Search Results (3,749)

Flying Ad Hoc Networks (FANETs) composed of multiple unmanned aerial vehicles (UAVs) are a promising solution for emergency wireless communications when terrestrial infrastructure is unavailable. However, ensuring reliable Quality of Service (QoS) in these highly dynamic networks remains challenging due to topology changes, varying propagation conditions, and congestion. This work proposes a lightweight machine learning-based QoS optimization framework for multi-UAV emergency communications that combines realistic mobility modeling, empirical channel measurements, and adaptive traffic prioritization. UAV mobility patterns are generated with ArduSim, while LoS/NLoS propagation models are derived from real UAV flight experiments and integrated into ns-3. Multiple supervised machine learning algorithms—including Decision Trees, Random Forest, Support Vector Machines, k-NN, Gradient Boosting, and CatBoost—are trained using four input features derived from the network state: ${\mathrm{CBR}}_{\mathrm{src}}$, ${\mathrm{QP}}_{\mathrm{src}}$, ${\mathrm{CBR}}_{\mathrm{dst}}$, and ${\mathrm{QP}}_{\mathrm{dst}}$. Simulation results show that the proposed AI SMOTE EMERGENCY scheme, based on CatBoost, improves the Packet Delivery Ratio (PDR) by approximately 43% over the No-QoS baseline, achieving 89–93% delivery across all four application ports. Compared with EDCA, the proposed scheme maintains reliable delivery for all services, increases emergency throughput by 34–36%, and reduces end-to-end delay by about 70%. In addition, the higher delivery reliability translates into clear communication energy benefits, reducing energy waste across all evaluated topologies when compared with the No-QoS baseline. The inference time remains below 0.002 s, supporting real-time QoS adaptation in resource-constrained UAV networks. Full article

Honey quality and authenticity assessment require rapid and reliable analytical tools capable of supporting both laboratory and on-site applications. Near-infrared (NIR) spectroscopy represents a non-destructive and cost-effective approach; however, its performance depends on instrument characteristics and chemometric strategies. This study compared one benchtop and two portable NIR-based systems for predicting key physicochemical parameters (moisture, electrical conductivity, glucose, fructose, reducing sugars, pH, hydroxymethylfurfural, and diastatic activity) and for discriminating botanical origin in 80 Italian honey samples. Spectral data were processed using multiple pre-processing techniques and algorithms (PLS, k-NN, Random Forest, SVM), with and without wavelength selection (siPLS and CARS-PLS), under cross-validation schemes. The benchtop system achieved the highest regression performance (R² up to 0.91 for glucose and electrical conductivity) and the most reliable botanical classification (balanced accuracy = 0.90). Portable systems showed moderate predictive ability for bulk compositional parameters (R² up to 0.86 for glucose) but limited classification performance. Wavelength selection resulted in only marginal improvements. Hydroxymethylfurfural and diastatic activity were poorly predicted (R² up to 0.49), likely due to their low concentrations. Summarising, the main outcomes suggested that tested portable NIR settings are also suitable for rapid quantitative screening of chemical traits, whereas the benchtop system provide higher precision for botanical qualitative authentication. Full article

Geographical origin identification of fragrant pears is crucial for ensuring fruit quality, protecting regional brand value, and maintaining market order. However, pears from different origins often exhibit highly similar appearance and physicochemical properties, making rapid and nondestructive identification challenging for traditional methods. This study proposes a hyperspectral origin identification method based on an enhanced one-dimensional convolutional neural network (ECNN-1D) incorporating an Efficient Channel Attention (ECA) mechanism, using visible–near-infrared (Vis–NIR) and short-wave infrared (SWIR) spectral data. To address the technical challenges of highly similar spectra, redundant features, and complex information distribution, ECNN-1D enhances discriminative spectral feature representation, overcoming limitations of conventional machine learning and standard deep learning models in feature extraction and classification stability. Systematic comparisons with machine learning models (LDA, RF, KNN, SVM) and deep learning models (VGG-1D, ResNet-1D, CNN-1D) showed that while all models performed well on Vis–NIR spectra, ECNN-1D achieved the highest test accuracy of 98.94% and F1 score of 98.95% on the more challenging SWIR spectra, outperforming other approaches. These results indicate that ECNN-1D enables high-precision, nondestructive origin identification of fragrant pears, with potential cost advantages, providing a reliable technical solution for fruit traceability and quality supervision. Full article

