Search Results (8,824)

Solar greenhouses are an important component of modern facility agriculture, and the dynamic changes in their internal environment directly affect crop growth and yield. Among these factors, crop transpiration releases water vapor through transpiration, directly altering the indoor humidity balance and forming a dynamic coupling with factors such as temperature and light. The environment of solar greenhouses exhibits highly nonlinear and multivariate coupling characteristics, leading to insufficient prediction accuracy in existing models. However, accurate predictions are crucial for regulating crop growth and yield. However, current mainstream greenhouse environmental prediction models still have obvious limitations when dealing with such complexity: traditional machine learning models and single-variable-driven models have issues such as insufficient accuracy (average MAE is 15–20% higher than in this study) and weak adaptability to nonlinear environmental changes in multi-environmental factor coupling predictions, making it difficult to meet the needs of precision farming. A review of relevant research over the past five years shows that while LSTM-based models perform well in time series prediction, they ignore the spatial correlations between environmental factors. Models incorporating attention mechanisms can capture key variables but suffer from high computational costs. To address these issues, this study proposes a prediction model based on multi-strategy optimization and gradient-boosting (GBDT) algorithms. By introducing a multi-scale feature fusion module, it addresses the accuracy issues in multi-factor coupling prediction. Additionally, it employs a lightweight network design to balance prediction performance and computational efficiency, filling the gap in existing research applications under complex greenhouse environments. The model optimizes data preprocessing and model parameters through Sobol sequence initialization, adaptive t-distribution perturbation strategies, and Gaussian–Cauchy mixture mutation strategies and combines CatBoost for modeling to enhance prediction accuracy. Experimental results show that the MSCSO–CatBoost model performs excellently in temperature prediction, with the mean absolute error (MAE) and root mean square error (RMSE) reduced by 22.5% (2.34 °C) and 24.4% (3.12 °C), respectively, and the coefficient of determination (R²) improved to 0.91, significantly outperforming traditional regression methods and combinations of other optimization algorithms. Additionally, the model demonstrates good generalization capability in predicting multiple environmental variables such as temperature, humidity, and light intensity, adapting to environmental fluctuations under different climatic conditions. This study confirms that combining multi-strategy optimization with gradient-boosting algorithms can significantly improve the prediction accuracy of solar greenhouse environments, providing reliable support for precision agricultural management. Future research could further explore the model’s adaptive optimization in complex climatic regions. Full article

Sea surface temperature (SST) is vital for climate monitoring and extreme weather forecasting. Existing global SST datasets are typically provided at daily to seasonal resolutions, while hourly data remain limited to regional scales. Polar-orbiting satellites offer global coverage but low temporal resolution, providing only 1–2 observations per day. Geostationary satellites provide high temporal resolution but cover only part of the region. These limitations create a gap in the availability of global, hourly SST data. To address this, we propose a Triple-Collocation (TC)-based fusion algorithm for generating accurate global hourly SST data through multi-source integration. The method includes data preprocessing (quality control and linear interpolation), merging five geostationary SST datasets into two global sets by priority, applying TC fusion to three polar-orbiting datasets, and finally combining all sources via multi-source TC fusion. Results show improved temporal resolution and increased spatial coverage to 32%. The fused dataset achieves high accuracy, with a daily mean Bias below 0.0427 °C, RMSE about 0.5938 °C to 0.6965 °C, and R² exceeding 0.9879. These outcomes demonstrate the method’s reliability and its potential for supporting climate and environmental research. Full article

