufacturing, particularly in laser-based powder bed fusion of polymers (PBF-LB/P), where crystallization-driven thermal instabilities, governed by isothermal crystallization within a narrow sintering window, precipitate defects such as curling, warping, and delamination. In contrast to metal-based systems dominated by melt-pool hydrodynamics, polymer PBF-LB/P requires monitoring strategies capable of resolving subtle spatio-temporal thermal deviations under realistic industrial operating conditions. Although machine learning, particularly convolutional neural networks (CNNs), has demonstrated efficacy in defect detection, a structured evaluation of heterogeneous modeling paradigms and their deployment feasibility in polymer PBF-LB/P remains limited. This study presents a systematic cross-paradigm assessment of unsupervised anomaly detection (autoencoders and generative adversarial networks), supervised CNN classifiers (VGG-16, ResNet50, and Xception), hybrid CNN-LSTM architectures, and physics-informed neural networks (PINNs) using 76,450 synchronized thermal and RGB images acquired from a commercial industrial system operating under closed control constraints. CNN-based models enable frame- and sequence-level defect classification, whereas the PINN component complements detection by providing physically consistent thermal-field regression. The results reveal quantifiable trade-offs between detection performance, temporal robustness, physical consistency, and algorithmic complexity. Pre-trained CNNs achieve up to 99.09% frame-level accuracy but impose a substantial computational burden for edge deployment. The PINN model attains an RMSE of approximately 27 K under quasi-isothermal process conditions, supporting trend-level thermal monitoring. A lightweight hybrid CNN achieves 99.7% validation accuracy with 1860 parameters and a CPU-benchmarked forward-pass inference time of 1.6 ms (excluding sensor acquisition latency). Collectively, this study establishes a rigorously benchmarked, scalable, and resource-efficient deep-learning framework tailored to crystallization-dominated polymer PBF-LB/P, providing a technically grounded basis for real-time industrial quality monitoring. Full article

Effective, efficient, and early animal disease prediction is a challenging task. Identifying and reducing animal health risks is important for preventing disease outbreaks and improving cattle management. This study presents the machine-learning and hybrid deep-learning models for animal risk prediction. We employed eight classifiers (Support Vector Machine, Logistic Regression, Decision Tree, K-Nearest Neighbors, Gaussian Naive Bayes, and Random Forest) along with feature-enhanced hybrid variants (RF–CNN and RF–ANN) to early detect risk to animals’ health. Our main objective is to develop and evaluate robust ML models for predicting animal health risks. Apart from these, we also present a comparative study of the conventional and hybrid models to construct a decision support system for early disease prediction. The experimental work reveals that RF obtained the highest accuracy of 95.77%, a macro F1-score of 0.9343, and a weighted F1-score of 0.9515. We also conduct the statistical test to confirm the robustness of the model for animal disease prediction. The proposed framework provides a scalable, interpretable decision-support system for real-world animal health monitoring and early disease intervention. Full article

To address the limitations of traditional runoff prediction methods—namely, the oversimplification of meteorological factor selection, ambiguous interactions among core variables, and the disruptive influence of redundant inputs—this study focuses on the Zijiang River Basin as a representative case. A suite of machine learning models, including Long Short-Term Memory Neural Network (LSTM), Convolutional Neural Network (CNN)-LSTM, Temporal Convolutional Network (TCN), and Gradient Boosting Regression Tree (GBRT), was constructed and trained using 13 distinct combinations of meteorological variables. These configurations were systematically evaluated to assess their compatibility with each model in simulating daily runoff patterns. Additionally, the Shapley Additive Explanations (SHAP) algorithm was employed to quantitatively assess the contribution of each factor to predictive accuracy. Among the models tested, the TCN model consistently demonstrated superior performance, particularly in mitigating the effects of irrelevant or redundant features. The GBRT model showed distinctive strengths in accurately predicting peak flow timings. Of all input configurations, the combination of “runoff + precipitation + evaporation + temperature” emerged as the most effective. Findings indicate that the predictive value of individual meteorological variables hinges primarily on their direct correlation with runoff, while the effectiveness of multi-factor schemes depends on the degree of functional integration—specifically, the coupling of hydrological recharge, consumption, and regulatory processes. The presence of redundant variables was found to impair model performance unless they contributed to a meaningful synergistic relationship with core inputs. The SHAP analysis further reinforced these insights: precipitation-related variables proved to be the most critical to prediction accuracy, whereas temperature and evaporation served more complementary roles. Notably, the inclusion of relative humidity tended to suppress runoff responses and increased deviation in peak timing estimates. These findings shed light on the nuanced interplay between meteorological input design and model selection, offering a robust foundation for optimizing data-driven runoff prediction frameworks. Full article