Estimating the state of charge (SoC) is a critical task for effective management of electric vehicle batteries. Simple machine learning methods (LR, KNN, etc.) often suffer from limited prediction accuracy, while deep learning approaches (LSTM, CNN, etc.) generally require high computational resources and behave as black-box models with limited explainability. To overcome these limitations, the present work proposes a SoC estimation approach based on the Light Gradient Boosting Machine (LightGBM). The proposed model provides a balanced trade-off between prediction accuracy and computational efficiency. Furthermore, feature engineering is performed to derive additional informative features, improving the model’s ability to learn driving conditions and battery dynamics. In addition, the study incorporates a seasonal analysis by evaluating the model under both summer and winter conditions, allowing the impact of environmental variations on SoC estimation performance to be investigated. Moreover, Explainable Artificial Intelligence (XAI) techniques are employed to interpret the model predictions. Evaluation on real-world on-road data demonstrated that the proposed model achieved substantial improvements in estimation performance compared to recent studies. Full article

The ability to continuously learn over time by incorporating new information while holding onto previously acquired expertise is known as incremental learning (IL). Although this concept is fundamental to human learning, existing machine learning techniques have a significant propensity to forget prior experience by overwriting previously learned patterns from classes. The continuous learning of new information in K-nearest neighbor (KNN) with lazy learning strategies compounds to loss of old knowledge upon learning new information and stability-plasticity dilemma. The change in new data points and data distributions in unforeseen ways impacts KNN’s ability to adapt to changes in class label distribution, leading to concept drift. This experiment models a hybrid 3WDKNN-based incremental learning algorithm (ILA) designed for application in a heterogeneous and dynamically changing environment. This model addresses the limitations of KNN by overcoming computational costs and inefficiencies associated with loss of information in classes, while facilitating incremental learning to attain high predictive accuracy in crop yield datasets. The algorithm employs weighted voting to identify optimal assigned classes for the nearest neighbor and uses memory reconstruction strategy for class incremental learning until the memory is full without forgetting. Using weighted voting for the best assigned classes for the nearest neighbor, the algorithm uses a local mean vector to determine the best distances for the shortest-term incremental learning to achieve the highest performance accuracy in a concept drift environment. The hybrid 3WDKNN_ILA was developed and evaluated alongside advanced algorithms within the same dataset context. The model improves performance in incremental learning contexts by utilizing current concepts and minimizing errors on both current and recent data to avoid parameterization. The model achieves optimal efficient incremental learning by mitigating intentional loss and minimizing errors associated with valuable class information derived from aggregated mean values through class rectification and transfer. The hybrid model achieves the best efficient performance accuracy in all the tested weighted averages of 200W, 500W, and 1000W with tested set K values of 5, 9, and 13K. This hybrid model demonstrates performance accuracy of 97% at a value of 13K, whereas 3WD_KNN achieves 96% at 9K, HoKNN attains 89% at 13K, and 1IKNN reaches 88% at 9K accuracy, respectively. The integrated novelty in the hybrid 3WDKNN_ILA proves superior in terms of computational efficiency, accuracy, and high-level incremental performance and learning in comparison with other tested models of algorithms. Full article

Background/Objectives: Assessment of infant General Movements (GMs) is essential for early detection of neurological disorders such as cerebral palsy, but current methods depend on expert interpretation. This study proposes an automated and interpretable framework for infant movement classification using pose-based representations from RGB videos. Methods: A pose-driven pipeline was developed to extract 2D skeletal key points using a two-stage tracking strategy. Joint coordinates were normalized using the shoulder center and inter-shoulder distance. Videos were segmented into overlapping temporal windows, and each segment was represented using Pose-LBP histograms and motion ratio features. Classification was performed with a cost-sensitive subspace k-nearest neighbor ensemble (CSS-kNN-E). Performance was evaluated using stratified 10-fold cross-validation on a five-class infant movement dataset. Results: The proposed method achieved 99.16% (±0.48%) accuracy, 99.19% (±0.50%) sensitivity, 99.76% (±0.13%) specificity, and 99.23% (±0.48%) F1-score. The model demonstrated strong discrimination across classes and robustness to class imbalance. Conclusions: The framework provides an accurate and scalable solution for automated infant movement analysis. It reduces dependency on expert evaluation and has strong potential for early clinical screening and decision support. Full article