This study proposes a novel non-destructive approach to assessing and predicting the quality of stored date fruits using a composite quality index (Qi) modeled via visible–near-infrared (VIS–NIR) spectroscopy and artificial neural networks (ANNs). Two leading cultivars, Sukkary and Khlass, were stored for 12 months using three temperature regimes (25 °C, 5 °C, and −18 °C) and five types of packaging. The samples were grouped into six moisture content categories (4.36–36.70% d.b.), and key physicochemical traits, namely moisture, pH, hardness, total soluble solids (TSSs), density, color, and microbial load, were used to construct a normalized, dimensionless Qi. Spectral data (410–990 nm) were preprocessed using second-derivative transformation and modeled using partial least squares regression (PLSR) and the ANNs. The ANNs outperformed PLSR, achieving the correlation coefficient (R²) values of up to 0.944 (Sukkary) and 0.927 (Khlass), with corresponding root mean square error of prediction (RMSEP) values of 0.042 and 0.049, and the relative error of prediction (REP < 5%). The best quality retention was observed in the dates stored at −18 °C in pressed semi-rigid plastic containers (PSSPCs), with minimal microbial growth and superior sensory scores. The second-order Qi model showed a significantly better fit (p < 0.05, AIC-reduced) over that of linear alternatives, capturing the nonlinear degradation patterns during storage. The proposed system enables real-time, non-invasive quality monitoring and could support automated decision-making in postharvest management, packaging selection, and shelf-life prediction. Full article

Accurate classification of brain tumors in medical imaging is crucial to ensure reliable diagnoses and effective treatment planning. This study introduces a novel double ensemble framework that synergistically combines pre-trained Deep Learning (DL) models for feature extraction with optimized Machine Learning (ML) classifiers for robust classification. The framework incorporates comprehensive preprocessing and data augmentation of brain Magnetic Resonance Images (MRIs), followed by deep feature extraction based on transfer learning using pre-trained Vision Transformer (ViT) networks. The novelty of our approach lies in its dual-level ensemble strategy: we employ a feature-level ensemble, which integrates deep features from the top-performing ViT models, and a classifier-level ensemble, which aggregates predictions from various hyperparameter-optimized ML classifiers. Experiments on two public MRI brain tumor datasets from Kaggle demonstrate that this approach significantly surpasses state-of-the-art methods, underscoring the importance of feature and classifier fusion. The proposed methodology also highlights the critical roles that hyperparameter optimization and advanced preprocessing techniques can play in improving the diagnostic accuracy and reliability of medical image analysis, advancing the integration of DL and ML in this vital, clinically relevant task. Full article

Corn as a key food crop, has a wide range of varieties with similar appearances, making manual classification challenging. Thus, fast and non-destructive seed variety identification is crucial for improving yield and quality. Hyperspectral imaging is commonly used for non-destructive seed classification. For the advancement of smart agriculture and precision breeding, in this study, 30 corn varieties from Northwest China were analyzed using hyperspectral images (870–1709 nm) to extract spectral reflectance from the embryonic region. Traditional methods often involve selecting specific bands, which can lead to information loss and limited variety selection. In this study, information loss was reduced and manual intervention was minimized by using full-band spectral data. And preprocessing is performed using first-order derivatives to reduce the interference of noise and irrelevant information. Classification experiments were conducted using KNN, ELM, RF, 1DCNN, and an improved 1DCNN-LSTM-ATTENTION-ECA (CLA-CA) model. The CLA-CA model achieved the highest classification accuracy of 95.38%, significantly outperforming traditional machine learning and 1DCNN models. It is demonstrated that the innovative module combination method proposed in this study is able to successfully classify varieties of corn seeds, which provides a new option for the rapid and non-destructive identification of a variety of corn seeds. Full article

Demand for OIS (Optical Image Stabilization) actuator modules, developed for shake correction technologies in industries such as smartphones, drones, IoT, and AR/VR, is increasing. To enable real-time and precise inspection of these modules, an AI algorithm that maximizes defect detection accuracy is required. This study proposes an unsupervised learning-based algorithm that is robust to noise and capable of real-time processing for accurate defect classification of OIS actuators in a smart factory environment. The proposed algorithm performs noise-reduction preprocessing, considering the sensitivity of small components and lighting imbalances, and defines three dynamic Regions of Interest (ROIs) to address positional deviations. A customized AutoEncoder (AE) is trained for each ROI, and defect classification is conducted based on reconstruction errors, followed by a final comprehensive decision. Experimental results show that the algorithm achieves an accuracy of 0.9944 and an F1 score of 0.9971 using only a camera without the need for expensive sensors. Furthermore, it demonstrates an average processing time of 2.79 ms per module, ensuring real-time capability. This study contributes to precise quality inspection in smart factories by proposing a robust and scalable unsupervised inspection algorithm. Full article