Spatio-temporal features are crucial for maritime trajectory forecasting, especially in scenarios involving curved waterways or abrupt changes in ship motion patterns. Although Automatic Identification System (AIS) data, which are widely used for trajectory prediction, inherently include temporal and spatial information, effectively strengthening these features and integrating them into prediction models remains challenging. To address this challenge, we propose a Convolutional Neural Network (CNN)-Series-cOre Fused Time Series forecaster (SOFTS)-based framework that explicitly couples spatial and temporal features to achieve high-fidelity maritime trajectory forecasting, especially in scenarios with complex spatial patterns. We first employ a CNN-based spatial encoder to hierarchically abstract spatial density distributions through convolution and pooling operations, thereby learning global spatial structure patterns of ship movements. This encoder emphasizes overall spatial morphology rather than precise individual trajectory points. Second, we employ the SOFTS model to incorporate angular velocity, acceleration, and angular acceleration as input features to characterize ship motion states, which can capture the temporal dependencies of ship motion states from multivariate time series. Finally, the spatial embedding features extracted by the CNN are concatenated with the temporal feature representations learned by SOFTS along the feature dimension to form a joint spatiotemporal representation. This representation is then fed into a fusion regression module composed of fully connected layers to predict future ship trajectories. Experimental results on the validation dataset show that the proposed method achieves an MSE of 0.020 and an MAE of 0.060, outperforming several advanced time series forecasting models in prediction accuracy and computational efficiency. The introduction of angular velocity, acceleration, and angular acceleration features reduces the MSE and MAE by approximately 10.22% and 9.49%, respectively, validating the effectiveness of the introduced dynamic features in improving trajectory prediction performance. These results underscore the proposed method’s potential for intelligent navigation and traffic management systems by effectively enhancing inland river navigation safety and strengthening waterborne traffic monitoring capabilities. Full article

Crop yield estimation, particularly early-season yield prediction, is highly important for global food security and disaster mitigation. In this study, we utilized deep learning models combined with remote sensing data to develop in-season crop yield estimation models, enabling immediate yield prediction. We employed a convolutional neural network (CNN) for spatial feature extraction and a long short-term memory network (LSTM) for temporal patterns, complemented by Gaussian process regression (GP) that introduced geographical coordinates. Three groups of in-season yield prediction experiments were designed, utilizing four-phase, two-phase, and single-phase data, respectively. The results indicated that under the two-phase training scheme, the LSTM_GP model achieved the highest performance in the sixth period, with an $R^2$ value of 0.61 and a root mean square error ($RMSE$) value of 983.38 kg/ha. When trained on single-phase data at the twelfth phase (approximately mid-to-late July), the LSTM_GP model also performed best, attaining an $R^2$ value of 0.62 and an $RMSE$ value of 969.06 kg/ha. The single-phase prediction model outperformed time-series models in yield prediction accuracy. The periods from mid-to-late July to early-to-mid August represent critical crop growth stages were essential for accurate yield prediction. From our research, we found that adding GP can improve the prediction accuracy, especially for LSTM. Moreover, the proposed single-phase prediction model realized reliable crop yield prediction as well as the silking to early grain-filling stage (mid-to-late July), providing a critical lead time of approximately 2–2.5 months before harvest to support pre-harvest agricultural decision-making. Full article

