Search Results (7,234)

Soil salinization severely threatens agricultural sustainability in saline–alkali regions, and high-throughput, efficient screening of salt-tolerant rice varieties is critical to mitigating this threat. Traditional evaluation methods are constrained by low throughput, limited spatiotemporal resolution, and the lack of standardized indicators. To address these gaps, this study established a multi-scale spectral phenotyping framework integrating ground-based hyperspectral, UAV-borne multispectral, and Sentinel-2 satellite remote sensing data for high-throughput screening of salt-tolerant rice. Field experiments were conducted with 12 rice lines at five key growth stages in Ningxia, China, with synchronous ground spectral measurements and UAV image acquisition on the same day for each stage. Five feature selection methods were employed to screen salt stress-sensitive hyperspectral bands, with classification accuracy validated via a Support Vector Machine (SVM) model. The results showed that: (1) rice spectral characteristics varied dynamically across growth stages, and first-order differential transformation effectively amplified subtle spectral variations in stress-sensitive regions; (2) the Minimum Redundancy–Maximum Relevance (mRMR) method outperformed other methods, achieving 100% classification accuracy at key growth stages, with sensitive bands dominated by red edge bands (58.33%); (3) the constructed Salt Stress Index (SIR) showed strong correlations with classical vegetation indices and rice yield, and could clearly distinguish salt-tolerant and salt-sensitive rice varieties, with stable performance against field environmental noise; and (4) band matching between UAV and Sentinel-2 data enabled multi-scale data fusion and regional-scale salt stress monitoring. This framework realizes the transformation from qualitative spectral description to quantitative salt tolerance evaluation, providing standardized technical support for salt-tolerant rice breeding and precision management of saline–alkali lands. Full article

The development of AI-driven computational methods has enabled rapid and non-invasive analysis of respiratory sounds using acoustic data, particularly cough recordings. Although the COVID-19 pandemic accelerated research on cough-based acoustic analysis, many early studies were limited by insufficient data quality, lack of standardized protocols, and limited reproducibility due to data scarcity. In this study, we propose an audio analysis framework for cough-based respiratory disease screening research using COVID-19 as a clinically validated case dataset. All analyses were conducted on a single clinically acquired multicentric dataset collected under standardized conditions in certified laboratories in Mexico and Spain, comprising cough recordings from 1105 individuals. Model training and testing were performed exclusively within this dataset. The framework incorporates signal preprocessing and a comparative evaluation of segmentation strategies, showing that segmented cough analysis significantly outperforms full-signal analysis. Class imbalance was addressed using the Synthetic Minority Over-sampling Technique (SMOTE) for CNN2D models and the supervised Resample filter implemented in WEKA for classical machine learning models, both applied exclusively to the training subset to generate balanced training sets and prevent data leakage. Feature extraction and classification were carried out using Random Forest, Support Vector Machine (SVM), XGBoost, and a 2D Convolutional Neural Network (CNN2D), with hyperparameter optimization via AutoML. The proposed framework achieved a best balanced screening performance of 85.58% sensitivity and 86.65% specificity (Random Forest with GeMAPSvB01), while the highest-specificity configuration reached 93.90% specificity with 18.14% sensitivity (CNN2D with SMOTE and AutoML). These results demonstrate the methodological feasibility of the proposed framework under the evaluated conditions. Full article

Accurate extraction of crop planting structures is important for crop area and yield estimation, but complex and fragmented cropping patterns with overlapping phenology in the Hetao Irrigation District hinder reliable crop discrimination. This study proposes a hierarchical workflow that integrates vegetation masking with multi-source feature optimization for crop mapping. First, dual-temporal Sentinel-2 imagery (May and August) is used to generate a vegetation region-of-interest(ROI) mask via Otsu thresholding applied to the Normalized Difference Vegetation Index (NDVI), combined with pixel-wise maximum-value fusion to reduce phenology-driven omissions and background interference. Second, within the vegetation mask, Sentinel-2 spectral, vegetation-index, and texture features are combined with Sentinel-1 synthetic aperture radar (SAR) backscatter and SAR texture features to construct a multi-source feature set. Random Forest(RF) feature-importance ranking is used to select an effective feature subset, and four classifiers (RF, support vector machine (SVM), eXtreme Gradient Boosting (XGBoost), and convolutional neural network (CNN)) are compared under the same training/validation setting. The vegetation extraction achieves an overall accuracy of 91% (Kappa = 0.80). Using Sentinel-2 features only, the optimized subset with CNN attains the best performance (overall accuracy = 95%, Kappa = 0.93). Adding Sentinel-1 SAR texture features provides an additional improvement (overall accuracy = 96%, Kappa = 0.94), particularly for classes prone to confusion in fragmented plots. Area proportions derived from the final map are consistent with statistical yearbook data (percentage errors: maize 3.45%, sunflower 2.66%, wheat 0.11%, tomato 0.92%) under the study conditions. This workflow supports practical crop-structure monitoring in complex irrigation districts. Full article