Recognizing Manchu words can be challenging due to their complex character variations, subtle differences between similar characters, and homographic polysemy. Most studies rely on character segmentation techniques for character recognition or use convolutional neural networks (CNNs) to encode word images for word recognition. However, these methods can lead to segmentation errors or a loss of semantic information, which reduces the accuracy of word recognition. To address the limitations in the long-range dependency modeling of CNNs and enhance semantic coherence, we propose a hybrid architecture to fuse the spatial features of original images and spectral features. Specifically, we first leverage the Short-Time Fourier Transform (STFT) to preprocess the raw input images and thereby obtain their multi-view spectral features. Then, we leverage a primary CNN block and a pair of symmetric CNN blocks to construct a symmetric spectral enhancement module, which is used to encode the raw input features and the multi-view spectral features. Subsequently, we design a feature fusion module via Swin Transformer to fuse multi-view spectral embedding and thereby concat it with the raw input embedding. Finally, we leverage a Transformer decoder to obtain the target output. We conducted extensive experiments on Manchu words benchmark datasets to evaluate the effectiveness of our proposed framework. The experimental results demonstrated that our framework performs robustly in word recognition tasks and exhibits excellent generalization capabilities. Additionally, our model outperformed other baseline methods in multiple writing-style font-recognition tasks. Full article

This study aims to conduct a comprehensive comparative evaluation of three transformer-based models, PEGASUS, BART, and T5 variants (SMALL and BASE), for the task of abstractive text summarization. The evaluation spans across three benchmark datasets: CNN/DailyMail (long-form news articles), Xsum (extreme single-sentence summaries of BBC articles), and Samsum (conversational dialogues). Each dataset presents unique challenges in terms of length, style, and domain, enabling a robust assessment of the models’ capabilities. All models were fine-tuned under controlled experimental settings using filtered and preprocessed subsets, with token length limits applied to maintain consistency and prevent truncation. The evaluation leveraged ROUGE-1, ROUGE-2, and ROUGE-L scores to measure summary quality, while efficiency metrics such as training time were also considered. An additional qualitative assessment was conducted through expert human evaluation of fluency, relevance, and conciseness. Results indicate that PEGASUS achieved the highest ROUGE scores on CNN/DailyMail, BART excelled in Xsum and Samsum, while T5 models, particularly T5-Base, narrowed the performance gap with larger models while still offering efficiency advantages compared to PEGASUS and BART. These findings highlight the trade-offs between model performance and computational efficiency, offering practical insights into model scaling—where T5-Small favors lightweight efficiency and T5-Base provides stronger accuracy without excessive resource demands. Full article

The harmonized multi-sensor satellite data assists users by providing seamless analysis-ready data with enhanced temporal resolution. The Harmonized Landsat Sentinel (HLS) product has gained popularity due to the seamless integration of Landsat OLI and Sentinel-2 MSI, achieving a temporal resolution of 2.8 to 3.5 days. However, applications that require monitoring intervals of less than three days or cloudy data can limit the usage of HLS data. Gaofen-1 (GF-1) Wide Field of View (WFV) data provides the capacity further to enhance the data availability by harmonization with HLS. In this study, GF-1/WFV data is harmonized with HLS by employing deep learning-based conditional Generative Adversarial Networks (cGANs). The harmonized WFV data with HLS provides an average temporal resolution of 1.5 days (ranging from 1.2 to 1.7 days), whereas the temporal resolution of HLS varies from 2.8 to 3.5 days. This enhanced temporal resolution will benefit applications that require frequent monitoring. Various processes are employed in HLS to achieve seamless products from the Operational Land Imager (OLI) and Multispectral Imager (MSI). This study applies 6S atmospheric correction to obtain GF-1/WFV surface reflectance data, employs MFC cloud masking, resamples the data to 30 m, and performs geographical correction using AROP relative to HLS data, to align preprocessing with HLS workflows. Harmonization is achieved without using BRDF normalization and bandpass adjustment like in the HLS workflows; instead, cGAN learns cross-sensor reflectance mapping by utilizing a U-Net generator and a patchGAN discriminator. The harmonized GF-1/WFV data were compared to the reference HLS data using various quality indices, including SSIM, MBE, and RMSD, across 126 cloud-free validation tiles covering various land covers and seasons. Band-wise scatter plots, histograms, and visual image color quality were compared. All these indices, including the Sobel filter, histograms, and visual comparisons, indicated that the proposed method has effectively reduced the spectral discrepancies between the GF-1/WFV and HLS data. Full article

