Search Results (897)

The end-to-end efficiency of radio-frequency (RF)-powered wireless communication networks (WPCNs) in post-disaster underground mine environments can be enhanced through adaptive beamforming. The primary challenges in such scenarios include (i) identifying the most energy-constrained nodes, i.e., nodes with the lowest residual energy to prevent the loss of tracking and localization functionality; (ii) avoiding reliance on the computationally intensive channel state information (CSI) acquisition process; and (iii) ensuring long-range RF wireless power transfer (LoRa-RFWPT). To address these issues, this paper introduces an adaptive and safety-aware deep reinforcement learning (DRL) framework for energy beamforming in LoRa-enabled underground disaster networks. Specifically, we develop a Safe Adaptive Deep Q-Network (SADQN) that incorporates residual energy awareness to enhance energy harvesting under mobility, while also formulating a SADQN approach with dual-variable updates to mitigate constraint violations associated with fairness, minimum energy thresholds, duty cycle, and uplink utilization. A mathematical model is proposed to capture the dynamics of post-disaster underground mine environments, and the problem is formulated as a constrained Markov decision process (CMDP). To address the inherent NP hardness of this constrained reinforcement learning (CRL) formulation, we employ a Lagrangian relaxation technique to reduce complexity and derive near-optimal solutions. Comprehensive simulation results demonstrate that SADQN significantly outperforms all baseline algorithms: increasing cumulative harvested energy by approximately 11% versus DQN, 15% versus Safe-DQN, and 40% versus PSO, and achieving substantial gains over random beamforming and non-beamforming approaches. The proposed SADQN framework maintains fairness indices above 0.90, converges 27% faster than Safe-DQN and 43% faster than standard DQN in terms of episodes, and demonstrates superior stability, with 33% lower performance variance than Safe-DQN and 66% lower than DQN after convergence, making it particularly suitable for safety-critical underground mining disaster scenarios where reliable energy delivery and operational stability are paramount. Full article

Flash flood events are some of the most life-threatening natural disasters, so it is important to predict extreme rainfall events effectively. This study introduces an LSTM model that utilizes a customized loss function to effectively predict extreme rainfall events. The proposed model incorporates dynamic environmental variables, such as rainfall, LST, and NDVI, and incorporates additional static variables such as soil type and proximity to infrastructure. Wavelet transformation decomposes the time series into low- and high-frequency components to isolate long-term trends and short-term events. Model performance was compared against Random Forest (RF), Support Vector Machines (SVMs), Artificial Neural Networks (ANNs), and an LSTM-RF ensemble. The custom loss LSTM achieved the best performance (MAE = 0.022 mm/day, RMSE = 0.110 mm/day, R² = 0.807, SMAPE = 7.62%), with statistical validation via a Kruskal–Wallis ANOVA, confirming that the improvement is significant. Model uncertainty is quantified using a Bayesian MCMC framework, yielding posterior estimates and credible intervals that explicitly characterize predictive uncertainty under extreme rainfall conditions. The sensitivity analysis highlights rainfall and LST as the most influential predictors, while wavelet decomposition provides multi-scale insights into environmental dynamics. The study concludes that customized loss functions can be highly effective in extreme rainfall event prediction and thus useful in managing flash flood events. Full article

Magnetic core loss is an important indicator for describing the performance of magnetic elements. The traditional physical model has an insufficient performance for predicting the magnetic core loss of magnetic elements under complex conditions such as high temperature, non-sinusoidal waveform, and high frequency. To address this issue, this study proposes a physics-informed neural network (PINN)-based model for magnetic core loss prediction. In particular, this PINN-based model is constructed with a hybrid network architecture as a baseline algorithm, which combines a convolutional long short-term memory network (Conv-LSTM), power spectral density (PSD), and an ensemble learning method (including extreme gradient boosting (XGB), gradient boosting regression (GBR), and random forest (RF)). This design aims to address the complexity of magnetic core loss prediction. Moreover, the Steinmetz equation (SE) is improved to enhance the adaptability under complex conditions, and this improved Steinmetz equation (ISE) is integrated as physical constraints embedded in the neural network for magnetic core loss prediction. Based on the traditional data-driven loss term, the physical residual term is introduced as a regularization constraint to enable the prediction to satisfy both the observed data distribution and physical law. The experimental results show that the PINN-based model has a good prediction performance of magnetic core loss under complex conditions. Full article