Accurate mapping of grass species in biodiverse ecosystems, such as wetlands, is critical for ecological protection. Rapid advancements in remote sensing have established satellite data as a critical tool for wetland grass species mapping; however, its relatively coarse spatial resolution and susceptibility to cloud contamination limit the distinction of co-occurring species at fine scales. While Unmanned Aerial Vehicle (UAV) remote sensing offers high resolution and operational flexibility, relying on single-source features is often insufficient for fine-scale wetland species mapping due to the spectral similarity of co-occurring species. On the other hand, the fusion of multi-source remote sensing features (i.e., spectral, textural, and geometric features) likely provides a promising solution for achieving accurate, fine-scale grass species mapping in biodiverse ecosystems. In this study, we developed a wetland grass species mapping framework integrating spectral, textural, and geometric features derived from UAV RGB and multispectral imagery. Using a dataset of 95,880 image objects representing 24 wetland grass species classes collected in two years in Dajiu Lake National Wetland Park of China, we evaluated three machine learning algorithms—Support Vector Machine (SVM), Random Forest (RF), and eXtreme Gradient Boosting (XGBoost)—across various feature combinations. We found that while spectral features (i.e., red edge, normalized green–red difference index [NGRDI], and normalized difference vegetation index [NDVI]) (related to leaf pigment concentrations and cellular structures) exhibited the highest importance in wetland grass species mapping, textural (i.e., contrast) and geometric features (i.e., aspect ratio) significantly enhanced classification performance as complementary information, yielding improvements of up to 10.5% in overall accuracy (OA) and 0.103 in Macro-F1 scores. Specifically, the fusion of spectral, textural, and geometric features achieved optimal performance with an OA of 81.9% and a Macro-F1 of 0.807. Furthermore, the XGBoost model outperformed SVM and RF, improving OA by 9.4% and 2.8%, and Macro-F1 by 0.08 and 0.035, respectively. By identifying the optimal feature combination and machine learning algorithm, this study establishes an accurate method for wetland grass species mapping, offering new opportunities for ecological assessment and precision conservation in biodiverse landscapes. Full article

Bankruptcy prediction is currently a widely researched topic, as it typically results from a chain of negative events. Logistic Regression (LR) is one of the standard prediction tools; however, with advances in technology, machine learning (ML) methods are gaining prominence and demonstrating improvements in performance and accuracy. It remains inconclusive whether ML methods significantly outperform traditional approaches such as LR in bankruptcy prediction. In this study, we identified the most commonly applied basic ML techniques—namely, Artificial Neural Networks (ANNs), Support Vector Machines (SVMs), and Decision Trees (DTs)—which are frequently used in the literature for classification tasks. These methods were selected for empirical comparison with LR to evaluate their relative predictive performance and potential advantages in bankruptcy forecasting. In the EU, small and medium-sized enterprises (SMEs) constitute more than 99% of the economy; however, only a few survive beyond five years. This study examines bankruptcy prediction in the specific context of the Slovak Republic, using a sample of 2754 SME manufacturing enterprises from 2020 to 2021 and 3158 from 2022 to 2023. All models show good predictive performance; however, the small statistical difference between the results does not conclusively demonstrate the superiority of ML methods over LR. Full article