Accurate gold price forecasting is crucial for economic stability and investment decision-making. In order to improve the accuracy of gold price prediction and quantify the uncertainty of gold price fluctuation, this paper proposes a hybrid model (CNN-QRLSTM) that integrates convolutional neural network (CNN) and quantile regression long- and short-term memory network (QRLSTM) and innovatively introduces news text data to quantify the media sentiment. We combine EEMD with the Hurst index to remove white noise from the original signal, and the processed data is used as the input layer of the prediction model. Furthermore, to demonstrate the impact of news sentiment on gold prices, this paper employs entropy measurement methods based on information theory to quantify the uncertainty and information content embedded within processed gold price sequences and derived sentiment indicators. The mutual information (MI) algorithm, based on information entropy, captures the nonlinear correlations between financial keywords and market sentiment. It constructs a financial sentiment lexicon (covering keywords such as economic policies and geopolitical conflicts), combines semantic rules with context-weighted strategies, calculates sentiment scores for news texts, and generates daily aggregated media sentiment indicators. This entropy-based perception method not only enhances the interpretability of emotion-driven fluctuations but also provides a theoretical foundation for reducing prediction uncertainty through multi-source data fusion. The experiment uses 2022–2025 daily London gold spot price data, Shanghai Gold Exchange gold price data, and the same period of Gold Investment Network gold market news to carry out the study. The empirical study shows that the synergy of multi-source data fusion and the quantile regression mechanism can improve the accuracy of gold price prediction and the new paradigm of risk interpretation while providing theoretical support for the formulation of quantitative investment strategies. Full article

This study examines the impact of recovered steel fibers (WTSFs) and waste tire aggregates of varying sizes—fine (FWTR), small coarse (SCWTR), and large coarse (LCWTR)—on the compressive strength of concrete subjected to elevated temperatures. Forty mixes were formulated utilizing four distinct WTR replacement ratios (0%, 5%, 10%, 20%) and four WTSF doses (0%, 0.5%, 1%, 2%), and evaluated at temperatures of 24 °C, 100 °C, 200 °C, and 300 °C. The findings indicate that elevated temperatures consistently diminish compressive strength, although the reference concrete saw around 18% loss at 300 °C, with WTR-containing mixes demonstrating losses ranging from 25% to 45%, contingent upon rubber size and dose. The type of WTR was critical—LCWTR mixes exhibited superior residual strength retention due to enhanced particle–matrix interlocking, whereas FWTR mixtures saw the most significant decline. The inclusion of WTSF increased strength by 2–10% at 0.5–1.0% fiber content through crack bridging, but excessive fiber addition (2.0%) decreased workability and caused clustering, leading to up to 40% strength loss. The ideal combination was 5LCWTR–1WTSF, which sustained 36.97 MPa at 24 °C and 29.65 MPa at 300 °C, indicating superior performance across all temperature ranges. Predictive modeling utilizing machine learning techniques (SVR, KRR, 1D-CNN, and DRL) corroborated the experimental results, with the CNN attaining the maximum generalization accuracy (R² = 0.9374) and the KRR exhibiting the most consistent performance (R² = 0.9305). The models indicated that WTR and temperature were the primary variables diminishing strength, although modest WTSF ratios enhanced overall thermal resilience. SHAP and ALE analysis further validated that WTR content exhibited the most significant negative feature contribution (~−6 MPa), succeeded by temperature, although modest fiber inclusion demonstrated a positive SHAP effect (+2–4 MPa), corroborating the experimentally observed non-linear reinforcement threshold. The combined experimental–computational framework demonstrates that the combination of coarse rubber aggregates (5–10%) with appropriate WTSF content (0.5–1.0%) improves sustainability and high-temperature durability. The integration of physical testing and interpretable AI modeling creates a hybrid approach that can anticipate and enhance thermo-mechanical performance in sustainable concrete systems. Full article

