Search Results (1,624)

Background/Objectives: Trunk injection of oxytetracycline (OTC) can suppress Candidatus Liberibacter asiaticus (CLas) and improve the productivity of citrus trees affected by huanglongbing (HLB), a devastating bacterial disease, but conventional acidic formulations may cause phytotoxicity and exacerbate trunk injury. This study evaluated a proprietary adjuvant intended to stabilize OTC at higher pH and assessed streptomycin (STM) as an alternative or complement to OTC. Methods: Two commercial field trials with HLB-affected ‘Valencia’ sweet orange trees compared a 2 × 4 factorial combination of two formulations, adjuvant/high-pH and no-adjuvant/low-pH, and four antibiotic treatments: none, OTC, STM, and OTC + STM. Tree growth, canopy health, phytotoxicity, CLas load, external wound responses, fruit drop, yield, and fruit quality were evaluated. Results: Tree growth and canopy health were not affected by treatment. The adjuvant/high-pH formulation caused severe canopy phytotoxicity in trial 1 and increased wound width, wound length, and bark cracking in both trials, compared to the control. OTC and OTC + STM generally reduced fruit drop, increased yield, and improved fruit quality attributes though effects on CLas were moderate and not consistent. STM alone provided no consistent therapeutic or horticultural benefit, and OTC + STM were not consistently superior to OTC alone. Conclusions: OTC was the primary effective component to mitigate HLB in affected citrus trees. The adjuvant/high-pH formulations did not affect OTC efficacy but caused tree injury, even in the absence of OTC. Novel trunk-injection formulations must balance chemical stability and delivery with plant tissue compatibility and safety to meet commercial viability. Full article

Wind farm layout optimization (WFLO) requires balancing energy production against infrastructure requirements while providing decision-makers with a defensible method for selecting Pareto-optimal alternatives. This study proposes a preference-guided NSGA-III framework integrated with the Fuzzy Analytic Hierarchy Process (FAHP) for the multiobjective optimization of annual energy production (AEP) and internal road length. Wake interactions are modeled using the Jensen wake model with sum-of-squares superposition, while the internal road network is approximated using a Euclidean minimum spanning tree. Decision-maker preferences are represented through triangular fuzzy pairwise judgments between AEP and road length. The fuzzy priorities are defuzzified and normalized to obtain objective weights, which are used conditionally during partial-front environmental selection and subsequently to rank the final nondominated solutions. The framework was evaluated on a 20-turbine, 2000 m × 2000 m test case using a population of 50, 300 generations, and 30 independent runs per algorithm. Compared with conventional NSGA-III, the proposed NSGA-III FAHP method increased mean hypervolume from 16.5012 to 28.1578. The improvement remained statistically significant after Holm correction ($p=4.617\times {10}^{-7}$) and showed a large effect size (Cliff’s ($\delta =0.809$)). Differences in the ratio of nondominated individuals, uniformity degree, execution time, best AEP, and best road length were not statistically significant. Sensitivity analysis across seven AEP-road preference scenarios showed that balanced and moderately biased weights produced the highest hypervolume, while AEP remained stable between 84.904 and 84.948 GWh. These results indicate that the proposed framework primarily improves objective-space coverage and provides an explicit mechanism for incorporating uncertain preference information into WFLO. Full article

This study addresses a regime-conditioned question in electricity theft detection: when only monthly billing series and inspection-confirmed labels are available, which supervised model families recover irregular consumption without relying on the temporal resolution of advanced metering infrastructure (AMI)? The working sample comprises 4000 utility customers and 864 confirmed theft cases, each represented by 53 monthly kWh values from January 2021 to May 2025. After majority-class undersampling that retains all theft observations and construction of a balanced 1:1 learning set, eight classifiers are compared under an 80/20 stratified split: K-Nearest Neighbors, Decision Tree, Support Vector Machine, Random Forest, two dense multilayer perceptrons, Long Short-Term Memory, and a one-dimensional Convolutional Neural Network. Performance is assessed through threshold-optimized accuracy together with precision, recall, F1-score, the area under the receiver operating characteristic curve (AUC), and confusion matrices. On the hold-out test set, Random Forest and the compact dense network both reach an accuracy of 0.685; Random Forest attains the highest AUC (0.748) and F1-score (0.677). Even so, these models miss about one-third of the hold-out theft accounts (59 and 65 false negatives out of 173). Sequential deep models underperform on this short monthly regime. The results support ensembles and compact dense networks for monthly theft screening and indicate that AMI-oriented sequential gains do not transfer automatically to 53-point billing vectors under the present protocol. Full article