Peri-urban areas in Eastern Europe are undergoing rapid land transformation driven by suburban housing expansion and infrastructure development, yet the processes through which vegetation is progressively degraded and built-up areas intensify remain insufficiently documented. This study analyses vegetation loss and urban expansion in the peri-urban belt of Timișoara, Western Romania, between 2020 and 2025 using Sentinel-2 multispectral imagery, two key spectral indices (NDVI and NDBI), and a Random Forest (RF) classifier. The results reveal a gradual, multi-stage transformation trajectory, where dense vegetation transitions first into sparse vegetation and bare soil before consolidating into built-up surfaces, rather than being replaced abruptly. Substantial vegetation decline is accompanied by notable increases in built-up land, with strong spatial differences between communes depending on development pressure. The integration of RF classification with spectral index analysis allows these transitions to be validated and interpreted more reliably, helping distinguish structural suburbanisation from short-term spectral variability. Overall, the study demonstrates the value of combining NDVI, NDBI and AI-supported land-cover classification to capture nuanced peri-urban transformation dynamics and provides actionable insights for spatial planning and sustainable land management in rapidly growing metropolitan regions. Full article

Grain aging during storage leads to quality deterioration and significant economic losses. Traditional analytical approaches are often labor-intensive, slow, and inadequate for modern intelligent grain storage management. This review summarizes recent advances in the intelligent discrimination of grain aging using volatile organic compound (VOC) fingerprints combined with machine learning (ML) techniques. It first outlines the biochemical mechanisms underlying grain aging and identifies VOCs as early and sensitive biomarkers for timely determination. The review then examines VOC determination methodologies, with a focus on headspace solid-phase microextraction coupled with gas chromatography-mass spectrometry (HS-SPME-GC-MS), for constructing volatile fingerprinting profiles, and discusses related method standardization. A central theme is the application of ML algorithms, including Partial Least Squares Discriminant Analysis (PLS-DA), Support Vector Machines (SVM), Random Forest (RF), and Convolutional Neural Networks (CNN)) for feature extraction and pattern recognition in high-dimensional datasets, enabling effective discrimination of aging stages, spoilage types, and grain varieties. Despite these advances, key challenges remain, such as limited model generalizability, the lack of large-scale multi-source databases, and insufficient validation under real storage conditions. Finally, future directions are proposed that emphasize methodological standardization, algorithmic innovation, and system-level integration to support intelligent, non-destructive, real-time grain quality monitoring. This emerging framework provides a promising powerful pathway for enhancing global food security. Full article

To address the pressing need for compact and highly reliable perception systems in autonomous mobile robots, a compact bandpass filter (BPF) integrating slot-line resonator with substrate-integrated waveguide (SIW) technology for robotic millimeter-wave radar front ends was proposed. By integrating slot-line resonators between adjacent SIW cavities, the proposed design effectively increases the filtering order without increasing the layout area. This approach not only generates extra transmission poles but also creates a sharp transmission zero at the upper stopband, thereby significantly enhancing out-of-band rejection. This characteristic is crucial for robotic radar operating in complex and dynamic environments, as it effectively suppresses out-of-band interference and improves the system signal-to-noise ratio and detection reliability. To validate the performance, a prototype filter operating in the 24.25–27.5 GHz passband was fabricated. The measured results show good agreement with simulations, demonstrating low insertion loss, compact size, and wide stopband. Finally, to validate its compatibility with robotic radar modules, the chip was assembled onto a PCB using surface-mount technology. The responses of the bare die and the packaged module were then compared to evaluate the impact of integration on the overall RF performance. The proposed design offers a key filtering solution for next-generation high-performance, miniaturized robotic perception platforms. Full article