This study presents a definitive framework for Cocos nucifera (coconut) shell valorization, integrating high-resolution thermogravimetry with advanced machine learning. Physicochemical analysis confirms a high-energy feedstock (45.7% carbon, 71.5% volatiles), with SEM/XEDS and FTIR revealing heterogeneous, lignocellulosic, catalytic-rich structural matrix. TG/DTG analysis identified distinct degradation windows: hemicellulose (135–395 °C), cellulose (270–430 °C), and protracted lignin decomposition (275–675 °C). Kinetic modeling indicates that pyrolysis follows a third-order (F3) continuous degradation mechanism across the studied range, supported by high correlation coefficients (R² = 0.93–0.96). The mean kinetic and thermodynamic parameters—specifically an activation energy of 165 kJ·mol⁻¹ (calculated across the 10–60 wt% conversion range during hemicellulose and cellulose pyrolysis), a positive activation enthalpy (159 kJ·mol⁻¹), and a Gibbs free energy of activation (155 kJ·mol⁻¹)—suggest that the thermochemical conversion of coconut shell is an endothermic, non-spontaneous process with moderate energy requirements. Furthermore, the integration of kNN machine learning yielded near-perfect predictive metrics (R² ≈ 1.000) using optimized hyperparameters (k = 85 for TG, k = 100 for DTG, and k = 50 for conversion). These findings suggest that coconut shells can be efficiently valorized as a high-energy feedstock, with data enabling reliable and optimized prediction of thermal degradation to minimize experimental waste. Full article

The Yellow River Basin contains abundant coal resources; however, its ecological environment is inherently fragile, and vegetation degradation has been further intensified by extensive mining activities. Accurate classification of individual tree species in mining-affected areas is therefore essential for assessing ecological conditions and establishing a scientific foundation for targeted restoration and sustainable management. To address this need, an evaluated machine learning framework was developed and evaluated for individual tree species classification in a coal mining area of the Yellow River Basin using integrated unmanned aerial vehicle (UAV) data. A comprehensive feature set was constructed by extracting 278 attributes per tree. These attributes included 224 spectral bands and 29 hyperspectral indices derived from hyperspectral imagery, 24 textural metrics obtained from RGB orthophotos, and one canopy height feature generated from a LiDAR-derived model. Based on ground-truth data from 1095 individual trees, seven machine learning algorithms were trained and systematically compared: Random Forest (RF), Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Decision Tree (DT), Gradient Boosting (GB), Logistic Regression (LR), and XGBoost. Statistical significance testing using 5 × 5 repeated cross-validation, together with the Friedman test and post hoc Nemenyi test, and additional model stability analysis consistently identified XGBoost as the optimal classifier. On an independent test set, XGBoost achieved high accuracy (Overall Accuracy = 0.897, Kappa = 0.811) with an efficient training time of 2.36 s. Further analysis demonstrated the critical and complementary roles of hyperspectral and structural features in species discrimination. The optimized model was subsequently applied to generate a detailed wall-to-wall tree species map across the entire mining area. Overall, this study presents a statistically informed comparison of classifiers for multi-source feature-based species discrimination and delivers an evaluated and practical pipeline for effective vegetation monitoring. The proposed framework provides a scientific tool for assessing and managing ecological recovery in complex mining environments, particularly within ecologically sensitive regions such as the Yellow River Basin. Full article

Accurate yield estimation is vital for precision wheat management and breeding. Traditional methods based on single growth stages or single-source data cannot capture cumulative growth effects, limiting prediction accuracy. UAV remote sensing provides high-resolution, multi-source, and multi-temporal data, enabling improved non-destructive yield estimation. In this study, UAV-based multispectral and RGB imagery were collected at six key growth stages, and vegetation indices, texture, and color features were extracted to develop yield prediction models using RF, XGBoost, and KNN under single- and multi-temporal scenarios. The results showed that red-edge-based vegetation indices were highly sensitive to wheat yield and outperformed texture- and color-based features. Multi-feature fusion further improved prediction accuracy at key growth stages, particularly during booting and flowering (R² = 0.53–0.67). Compared with single-temporal models, multi-temporal data fusion significantly enhanced yield estimation accuracy, achieving a maximum R² of 0.72 by integrating data from the late-jointing, booting and flowering stages. Among the algorithms, XGBoost and KNN exhibited superior accuracy and stability across most growth stages. Overall, these results demonstrate that integrating UAV-based multi-source and multi-temporal remote sensing data effectively improves the accuracy and robustness of wheat yield estimation, providing valuable technical support for precision agriculture and phenotyping-assisted breeding. Full article