Financial institutions face an escalating volume of cybersecurity threats, yet existing decision frameworks rarely link predictive analytics to operational security priorities. Drawing on Task-Technology Fit theory, this study develops a machine learning-based decision-support framework to classify cybersecurity breach types in financial institutions and to identify the organizational risk factors that determine them. Analyzing 935 publicly disclosed incidents from the VERIS Community Database (VCDB, NAICS 52), we compare XGBoost against Random Forest, Logistic Regression, and Decision Tree. XGBoost achieves the most balanced performance (accuracy: 95.19%; weighted F1: 0.9519; 5-fold CV: 96.68% ± 0.21%). Feature importance analysis reveals ATM/kiosk infrastructure and breach pattern as the strongest predictors, translating into concrete SOC monitoring priorities. This framework supports UN/SDG 9 (Industry, Innovation and Infrastructure) and UN/SDG 16 (Peace, Justice and Strong Institutions) by strengthening the cyber resilience of financial institutions through open, replicable, data-driven methods. The open-data framework is replicable without commercial threat intelligence licenses. Full article

Planning collision-free paths for unmanned aerial vehicles in cluttered three-dimensional environments requires balancing path length, smoothness, and consistency across repeated queries. However, existing bidirectional RRT* planners generally do not exploit two sources of information generated during the search: the length and visibility of the gap between the two trees, and the local obstacle geometry revealed when an extension is blocked. This paper proposes SACE-Bi-RRT*, a bidirectional RRT* planner that feeds the connection state and the collision geometry back into the search. A dual-tree guided expansion strategy regulates the probability and the target of the guided extension by the incrementally maintained closest node pair and its line-of-sight visibility. A tangent-plane deflection strategy projects the blocked extension onto the tangent plane of the hit obstacle, which converts the collision into a deterministic detour. The step length follows the local clearance; scrambled Sobol sequences with an in-obstacle-triggered bridge test supply the exploratory samples, and the trees merge with the pair of minimum seam cost. In 100 independent runs in each of three simulated environments, SACE-Bi-RRT* shortens the final path by 12.1% to 31.3% relative to five baselines, whose average turning angle is 1.3 to 2.6 times its own. The coefficient of variation of its path length stays below 1.9%, against 3.8% to 12.1% for the baselines, and the converged planning time remains below 0.7 s. Full article

Balancing the vegetative and reproductive developmental cycles in a citrus orchard is essential to maintain sustainability. Plant growth regulators (PGRs) offer an effective tool for managing shoot growth rate and fruit production of citrus trees. By moderating shoot elongation and reducing canopy expansion, PGRs help minimise the frequency and intensity of pruning, substantially reducing labour costs and improving orchard management. Evidence from multi-year experiments showed PGR-treated citrus trees can maintain or increase yield efficiency, producing equal or greater fruit/canopy (m³) than untreated controls. Strategic application of PGRs can moderate alternate bearing by promoting more consistent and fruitful shoots, stabilising annual yields. Economic assessments showed significant reductions in labour costs, especially when trees treated with PGRs required less hand pruning. This review synthesises historic and contemporary research and the mechanisms by which PGRs exert their effects in citrus. It identifies knowledge gaps, such as the need for long-term studies, optimal timing for different cultivars, and integrated strategies suited to different environmental conditions. Plant growth regulators could be an effective tool for stable citrus production, offering the potential for more efficient tree canopy management when used responsibly in accordance with regulatory requirements and integrated with other orchard management practices. Full article

Class imbalance and class cardinality both affect multiclass classification, but their influence on probabilistic estimation has been less explored. This study examines these impacts using an e-commerce dataset. The study follows a four-stage methodology comprising classifier comparative evaluation, controlled class-cardinality analysis, validation using real categorical variables, and class-imbalance evaluation. Multiclass classification tasks are evaluated using Support Vector Machine, Gaussian Naive Bayes, Logistic Regression, Random Forest, and Decision Tree classifiers. Under five-fold cross-validation, performance is assessed using the macro-F1 score, log loss, and accuracy. Results show that macro-F1 score and accuracy decrease as class cardinality increases, causing greater classification difficulty. Tree-based models like Random Forest exhibit more balanced performance across classes. Gaussian Naive Bayes obtains the lowest log loss, indicating more accurate probability estimations. Class cardinality effects are isolated by varying the number of classes while keeping the features and classifier fixed. Increasing class cardinality reduced posterior confidence and increased entropy and log loss. Using real-time categorical variables, these trends are confirmed. Class imbalance primarily affects minority class performance, whereas class cardinality exerts a broader influence on probabilistic confidence and prediction uncertainty. The findings emphasize the necessity to consider class cardinality, class imbalance, and probabilistic metrics when evaluating multiclass classification models. Full article