Bladder cancer (BC) is the most common malignancy of the urinary tract. Approximately 75% of cases are non-muscle-invasive BC (NMIBC), while muscle-invasive BC (MIBC) and advanced tumors account for most cancer-specific mortality. Accurate assessment of tumor invasion is essential, as staging variability may lead to inappropriate treatments. Tumor invasion involves several mechanisms including extracellular matrix (ECM) remodeling mediated by metalloproteinases, angiogenesis, and cell adhesions. Masson’s trichrome staining (MTS) provides relevant information on ECM composition. This study evaluated the application of machine learning to MTS-stained bladder biopsies to predict muscle invasion. A retrospective analysis of bladder biopsy images obtained from transurethral resections and cystectomies (2022–2024). A total of 702 histological images were analyzed. A convolutional neural network (CNN) was trained to classify tumors as MIBC or NMIBC and model outputs were correlated with clinical variables. The CNN achieved an accuracy of 95.2% in the training set and 90.1% in validation. Model-derived probabilities were significantly associated with tumor grade, lesion size, and muscle invasion. Logistic regression demonstrated a strong association with invasive disease (OR = 0.07, p = 0.017). CNN-based analysis of MTS-stained bladder biopsy images enable accurate prediction of muscle invasion, with potential to improve diagnostic precision. Full article

In this paper, a method for determining the filling level of grooves (1 mm (W) × 0.25 mm (H)) in pressed titanium pipe-fitting joints is presented. The joints are inspected in a water bath using a 20 MHz phased array ultrasound, and the acquired raw B-scans are evaluated by a convolutional neural network that performs per-groove regression. Reference filling levels are obtained destructively from micrographs. Compared to X-ray computed tomography and destructive sectioning, the proposed approach overcomes the low material contrast between pipe and fitting, avoids long scan times, and enables a nondestructive, potentially inline-capable quantitative assessment of sub-millimeter grooves. A manual high-frequency ultrasound evaluation with a single probe and conceivable rule-based time-of-flight pipelines with hand-crafted echo picking and thresholds both show only moderate agreement with CT references and require substantial feature engineering for multiple echoes. In contrast, the PAUT-CNN method exploits the full raw B-scan without explicit feature design and achieves a root mean square error of about 7% of the groove filling levels on a held-out test set, corresponding to an absolute error on the order of a few tens of micrometers in groove height. This demonstrates that high-frequency phased array ultrasound combined with data-driven evaluation can quantitatively assess the filling of sub-millimeter grooves in aerospace-relevant press-fit connections. Full article

Background: Embryoid bodies (EBs) play a central role in organoid engineering, where their formation fidelity and size critically influence downstream differentiation outcomes. Current EB production workflows primarily rely on retrospective quality assessment, which limits reproducibility in high-throughput culture systems. Objective: This study aimed to develop a prospective, non-invasive framework that integrates early-phase bright-field time-lapse imaging with a three-dimensional convolutional neural network to predict EB formation outcomes and final EB diameter within the microwell platform. Methods: Time-lapse image sequences collected during the first hours after cell seeding on the microwell array were used to train 3D-CNN models for classification (formation vs. non-formation) and regression (final diameter). A balanced dataset was constructed through under-sampling, and five-fold cross-validation with data augmentation was applied to evaluate model performance. Results: The classification model achieved an accuracy of 96.5%, reliably distinguishing between successful and failed EB formation using short-duration image sequences. The regression model predicted the final EB diameter with a mean absolute error of ±7.1 µm, reflecting strong agreement with measured values and capturing seeding-density-dependent size variations. Conclusions: Early aggregation dynamics captured by bright-field time-lapse imaging contain sufficient spatiotemporal information to enable accurate, prospective EB quality prediction. The proposed framework provides a label-free and automation-compatible strategy for improving reproducibility in large-scale EB manufacturing and supports the future development of adaptive and closed-loop organoid culture systems for clinical applications. Full article