To address the prevalent noise issue in images generated by HumanNeRF, this paper proposes an image denoising method that combines self-supervised contrastive learning and Generative Adversarial Networks (GANs). While HumanNeRF excels in realistic 3D human reconstruction tasks, its generated images often suffer from noise and detail loss due to incomplete training data and sampling noise during the rendering process. To solve this problem, our method first utilizes a self-supervised contrastive learning strategy to construct positive and negative sample pairs, enabling the network to effectively distinguish between noise and human detail features without external labels. Secondly, it introduces a Generative Adversarial Network, where the adversarial training between the generator and discriminator further enhances the detail representation and overall realism of the images. Experimental results demonstrate that the proposed method can effectively remove noise from HumanNeRF images while significantly improving detail fidelity, ultimately yielding higher-quality human images and providing crucial support for subsequent 3D human reconstruction and realistic rendering. Full article

Cancer cachexia (CC) is a multifactorial, multi-organ syndrome characterized by systemic inflammation, metabolic dysregulation, anorexia, and progressive depletion of skeletal muscle and adipose tissue. Despite its high prevalence among patients with advanced malignancies, effective therapeutic options remain limited. Recent studies have elucidated the molecular underpinnings of CC and the therapeutic potential of natural herbs, highlighting the involvement of central nervous system regulation, adipose tissue, immune responses, gut microbiota, skeletal muscle, and disruptions in anabolic–catabolic signaling pathways such as mTOR, UPS, NF-κB, and STAT3. Persistent inflammation induces E3 ubiquitin ligases (Atrogin-1/MuRF-1) through cytokines including IL-6 and TNF-α, thereby impairing muscle homeostasis, while suppression of anabolic cascades such as IGF-1/mTOR further aggravates muscle atrophy. The limited efficacy and adverse effects of synthetic agents like megestrol acetate underscore the value of herbal therapies as safer adjunctive strategies. Botanicals such as Coicis Semen, Scutellaria baicalensis, and Astragalus demonstrate anti-inflammatory and muscle-preserving activities by modulating NF-κB, IL-6, and oxidative stress signaling. Numerous investigations indicate that these herbs downregulate MuRF-1 and Atrogin-1 expression, enhance appetite, and attenuate muscle loss, though they exhibit minimal influence on tumor suppression. While promising, current evidence remains largely preclinical and mechanistic validation is incomplete. This review consolidates contemporary insights into CC pathogenesis and the bioactivity of herbal interventions, highlighting the need for translational research to bridge preclinical findings with clinical applicability. Full article

High-performance dielectric materials that can be processed at ultra-low temperatures are essential for next-generation LTCC technologies and compact RF–microwave components. In this work, a multicomponent Bi–Fe–Nb oxide system was synthesized using a modified citrate sol–gel method and thermally treated at only 400 °C to investigate its structural evolution and dielectric behavior. XRD and Raman analysis revealed the coexistence of a well-crystallized BiOCl phase embedded within a partially amorphous Bi–Fe–Nb–O matrix. SEM and EDS mapping confirmed the presence of two distinct microstructural regions, reflecting differences in local composition and crystallization kinetics. Microwave measurements at 2.7 and 5.0 GHz showed low dielectric losses and a stable dielectric response. Impedance spectroscopy in the RF range revealed strong Maxwell–Wagner polarization at low frequencies and thermally activated relaxation evidenced by the temperature shift in the modulus and impedance peaks. Arrhenius analysis of the relaxation frequencies yielded similar activation energies from both modulus and impedance formalisms, indicating a single underlying relaxation mechanism. Equivalent-circuit fitting confirmed non-Debye behavior, with nearly temperature-independent capacitance and decreasing resistance consistent with thermally activated conduction. These results demonstrate that the Bi–Fe–Nb system exhibits promising dielectric stability and functional behavior even when processed at exceptionally low temperatures. Full article