Fast and accurate recognition of basic waveforms is important in embedded sensing, signal testing, and hardware measurement systems, especially under strict constraints on computation, memory, and power consumption. To address this problem, this paper proposes a lightweight waveform recognition method based on first-order and second-order differential features, together with decision tree and random forest classifiers. The proposed method transforms sampled waveforms into sign-based statistical features in the differential domain and performs classification through counting, comparison, and logical decision operations, thereby avoiding complex convolution, floating-point computation, and large-scale parameter storage. This paper first analyzes the separability of typical waveforms under differential statistics and studies the effect of noise on classification error. On this basis, a hierarchical recognition framework is constructed for five common waveform types, namely sine, square, triangle, rising sawtooth, and falling sawtooth. The models are trained on a PC platform and then implemented on an FPGA using Verilog. The experimental results show that the random forest achieves an accuracy of 99.7%, while the decision tree achieves 98.6%. On the xc7a35tfgg484-2 FPGA, both models consume zero DSP and zero BRAM resources. The random forest uses 1854 LUTs and 352 FFs, while the decision tree uses only 239 LUTs and 242 FFs. These results demonstrate that the proposed method achieves a favorable balance between recognition accuracy and hardware cost. The method is therefore well suited to real-time waveform recognition on resource-constrained FPGA platforms. Full article

Rapid surrogate prediction of ducted propeller performance is challenging when only a limited number of independent geometries are available and operating points belonging to the same geometry are strongly correlated. This study proposes a sensitivity-informed physics-regularized backpropagation neural network (SIPR-BP) for simultaneous prediction of the thrust coefficient K_T and the scaled torque coefficient 10K_Q. A CFD database comprising 20 Ka4-70-derived parameterized geometries, each evaluated at five advance ratios, provides 100 observations and 20 complete performance curves. The framework combines three main strategies. First, two-component multi-output partial least-squares (PLS) curve surrogates are reconstructed exclusively from the training geometries of each outer fold to generate leakage-controlled conditional Sobol gate priors. Second, the operating coordinate J is separated from geometric gating and represented by five ordered curve nodes, which guarantee non-increasing K_T and 10K_Q responses over the investigated interval. Third, training-only physics-consistency reliability weighting and a three-member ensemble improve robustness to locally irregular CFD responses and initialization variability. Under a ten-round geometry-grouped holdout protocol, SIPR-BP achieves a geometry-balanced MAPE of 2.65%, RMSE of 0.0112, MAE of 0.00911, and pooled R² of 0.951. When evaluated under the same outer partitions, a two-component PLS baseline yields a MAPE of 4.38%. Across the evaluated PLS, Extra Trees, GPR, and SVR baselines, SIPR-BP reduces geometry-balanced MAPE by approximately 39.6–79.2%. The results indicate that the proposed framework improves unseen-geometry prediction while preserving the prescribed response-curve structure. Full article

High-spatiotemporal-resolution evapotranspiration (ET) is critical for precision irrigation management and water resource regulation. Regarding the existing spatiotemporal fusion methods suffering from sparse high-resolution observations and coarse land surface temperature (LST), this study took winter wheat in Luancheng District, Hebei Province, as the research object, and proposed a remote sensing ET retrieval method based on the LST sharpening model. The Data Mining Sharpener (DMS) algorithm combined with Sentinel-2 multispectral data was used to downscale MODIS LST from 1000 m to 10 m, with auxiliary variables (DEM, albedo, NDVI, land cover) integrated into the Cubist regression tree to improve the physical rationality and spatial details of MODIS LST. The 10 m resolution ET was estimated from 10 m sharpened LST and Sentinel-2 multispectral data using the surface energy balance model, and the unmixing–weight ET image fusion model (UWET) was adopted to fuse the 10 m resolution ET with MODIS low-resolution ET to generate a daily 10 m ET dataset covering the entire winter wheat growing season. Validation with eddy covariance flux measurements showed that the correlation coefficient R = 0.921, RMSE = 0.779 mm/day during 2019–2020, and R = 0.900, RMSE = 0.831 mm/day during 2020–2021. The results demonstrate that auxiliary variables significantly enhance the spatial reality of LST, LST sharpening effectively improves the spatial heterogeneity of ET, and Sentinel-2 data compensates for the temporal deficiency of Landsat, thereby greatly promoting the accuracy of spatiotemporal fusion. This method can provide reliable high-spatiotemporal-resolution data support for refined farmland irrigation management and water resources regulation. Full article