Unmanned aerial vehicle (UAV) imagery poses persistent challenges for object detection, including dense small objects, large-scale variation, cluttered backgrounds, and stringent localization requirements, where conventional two-stage detectors often fall short in fine-grained small-object representation, efficient global context modeling, and classification–localization consistency. We specifically target low-altitude UAV-captured imagery with highly flexible viewpoints (near-nadir to oblique) and frequent platform-induced motion blur, which makes dense small-object localization substantially more challenging than in conventional remote-sensing imagery. To address these issues, we propose CASA-RCNN, a context-adaptive and scale-aware two-stage detection framework tailored to UAV scenarios. CASA-RCNN introduces a shallow-level enhancement module, ConvSwinMerge, which strengthens position-sensitive cues and suppresses background interference by combining coordinate attention with channel excitation, thereby improving discriminative high-resolution features for small objects. For deeper semantic features, we incorporate an adaptive sequence modeling module based on MambaBlock to capture long-range dependencies and support context reasoning in crowded or occluded scenes with practical computational overheadon a desktop GPU. In addition, we adopt Varifocal Loss for quality-aware classification to better align confidence scores with localization quality, and we design a ScaleAdaptiveLoss to dynamically reweight regression objectives across object scales, compensating for the reduced gradient contribution of small targets during training. Experiments on the VisDrone2021 validation benchmark show that CASA-RCNN achieves 22.9% mAP, improving Faster R-CNN by 9.0 points; it also reaches 36.6% mAP₅₀ and 25.7% mAP₇₅. Notably, performance on small objects improves to 12.5% mAP_s (from 6.9%), and ablation studies confirm the effectiveness and complementarity of the proposed components. Full article

Cotton spider mites pose a significant threat to cotton production, while traditional manual investigation and blanket pesticide application are inefficient for precision pest management in large-scale cotton fields. To address this challenge, this study developed an integrated UAV multispectral remote sensing system for spider mite monitoring and precision spraying. Multispectral imagery was acquired from cotton fields in Shaya County, Xinjiang using UAV-mounted cameras, and vegetation indices including RDVI, MSAVI, SAVI, and OSAVI were selected through feature optimization. Comparative evaluation of three machine learning models (Logistic Regression, Random Forest, and Support Vector Machine) and two deep learning models (1D-CNN and MobileNetV2) was conducted. Considering classification performance and computational efficiency for real-time UAV deployment, Random Forest was identified as optimal, achieving 85.47% accuracy, an 85.24% F1-score, and an AUC of 0.912. The model generated centimeter-level spatial distribution maps for precise spray zone delineation. An improved NSGA-III multi-objective path optimization algorithm was proposed, incorporating PCA-based heuristic initialization, differential evolution operators, and co-evolutionary dual population strategies to optimize deadheading distance, energy consumption, operation time, turning frequency, and load balancing. Ablation study validated the effectiveness of each component, with the fully improved algorithm reducing IGD by 59.94% and increasing HV by 5.90% compared to standard NSGA-III. Field validation showed 98.5% coverage of infested areas with only 3.6% path repetition, effectively minimizing pesticide waste and phytotoxicity risks. This study established a complete technical pipeline from monitoring to application, providing a valuable reference for precision pest control in large-scale cotton production systems. The framework demonstrated robust performance across multiple field sites, though its generalization is currently limited to one geographic region and growth stage. Future work will extend its application to additional cotton varieties, growth stages, and geographic regions. Full article