Background: Machine learning-based Artificial Intelligence (AI) models have shown significant potential in the biomedical field, offering promising advances in diagnostics, personalized medicine, and patient care. However, to build these models, we have to deal with important challenges, including (1) the scarcity and low quality of available datasets in many important applications and (2) privacy concerns associated with sensitive patient data. Synthetic data (SD) generation has emerged as a promising strategy to address these challenges, yet many existing approaches struggle to simultaneously preserve privacy and accurately model tabular data, the predominant format in healthcare. Methods: We propose Kernel Density Estimation–K-Nearest Neighbors (KDE-KNN), a privacy-aware tabular data generation method, and evaluate its performance against state-of-the-art techniques. Using sepsis detection as a real-world case study, we assess both data utility and privacy protection. Results: Models trained on KDE-KNN-generated SD outperformed those trained on real data across both internal testing and external validation. In particular, a support vector machine achieved superior performance when trained on SD relative to real data. This gain is likely driven by the balanced class distribution of the synthetic dataset, underscoring KDE-KNN’s utility as an effective data balancing strategy. Consistent performance in external validation further supports the robustness and generalizability of the proposed approach. Privacy evaluation indicated a lower re-identification risk, with a mean distance to closest record of 4.971 between synthetic and real samples, compared with 2.715 among real samples. Conclusions: KDE-KNN effectively captures underlying population distributions while generating high-quality SD that preserve statistical fidelity and protect sensitive information. By balancing the trade-off between utility and privacy, the method produces representative datasets without exposing individual records. These findings position KDE-KNN as a valuable tool for data-scarce and privacy-sensitive applications, with broad potential across healthcare and other data-driven domains. Full article

Framed within data-centric artificial intelligence, this study integrates statistics, geotechnologies and AI to improve water quality prediction. The primary objective was to identify the minimum sample size required to train robust and accurate machine learning models. Based on 30 sampling points in a tropical wetland in northern Colombia, ammonium concentration was selected as the target variable, and total dissolved solids, suspended solids, phosphate, dissolved oxygen, nitrate and chemical oxygen demand were chosen as predictors. Because 30 observations are insufficient to train robust models, data augmentation was performed using ordinary kriging (OK) and empirical Bayesian kriging (EBK). From the kriging-interpolated surfaces, 1000 synthetic points (randomly and spatially distributed while preserving the estimated spatial structure) were sampled; from this expanded dataset, subsamples of varying sizes were drawn to train six algorithms: multiple linear regression (MLR), random forest (RF), k-nearest neighbours (k-NN), gradient boosting machines (GBM), multilayer perceptron (MLP) and radial basis function neural network (RBF-NN). The RF, k-NN, MLP, RBF-NN and GBM models trained on the interpolated data exhibited excellent performance: in the testing phase, they achieved adjusted coefficients of determination > 0.95 and symmetric mean absolute percentage errors (SMAPEs) < 10%, and the resulting predictive surfaces showed comparable performance under external validation. According to the criteria of stability, goodness of fit, and external validation, the optimal minimum sample size for most algorithms was 104 observations. These results represent a significant advance in mitigating data scarcity in water quality modelling. The identification of effective data augmentation methods and the determination of appropriate sample sizes, as demonstrated here, support the robust application of AI techniques in water quality prediction. The proposed strategy is transferable to other quantitative, spatially continuous environmental variables and thus contributes to the development of the emerging subdiscipline of geospatial artificial intelligence (GeoAI). Full article

Accurate prediction of blasting-induced peak particle velocity (PPV) is critical for assessing structural damage risk and ensuring safe tunnel construction. This study proposes an AI agent-based Evaluator-Optimizer workflow that automates the model-development pipeline from prepared dataset input through model training, performance evaluation, hyperparameter optimization, and ensemble construction, with limited manual intervention after dataset definition. The framework employs a multi-agent architecture comprising three collaborative agents—an Orchestrator, an Evaluator, and an Optimizer—supported by a large language model (LLM) reasoning layer. The Evaluator agent analyzes model performance across multiple metrics and generates diagnostic insights; the Optimizer agent translates these insights into structured optimization plans; and the Orchestrator coordinates the evaluate-optimize loop and stopping logic. The workflow was applied to a dataset of 102 tunnel blasting events. Nine candidate regression models spanning tree-based, kernel-based, neural network, and regularized linear families were trained and evaluated. The results show that the workflow enables three substantive observations: (i) across five tree-based models the powder factor is the dominant predictor (28.7–50.5% relative importance); (ii) under 50 Monte-Carlo repeated 80/20 splits, KNN and the Voting ensemble are statistically indistinguishable and form the most stable performance cluster, while Gradient Boosting lies within the same cluster with larger variance; and (iii) under nested 5 × 5 cross-validation, the un-leaked R² for the top models is about 0.84–0.86, which quantifies the small-sample over-optimism that any future PPV study on single 80/20 splits should expect. The study therefore contributes both a portable agent architecture for tabular geotechnical regression and a concrete cautionary result about single-split benchmarking. Full article