Power transformers are among the most critical components of electric power transmission and distribution systems, and unexpected failures can lead to substantial economic losses and prolonged power outages. Dissolved Gas Analysis (DGA) is the most widely used diagnostic technique for transformer fault diagnosis and involves interpreting gases dissolved in insulating oil. However, conventional interpretation methods, such as the Rogers ratio, the Doernenburg ratio, the IEC 60599 ratio method, and the Duval Triangle, rely heavily on expert knowledge, may produce inconsistent diagnoses for the same oil sample, and may fail to provide a diagnosis in certain cases. In this study, 12 classification models were evaluated using the publicly available Power Transformers Fault Detection and Diagnosis (FDD) and Remaining Useful Life (RUL) dataset and a unified evaluation protocol. Model performance was assessed using Accuracy, Balanced Accuracy, and Macro-F1 score, while model interpretability was investigated through Shapley Additive Explanations (SHAP) analysis. The results showed that ensemble tree-based methods achieved the best overall performance. LightGBM and Random Forest both attained an Accuracy of 0.969 and a Macro-F1 score of 0.924, while LightGBM further achieved the highest Balanced Accuracy of 0.940. XGBoost exhibited the most stable performance under cross-validation. SHAP analysis revealed that engineered relative concentration features, particularly the CO/H₂ ratio and the combined gas ratio, were among the most influential features for fault classification. These findings demonstrate that, for datasets of this scale, ensemble tree-based models combined with well-designed features provide strong and interpretable performance for imbalanced DGA-based fault diagnosis, highlighting the effectiveness of feature-based ensemble learning for small- to medium-sized datasets. Full article

Accurate indoor localization is a fundamental enabling technology for modern smart environments and Location-Based Services (LBS). Among the various indoor positioning technologies, Bluetooth Low Energy (BLE) has emerged as a popular solution due to its low cost and low power consumption. However, BLE signals suffer from severe environmental noise, while continuously executing complex positioning models can quickly deplete the battery resources of mobile devices. To address both problems jointly, this paper proposes a robust and sustainable machine learning framework for indoor localization on mobile devices. The framework first applies a discrete-time Kalman Filter that suppresses noise induced by walls and moving human bodies, and then benchmarks 12 machine learning models (including a Neural Network baseline) on a real-world dataset of 15,000 samples from 10 smartphones under a $5\times 3$ repeated cross-validation (CV) protocol. To identify the best model for mobile deployment, we introduce the Green Efficiency Index (GEI), which balances positioning accuracy against software-estimated energy consumption in Joules. Results show that the evaluated Multi-Layer Perceptron (MLP) baseline struggles with the noisy BLE data, producing a Mean Absolute Error (MAE) of 1.81 m, whereas the evaluated tree-based models map indoor spatial patterns far more accurately. K-Nearest Neighbors (KNN) achieves the lowest MAE at 1.175 m but requires substantial memory, making it unsuitable for sustainable mobile deployment. Extra Trees therefore emerges as the optimal solution, achieving an MAE of 1.347 m with low energy consumption and a compact memory footprint. The framework also normalizes hardware differences across all 10 tested smartphones, providing an accurate, energy-efficient, and generalizable solution for indoor localization. Full article

Complex optimization tasks in data-driven prediction and engineering applications often involve nonlinear, multimodal, and ill-conditioned objective functions. This study proposes an Enhanced Moss Growth Optimization algorithm (EMGO), an improved variant of the baseline MGO framework, to enhance exploratory step-size control and local covariance exploitation. EMGO incorporates two key algorithmic augmentations: a budget-adaptive jump regulation mechanism that balances global dispersal and fine-grained refinement, and a shrinkage-regularized covariance-guided sampling operator with relative eigenvalue flooring to exploit correlation structures among elite individuals without rank deficiency. The proposed algorithm is evaluated on the CEC2017 benchmark suite across 50 and 100 dimensions with 29 test functions, 30 independent runs, and a budget of $3\times {10}^5$ function evaluations per run, compared against ten state-of-the-art optimizers including CMA-ES, L-SHADE, SBO, and baseline MGO. Nonparametric Friedman ranking, Holm-adjusted Wilcoxon signed-rank tests, and runtime-matched analyses demonstrate that EMGO achieves highly competitive performance across high-dimensional landscapes. Furthermore, EMGO is applied to tune support vector regression (SVR) hyperparameters for effluent suspended solid (SS) prediction using the UCI Water Treatment Plant dataset under an expanding-window rolling-origin cross-validation scheme. EMGO-SVR achieves superior predictive accuracy ($\mathrm{RMSE}=5.58\pm 0.64$, $\mathrm{MAE}=3.97\pm 0.46$, $R^2=0.889\pm 0.028$), outperforming standard SVR, tree-based ensembles, and Bayesian optimization baselines. SHAP-based feature importance analysis confirms the physical and process consistency of the model predictions. Full article