Motion sickness (MS) is a prevalent condition that can significantly degrade user comfort and immersion, particularly in virtual reality (VR) environments. Accurate prediction models are essential for early detection and mitigation of MS symptoms, thereby improving the overall VR experience. Most existing approaches rely on bio-physiological data acquired through body-mounted sensors, which may restrict user mobility and diminish immersion. This study proposes a less intrusive alternative, leveraging head and torso kinematic data for MS prediction. We introduce a hybrid Convolutional–Recurrent Neural Network (C-RNN) designed to capture both spatial and temporal features for enhanced classification accuracy. Using a dataset of 40 participants, the proposed C-RNN outperformed traditional machine learning models—including Support Vector Machines (SVMs), k-Nearest Neighbors (KNN), Decision Trees (DT), and a baseline Recurrent Neural Network (RNN)—across multiple evaluation metrics. The C-RNN achieved 85.63% accuracy, surpassing SVM (60%), KNN (73.75%), DT (74.38%), and RNN (81.88%), with corresponding gains in precision, recall, F1-score, and ROC AUC. These results demonstrate that head–torso motion patterns provide sufficient predictive signal for accurate MS detection, offering a non-intrusive, efficient alternative to physiological sensing that supports improved comfort and sustained immersion in VR. Full article

This study proposes a hybrid deep learning framework that integrates supervised classification and unsupervised profiling for electricity consumption analysis. In the supervised phase, a one-dimensional Convolutional Neural Network combined with Long Short-Term Memory (1D CNN–LSTM) architecture is developed to classify daily load patterns. The performance of the proposed model is compared with traditional machine learning and deep learning approaches, including Support Vector Machine (SVM), k-Nearest Neighbors (KNN), a standalone Long Short-Term Memory (LSTM) model, a Transformer-based model, and a standalone 1D CNN model. Experimental results on the Precon house dataset and the CU-BEMS dataset demonstrate that the proposed hybrid architecture outperforms the benchmark models, achieving classification accuracies of 87.59% and 86.40%, respectively. In the unsupervised phase, the trained CNN–LSTM encoder is utilized as a deep feature extractor. The resulting 32-dimensional latent embeddings are clustered using K-Means, Gaussian Mixture Model (GMM), Agglomerative, Spectral, and Ensemble methods. Clustering robustness is evaluated through bootstrap-based stability analysis using the Adjusted Rand Index (ARI) and the Normalized Mutual Information (NMI). The results demonstrate stable and interpretable electricity consumption profiles, particularly in the residential dataset, where near-perfect clustering stability is observed for K-Means. The proposed framework provides both improved classification performance and robust consumption profiling based on deep embedding, offering a practical tool for energy management. Full article

Targeting resource-constrained Internet of Things (IoT) devices, this paper proposes Stuck-at-Fault Physical Unclonable Function (SAF-PUF), a lightweight Resistive Random-Access Memory (RRAM)-based PUF that exploits the intrinsic addresses of manufacturing-induced SAF defects as a stable entropy source. By using the coordinates of Stuck-at-1 (SA1) cells to seed a 32-bit Linear Feedback Shift Register (LFSR), SAF-PUF generates robust, variable-length responses with zero Bit Error Rate (BER) across a wide temperature range from −40 °C to 125 °C, without any error-correction circuitry. Experimental results based on 100,000 Challenge–Response Pairs (CRPs) demonstrate strong resilience against machine learning (ML) attacks, with prediction accuracies of logistic regression (LR), support vector machines (SVM), neural networks (NN) and convolutional neural networks (CNNs) remaining close to 50%. Moreover, a “use-then-conceal” mechanism is introduced to enhance post-authentication security, enabling response obfuscation with minimal cell reconfiguration. These features make SAF-PUF a high-security, low-overhead hardware root of trust suitable for IoT applications. Full article

Frontal alpha asymmetry (FAA), a pattern of brain activity that reflects the difference in alpha wave power between the left and right frontal areas of the brain, is considered a stable marker for an individual’s tendency to experience either more approach-related or withdrawal-related emotions. On the other hand, electrodermal activity (EDA) measures arousal by tracking changes in skin sweat, which are controlled by the sympathetic nervous system. This study explores the interrelation between EDA features, obtained from time and frequency domains, with FAA by means of the mutual information. Multiple cognitive tasks such as EAT, ship search, PVT and N-Back were analyzed in 10 participants in intervals of two hours over 24 h (12 trials), in which they had to face sleep deprivation conditions. The most informative EDA features about FAA, were used to identify the two main clusters associated to high and low FAA values through the hierarchical agglomerative clustering approach. Once data is labeled, a supervised classifier based on support vector machines (SVMs) is used to identify positive and negative emotional states by using a rigorous one-trial out cross-validation scheme. Results show consistent performance within tasks and trials, achieving accuracy values over 80% on average, giving an important insight about the use of EDA signal as an alternative to the more complex FAA measurement for tracking positive or negative emotional states. Full article