Machine learning helps intrusion detection systems learn new assaults quickly. These systems train on a dataset with several threats and may identify odd behavior. This research detects intrusion using Random Forest, KNN, and Gaussian Naive Bayes. We run the model on a comprehensive dataset. Dynamics Feature Selector (DFS) improves performance. This technique eliminates unnecessary inputs and improves predictions using statistical analysis and feature significance. DFS effectiveness is tested using the NSL-KDD dataset. The recommended hybrid approach, Gaussian NB, Random Forest, and KNN are compared in meta-learning. Getting excellent accuracy with fewer characteristics is the aim. In order to demonstrate how the model may function in actual cybersecurity scenarios, the final test makes use of common performance metrics such as accuracy, precision, recall, and F1-score. The proposed method outperforms previously reported results with around 96.09% accuracy, 93.21% precision, 92.53% recall, 92.79% F1-score, and 93.65% average performance. Full article

This study evaluated a portable multispectral imaging (MSI) system for simultaneously assessing chicken meat quality, including freshness and authenticity detection. For freshness, total aerobic counts and MSI analyses were performed on fresh and thawed samples throughout storage at 4 °C. For authenticity (product condition and origin), Greek and Danish chicken samples, both fresh and thawed, were analyzed in separate laboratories using identical instruments. Data were modeled using PLS-R, kNN, and SVM. Model performance for total viable count prediction was evaluated via R² and RMSE, while classification used accuracy, specificity, recall and precision. PLS-R beta coefficients highlighted the contribution of specific wavelengths. For Greek chicken fillets, kNN achieved the best performance on fresh samples (RMSE = 0.347, R² = 0.979), while PLS-R performed best on thawed samples (RMSE = 0.787, R² = 0.859). Wavelength 460 nm was the most important for all freshness predictions. Differences between Danish and Greek samples were observed in classification performance, optimal algorithms and key wavelengths. For origin classification (using fresh and thawed samples), models reached near-perfect accuracy, with PLS-DA highlighting 660 nm and 850 nm as most significant. These results demonstrate the MSI system’s potential for the rapid, accurate and simultaneous evaluation of multiple chicken meat quality attributes using a single instrument. Full article

In this study, a low-cost AS7265x-based multispectral electronic tongue system was developed for estimating milk composition and adulteration indicators and supported with an explainable artificial intelligence (XAI) framework. Experimental analyses were conducted on 190 augmented commercial milk samples, where fat, protein, solids-not-fat (SNF), density, freezing point, and added water ratio were treated as target variables. Sensor data were modeled as RAW, DERIVED, and FUSION feature sets, and regression performance was compared using Random Forest, Gradient Boosting, AdaBoost, KNN, and XGBoost. Model validation was carried out with both five-fold cross-validation and Leave-One-Out (LOO) strategies to assess field-level generalizability. Results showed that a narrow-band, low-cost optical sensor platform can estimate not only fat and protein but also SNF, density, and freezing point with high accuracy. Within the XAI framework, permutation-based importance analysis and SHAP were used to identify critical spectral bands for each target parameter, enabling data-driven recommendations for band-oriented sensor design optimization. The study presents a scalable methodology that integrates low-cost sensor design, multi-parameter quality estimation, and explainable modeling beyond traditional fat–protein-focused approaches. Across all six targets, the XAI analysis consistently identified the near-infrared channel at 860 nm (asIR_3) as the most informative band, reflecting the combined effect of water absorption and Mie scattering by fat globules; the visible channel at 680 nm (asVIS_4) emerged as a secondary band, reflecting dissolved-matter scattering. These bands are therefore the natural starting point for cost-reduced versions of the sensor. Among the compared feature sets (RAW, DERIVED, FUSION), the 18-band RAW configuration provided the most balanced performance across all six targets. Full article