Cloud detection is one of the primary challenges in preprocessing high-resolution remote sensing imagery, the accuracy of which is severely constrained by the multi-scale and complex morphological characteristics of clouds. Many approaches have been proposed to detect cloud. However, these methods still face significant challenges, particularly in handling the complexities of multi-scale cloud clusters and reliably distinguishing clouds from snow, ice and complex cloud shadows. To overcome these challenges, this paper proposes a novel cloud detection network based on the state space model (SSM), termed the Hierarchical Dilated Adaptive Mamba Network (HDAMNet). This network utilizes an encoder–decoder architecture, significantly expanding the receptive field and improving the capture of fine-grained cloud boundaries by introducing the Hierarchical Dilated Cross Scan (HDCS) mechanism in the encoder module. The multi-resolution adaptive feature extraction (MRAFE) integrates multi-scale semantic information to reduce channel confusion and emphasize essential features effectively. The Layer-wise Adaptive Attention (LAA) mechanism adaptively recalibrates features at skip connections, balancing fine-grained boundaries with global semantic information. On three public cloud detection datasets, HDAMNet achieves state-of-the-art performance across key evaluation metrics. Particularly noteworthy is its superior performance in identifying small-scale cloud clusters, delineating complex cloud–shadow boundaries, and mitigating interference from snow and ice. Full article

In modern industrial manufacturing, the mechanical properties of large bearing housing castings are critical to equipment reliability and lifespan. Traditional prediction methods relying on experimental testing and empirical formulas face challenges such as high costs, limited samples, and inadequate generalization capabilities. This study presents a machine learning approach for predicting mechanical properties of ZG270-500 cast steel, integrating multivariate data (chemical composition, process parameters) to establish an efficient predictive model. Utilizing real-world production data from a certain foundry and forging plant, the research implemented preprocessing steps including outlier handling, data balancing, and normalization. A systematic comparison was conducted on the performance of four algorithms: Backpropagation Neural Network (BPNN), Support Vector Regression (SVR), Random Forest (RF), and Extreme Gradient Boosting (XGBoost). The results indicate that under small-sample conditions, the SVR model outperforms other models, achieving a coefficient of determination (R²) between 0.85 and 0.95 on the test set for mechanical properties. The root mean square errors (RMSE) for yield strength, tensile strength, elongation, reduction in area, and impact energy are 7.59 MPa, 7.52 MPa, 0.68%, 1.47%, and 5.51 J, respectively. Experimental validation confirmed relative errors between predicted and measured values below 4%. SHAP value analysis elucidated the influence mechanisms of key process parameters (e.g., pouring speed, normalization holding time) and elemental composition on mechanical properties. This research establishes an efficient data-driven approach for large casting performance prediction and provides a theoretical foundation for guiding process optimization, thereby addressing the research gap in performance prediction for large bearing housing castings. Full article