Gully erosion is a significant threat to the sustainability of soil in Mediterranean basins. Despite its impact, there is a lack of research providing accurate regional-scale cartography of complete gully networks. This study aims to automatically map the gully network in the olive-growing landscapes of the Guadalquivir basin (Spain) using Machine Learning (ML) algorithms: Random Forest (RF), Support Vector Machine (SVM), Decision Tree (DT), and Logistic Regression (LR). We integrated these models with 17 predictive variables (including hydrotopographic, climatic, and edaphic factors) and the Gully Head Initiation (GHI) index. RF was the most suitable model, achieving an Area Under the Curve (AUC) of 0.91 and an F1-score of 0.83, and enabled the delineation of a gully network totalling 8439.05 km. Variable importance analysis revealed that flow accumulation (17.33%) and the GHI index (nearly 30%) were the primary predictors, with the Rainy Day Normal (RDN)-based formulation outperforming the maximum daily precipitation (Pmax)-based one. Spatially, countryside hill landscapes exhibited the highest gully densities (42.50 m/ha). The results demonstrate the effectiveness of combining ML with physically based indices to generate high-resolution gully cartography for soil conservation planning in Mediterranean olive groves. Full article

Background: The integration of multi-omics data, such as genomics and transcriptomics, into artificial intelligence models has advanced precision medicine. However, their clinical applicability remains limited due to model complexity. We integrated DNA mutation, RNA expression, and A>I(G) RNA editing data to develop a predictive model for drug response in breast cancer. Methods: We analyzed 104 patients from the Breast Cancer Genome-Guided Therapy Study (ClinicalTrials.gov: NCT02022202). Clinical variables, gene expression, tumor and germline DNA variants, and RNA editing features were integrated into machine learning models to predict therapy response. Generalized linear models (GLM), random forest (RF), and support vector machines (SVM) were trained and evaluated across multiple random 70/30 train-test splits. Feature selection was performed exclusively within the training set using LASSO regularization. Model performance was assessed using the F1-score on independent test sets. The additive effect of RNA editing was evaluated using paired comparisons across identical train/test splits. Results: We characterized the cohort using clinical, mutational, transcriptomic, and RNA editing profiles in 69 non-responders and 35 responders. Across repeated splits, adding RNA editing frequently maintained or modestly improved predictive performance, particularly in expression-based models, with paired analyses showing a statistically significant increase in F1-score. Conclusions: RNA editing represents a complementary molecular layer that can enhance multi-omic models for therapy response prediction in breast cancer, supporting further investigation of epitranscriptomic features in precision oncology. Full article

Forecasting cryptocurrency prices is challenging due to extreme volatility, nonlinear dynamics, and frequent structural shifts in digital asset markets. While recent research increasingly applies deep learning architectures, the predictive advantage of highly complex models in noisy financial environments remains uncertain. This study evaluates the forecasting performance of shallow and deep learning approaches by comparing Support Vector Machines (SVM), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU) models, along with hybrid configurations (GRU + SVM, LSTM + SVM, and GRU + LSTM). Using daily data spanning from 1 October 2020 to 23 September 2025 for five major cryptocurrencies—Bitcoin, Ethereum, Binance Coin, Solana, and Ripple—the models are estimated within a consistent framework and assessed using out-of-sample performance metrics, including MAE, MAPE, MSE, and R². The results indicate that greater algorithmic complexity does not necessarily improve forecasting accuracy. In several cases, the parsimonious SVM model outperforms deep neural network architectures, particularly for highly volatile assets, while hybrid models fail to provide systematic improvements and sometimes amplify prediction errors. SHapley Additive exPlanations analysis further shows that immediate price-based variables dominate predictive power, whereas many lagged technical indicators contribute relatively limited explanatory value. Overall, the findings underscore the importance of algorithmic parsimony, suggesting that simpler machine learning models may deliver more robust forecasts in highly volatile cryptocurrency markets. Full article