Bio-based phase change materials (PCMs) can increase transient heat storage in lightweight building envelopes, but their performance depends on the climate, transition properties, layer design, and assumptions used to translate thermal loads into carbon and cost indicators. Although PCM optimization, machine learning surrogates, and lifecycle assessment have each been studied extensively, comparatively few studies combine them while explicitly separating simulation-derived thermal outputs from scenario-dependent environmental and economic post-processing and benchmarking bio-based candidates against paraffin on a common wall area basis. This study develops a simulation-based screening framework for a south-facing office wall model using 18,000 EnergyPlus cases, climate-specific machine learning surrogates, TreeSHAP interpretation, NSGA-II optimization, and scenario-based lifecycle carbon and cost accounting. XGBoost achieved pooled held-out R² values of 0.974 for occupied discomfort degree-hours and 0.978 for total annual thermal demand. For Palermo, the directly re-simulated balanced configuration (T_m = 24.8 °C, L_h = 178 kJ/kg, 22 mm thickness, intermediate position) reduced occupant discomfort by 42.6% and the modeled single-zone total thermal demand by 6.0%. Under the central all-electric scenario (SCOP = SEER = 3.0, grid factor = 0.233 kg CO₂eq/kWh, 25 years), scenario-based net lifecycle carbon was −22.1 kg CO₂eq/m² for the analyzed south wall with an 8.0-year environmental payback, compared with −7.4 kg CO₂eq/m² and 19.2 years for RT28 paraffin. Energy savings did not recover the additional investment; the incremental lifecycle cost was +24.1 EUR/m². The theoretical contribution is a transparent, climate-dependent screening logic that couples surrogate interpretation with explicit evidence boundaries; the applied outcome is a palmitic–capric target-property region prioritized for laboratory validation rather than a deployment-ready product. Only directly re-simulated configurations are used for quantitative applied thermal claims; surrogate-only Pareto points are retained as exploratory screening candidates and are not interpreted as validated optima. The numerical results are specific to the modeled south-wall, single-zone boundary; whole-building and cross-regional application requires local recalibration and direct validation. By linking passive comfort, carbon accounting, material innovation, and responsible pre-experimental selection, the workflow is relevant to the decarbonization objectives represented by SDGs 7, 9, 11, 12, and 13. Full article

Pantograph arcing is both a vehicle current-collection problem and a railway-infrastructure condition-monitoring problem because repeated loss of electrical contact can accelerate wear of the overhead contact wire and pantograph strip, degrade traction power quality, and increase maintenance demand. This study develops a leakage-safe diagnostic framework for 3-kV DC railway operation using 13 independent high-frequency recordings from the public Trenitalia E464 pantograph-arcing dataset. Because the repository does not provide synchronized optical/contact-force ground truth, the machine-learning target is consistently treated as a physics-guided candidate interval rather than an independently verified arc label. Pantograph voltage, pantograph current, filter voltage, and braking-rheostat current were sampled at 50 kSa/s and transformed into 207 event-preserving analysis windows. A total of 849 candidate features were extracted across time, frequency, time-frequency, nonlinear, and physics-informed electrical domains. The strongest leave-one-recording-out configuration was Extra Trees with frequency-domain features, with mean event-level accuracy of 0.9936, balanced accuracy of 0.9952, Macro-F1 of 0.9932, MCC of 0.9874, ROC-AUC of 0.9994, and PR-AUC of 0.9989. Ten-repeat grouped five-fold validation, with complete recordings retained as groups, produced a mean Macro-F1 of 0.9910 (SD 0.0193) across 50 grouped test folds. Five hundred recording-grouped bootstrap resamples yielded a Macro-F1 mean of 0.9893 with a 95% confidence interval of 0.9694–1.0000. A dedicated guard audit found zero candidate-interval overlap in all 138 retained normal 100 ms feature windows. Sensitivity analysis showed that 100 ms spectral features were materially more stable than 20 ms features, while 25% and 50% candidate-overlap thresholds produced nearly identical performance. The dataset does not contain long-duration independently verified arc-free operation, chainage/GPS catenary position, or synchronized contact-force measurements; consequently, the results are interpreted as proof-of-concept electrical screening of candidate current-collection disturbances rather than fleet-wide ground-truth arc detection. Full article