The cultivation of potatoes is essential for rural food security, and the use of Unmanned Aerial Vehicle Red-Green-Blue (UAV-RGB) imagery allows for precise and cost-effective estimation of yield and identification of varieties, overcoming the limitations of manual assessment. We evaluated four INIA varieties (Bicentenario, Canchán, Shulay and Tahuaqueña) by integrating agronomic measurements (height, number and weight of tubers, leaf health) with color and textural indices derived from RGB orthomosaics. Yield prediction was modeled using Random Forest (RF) and Gradient Boosting (GB); varietal identification was approached with (i) a Convolutional Neural Network (CNN) that classifies RGB images and (ii) classical models such as Random Forest, Support Vector Machines (SVMs), K-Nearest Neighbors (KNNs), Decision Trees and Logistic Regression trained on EfficientNetB0 embeddings. The results showed significant genotypic differences in yield (p < 0.001): Tahuaqueña 13.86 ± 0.27 t ha⁻¹ and Bicentenario 6.65 ± 0.27 t ha⁻¹. The number of tubers (r = 0.52) and plant height (r = 0.23) correlated with yield; RGB indices showed low correlations (r < 0.3) and high redundancy (r > 0.9). RF achieved a better fit (Coefficient of determination, R² = 0.54; Root Mean Square Error, RMSE = 2.72 t ha⁻¹), excelling in stolon development (R² = 0.66) and losing precision in maturation due to foliar senescence. In classification, the CNN and RF on embeddings achieved F1-macro ≈ 0.69 and 0.66 (Receiver Operating Characteristic—Area Under the Curve, ROC AUC RF = 0.89), with better identification of Bicentenario and Shulay. We conclude that UAV-RGB is a cost-effective alternative for phenotypic monitoring and varietal selection in high Andean contexts. These findings support the integration of UAV-RGB imagery into breeding and monitoring pipelines in resource-limited Andean systems. Full article

Photovoltaic (PV) systems are subject to nonlinear performance degradation caused by operational and environmental factors, which limits reliable energy production. Most existing studies focus on power output forecasting and fail to isolate intrinsic efficiency losses from meteorological variability. This study proposes a degradation-aware deep learning framework for predicting PV performance loss using multi-sensor time-series data. Performance degradation is formulated as a reference-based performance loss ratio derived from the deviation between observed power output and an ideal physics-informed reference model. A hybrid convolutional neural network (CNN) and long short-term memory (LSTM) architecture is employed to jointly capture local feature representations and long-term temporal degradation dynamics. Model evaluation is conducted using a synthetically generated yet physically consistent dataset, informed by real PV measurements to ensure real-world relevance. Experimental results demonstrate that the proposed CNN–LSTM model outperforms baseline approaches, including persistence, linear regression, and XGBoost, particularly in terms of mean absolute error (MAE) and normalized root mean square error (RMSE). Additional analyses confirm stable error behavior and temporal generalization, highlighting the suitability of the proposed approach for degradation-aware performance monitoring and predictive maintenance in PV systems. Full article

Accurately quantifying the amount of corn straw returned to the field is crucial for evaluating conservation tillage measures and phaeozem protection. This study proposes a framework for quantitatively estimating the amount of corn straw returned to the field based on UAV multispectral imaging, integrating a standardized spectral correction strategy, a novel straw index (SI), and an improved deep learning model (convolutional neural network-straw, CNN-Straw). By combining multispectral images acquired by UAVs with ground-measured straw weight data, regression datasets covering autumn and spring conditions were constructed. The proposed straw index aims to enhance the spectral differences between non-photosynthetic straw residues and living vegetation. Furthermore, the CNN-Straw model, combining frequency domain convolution and local spatial attention mechanisms, has an improved ability to represent the complex texture of straw features. Experimental results show that CNN-Straw outperforms traditional machine learning models, including random forest (RF), support vector regression (SVR), and XGBoost, achieving a high coefficient of determination (R²) of 0.82 on different seasonal datasets and effectively reducing the root mean square error (RMSE) and mean absolute error (MAE). Cross-seasonal experiments further demonstrate the stable performance of the framework under different environmental conditions. The proposed method provides an efficient and scalable solution for the quantitative assessment of straw return to the field, supporting precision agricultural management and phaeozem conservation practices. Full article