Early-stage fungal contamination in maize kernels is difficult to identify visually and it can cause severe quality and safety risks during storage and transportation. Short-wave infrared (SWIR) hyperspectral imaging offers a rapid, non-destructive approach by capturing chemical information related to water, proteins, and lipids. This study investigates the early detection and classification of Gibberella zeae contamination in maize kernels using SWIR hyperspectral imaging combined with machine learning. Two maize varieties were artificially inoculated and cultured under controlled conditions, followed by hyperspectral data collection over six contamination stages. Various preprocessing techniques including standard normal variate (SNV), second derivative (SD), multiplicative scatter correction (MSC), and derivatives were evaluated to enhance data quality. Feature wavelength selection was performed using successive projections algorithm (SPA), competitive adaptive reweighted sampling (CARS), and uninformative variable elimination (UVE), significantly reducing redundancy and improving classification performance. Multiple models, including linear discriminant analysis (LDA), multilayer perceptron (MLP), support vector machine (SVM), a convolutional neural network (CNN), long short-term memory (LSTM) network, and a hybrid architecture Transformer that integrated a CNN, a LSTM network, and a Transformer (abbreviated as CLT), were constructed for both binary (healthy vs. contaminated) and multiclass classification tasks. Specifically, the multiclass task consisted of six contamination stages corresponding to contamination time from Day 0 to Day 5. The best binary classification task accuracy of 100% was achieved using SNV-preprocessed data with the MLP model. For multiclass classification task, the SD-preprocessed LDA model reached a test accuracy of 92.56%. Combined with appropriate preprocessing, feature selection and modeling, these results demonstrate that hyperspectral imaging is a powerful tool for the non-destructive, early-stage identification of fungal contamination in maize kernels, offering strong support for food safety and quality monitoring. Full article

High-dimensional mixed data often lack a unified semantic representation for continuous and discrete attributes, which hinders mixed-attribute similarity modeling and can result in unstable reducts and overfitting in existing neighborhood rough set (NRS) methods. To address this issue, we propose IF-EMD-SPA, an attribute reduction method for NRS grounded in Information Flow theory. Unlike conventional NRS methods that rely on discretization or a single reduction criterion, IF-EMD-SPA first establishes a unified representation framework for heterogeneous attributes based on classifications and an Information Channel Core. It then integrates Earth Mover’s Distance (EMD) and Set Pair Analysis (SPA) to define a similarity metric for mixed attributes. In addition, a three-stage greedy reduction strategy is designed under the dual constraints of dependency preservation and structural error, consisting of dependency-driven forward selection, similarity-driven structure completion, and backward redundancy removal. Experiments on five UCI benchmark datasets and two high-dimensional gene expression datasets show that IF-EMD-SPA achieves average accuracies of 93.5% (k-Nearest Neighbors, KNN), 93.9% (Support Vector Machine, SVM), and 90.8% (Classification and Regression Trees, CART), with SVM achieving the best results on all seven datasets. Under CART, it reaches 100% accuracy on Wine and WPBC, improving performance by up to 37.5 percentage points over comparison methods. Full article

Accurate and rapid identification of bacterial species is essential for public health, clinical diagnostics, and environmental monitoring. Although Raman spectroscopy offers a powerful, non-invasive alternative, reliance solely on spectral data often fails to distinguish species with highly similar signatures, particularly when the discriminating features are subtle. This difficulty is frequently compounded by a lack of integrated biological prior knowledge, which can hinder model performance. To address these challenges, we introduce BactoRamanBioNet, a novel multimodal neural network architecture. Our model employs a synergistic approach that utilizes a ResNet-Transformer architecture to capture complex spectral patterns and a CLIP text encoder to incorporate descriptive biological information, thereby enabling highly accurate multimodal classification of bacterial species. Empirical results demonstrate that BactoRamanBioNet achieves a classification accuracy of 98.2% and an F1-score of 98.0%. This performance surpasses the current state-of-the-art deep learning model, ResNet-1D, by 2.4% in accuracy and 2.0% in F1-score. Moreover, our model outperforms traditional classifiers, such as Support Vector Machine (SVM) and Random Forest (RF), by 9.8% and 7.9% in accuracy, respectively, while also exhibiting significant improvements in precision and recall. By establishing a new benchmark in performance and robustness, BactoRamanBioNet offers a powerful and reliable framework for automated microbiological analysis, paving the way for next-generation diagnostic systems. Full article