Acute lymphoblastic leukemia (ALL) is the most common childhood cancer, with pediatric ALL having a ~90 percent cure rate, while the adult cure rate is considerably lower. B-cell acute lymphoblastic leukemia (B-ALL) is the most common subtype of ALL and is generally treated through a variety of chemotherapy drugs that can cause undesired side effects, adverse events, or other complications. Consequently, there is a need for improved understanding of the shared gene expression profiles and underlying molecular mechanisms shared among various B-ALL subtypes. In this study, 259 publicly available RNA-sequencing samples were evaluated and retrieved from the NCBI Gene Expression Omnibus (GEO) database and then pre-processed using a robust computational workflow. Differential gene expression, pathway enrichment, marker prediction, and drug repurposing analyses were then performed to facilitate a better mechanistic understanding of disease. We found both previously identified as well as novel differentially expressed genes. Specifically, we observed upregulation in the HIST2H2AA3, EPHA7, and MPR1 genes; while downregulation was observed for the IGHA1, ANGPTL1, and CHAD genes. We identified multiple pathways, including “Integrins in Angiogenesis”, to be significantly affected in B-ALL. We then used these significant pathways to predict and rank 306 existing therapeutic targets that could potentially be repurposed for B-ALL, including three that have not been evaluated in human clinical trials. Using a tree-based classification algorithm, we also predicted ADAM28 as a possible mechanistic marker. The results of this study have potential implications for patients who have been diagnosed with B-ALL by providing improved mechanistic understanding and information on possible diagnostics and repurposed therapeutics for B-ALL. Full article

This study proposes a deep learning framework to classify anteroposterior (AP) and posteroanterior (PA) chest X-ray projections automatically. Multiple convolutional neural networks (CNNs), including ResNet18, ResNet34, ResNet50, DenseNet121, EfficientNetV2-S, and ConvNeXt-Tiny, were utilized. The NIH Chest X-ray Dataset, with 112,120 images, was used with strict patient-wise splitting to prevent data leakage. ResNet34 achieved the highest performance: 99.65% accuracy, 0.9956 F1 score, and 0.9994 ROC-AUC. Grad-CAM visualized model decisions, and expert-reviewed misclassified samples were removed to enhance dataset quality. This methodology highlights the importance of robust preprocessing, model interpretability, and clinical applicability in radiographic view classification tasks. Full article

This study introduces a promising authentication framework utilizing brain–computer interface (BCI) technology to enhance both security protocols and user experience. A key strength of this approach lies in its reliance on objective, physiological signals—specifically, brainwave patterns—which are inherently difficult to replicate or forge, thereby providing a robust foundation for secure authentication. The authentication system was developed and implemented in four sequential stages: signal acquisition, preprocessing, feature extraction, and classification. Objective feature extraction methods, including Fisher’s Linear Discriminant (FLD) and Discrete Wavelet Transform (DWT), were employed to isolate meaningful brainwave features. These features were then classified using advanced machine learning techniques, with Quadratic Discriminant Analysis (QDA) and Convolutional Neural Networks (CNN) achieving accuracy rates exceeding 99%. These results highlight the effectiveness of the proposed BCI-based system and underscore the value of objective, data-driven methodologies in developing secure and user-friendly authentication solutions. To further address usability and efficiency, the number of BCI channels was systematically reduced from 64 to 32, and then to 16, resulting in accuracy rates of 92.64% and 80.18%, respectively. This reduction streamlined the authentication process, demonstrating that objective methods can maintain high performance even with simplified hardware and pointing to future directions for practical, real-world implementation. Additionally, we developed a real-time application using our custom dataset, reaching 99.75% accuracy with a CNN model. Full article

With the continuous growth of network threats, intrusion detection systems need to have robustness and adaptability to effectively identify malicious behaviors. However, factors such as noise interference, class imbalance, and complex attack pattern recognition have posed significant challenges to traditional systems. To address these issues, this paper proposes a dynamic preprocessing-enhanced DyP-CNX framework. The framework designs a sliding window dynamic interquartile range (IQR) standardization mechanism to effectively suppress the temporal non-stationarity interference of network traffic. It also combines a random undersampling strategy to mitigate the class imbalance problem. The model architecture adopts a CNN-XGBoost collaborative learning framework, combining a dual-channel convolutional neural network (CNN) and two-stage extreme gradient boosting (XGBoost) to integrate the original statistical features and deep semantic features. On the UNSW-NB15 and CSE-CIC-IDS2018 datasets, the method achieved F1 values of 91.57% and 99.34%, respectively. The experimental results show that the DyP-CNX method has the potential to handle the feature drift and pattern confusion problems in complex network environments, providing a new technical solution for adaptive intrusion detection systems. Full article