Against the accelerating backdrop of global warming, drought-induced crop yield loss not only causes direct economic losses but may also disrupt the dynamic balance of food production and consumption, ultimately threatening global food security. In order to quantify drought-induced crop yield loss for safeguarding national food security, this study developed a model for evaluating drought-induced yield reduction in winter wheat by integrating solar-induced chlorophyll fluorescence (SIF), vegetation indices (VIs), and meteorological data. The results demonstrated that the following: (1) SIF could effectively capture interannual fluctuations in winter wheat yield and serve as a reliable quantitative indicator of yield variation. (2) Utilizing vegetation data such as SIF and the near-infrared reflectance of vegetation (NIRv), the developed models could directly quantify drought-induced yield losses in winter wheat based on normalized anomalies of vegetation and meteorological variables, without the need for additional auxiliary data or complex computations. Among all variable combinations tested, SIF demonstrated superior performance, yielding the most accurate predictions. (3) Both random forest (RF) and extreme gradient boosting (XGBoost) algorithms had similar performance in evaluating drought-induced yield loss. The results highlighted the advantages of combining the normalized anomaly of multiple sources of data as inputs in stress-induced crop yield loss evaluation, which was helpful for quick monitoring and early warning of the crop yield loss in the major grain production region. Full article

Landslides rank among the most frequent and devastating natural hazards globally, causing significant loss of life and property. As a result, landslide susceptibility assessment has become a central focus in geohazard research, which is devoted to preventing and alleviating the frequent occurrence of landslides. Numerous analytical models have been applied to evaluate landslide susceptibility, including Frequency Ratio (FR), Logistic Regression (LR), Support Vector Machine (SVM), Random Forest (RF), and various hybrid and neural network-based approaches. This review synthesizes current progress in integrating Nature-based Solutions (NBS) with modeling and policy frameworks, highlighting their potential to provide cost-effective, sustainable, and adaptive alternatives to conventional landslide mitigation strategies. Based on a systematic review of 127 peer-reviewed publications published between 2023 and 2025, selected from Web of Science, ScienceDirect, MDPI, Springer, and Google Scholar using predefined keywords and screening criteria, this study reveals that the most frequently used conditioning factors in landslide susceptibility modeling are slope (96 times), aspect (77 times), elevation (77 times), and lithology (77 times). Among modeling approaches, Random Forest (RF), Support Vector Machine (SVM), hybrid models, and neural network models consistently demonstrate high predictive performance. Despite the expanding body of literature on NBS, only 2.3% of all NBS-related studies specifically address landslide mitigation. The existing literature primarily concentrates on assessing the biophysical effectiveness of interventions such as vegetation cover, root reinforcement, and forest-based stabilization using a range of predictive modeling techniques. However, significant gaps remain in the integration of economic valuation frameworks, particularly cost–benefit analysis (CBA), to quantify the monetary value of NBS interventions in landslide risk reduction. This highlights a critical area for future research to support evidence-based decision-making and sustainable risk governance. Full article

In this study, a new semi-analytical model was developed that can calculate the output voltage of low-power microwave rectifiers as a function of frequency and input power. The model integrates diode rectification characteristics and frequency-dependent impedance mismatches within the same mathematical structure. Defined by second-order polynomial expressions for input power and frequency, the model directly incorporates reflection coefficient (S₁₁) data into the equations to account for frequency-dependent power losses caused by impedance mismatch, thereby improving calculation accuracy under wide-band conditions. To validate the model, a wide-band rectifier prototype with an FR4-based T-type matching network and a voltage doubler structure was designed and manufactured. Model calculations showed over 95% agreement with simulation results and closely followed the measured output voltage trends over the 0.5–3 GHz frequency range and input power levels from −12 dBm to 0 dBm. The proposed model provides a design-oriented and computationally efficient tool for wide-band, low-power RF energy harvesting and wireless power transfer applications, enabling rapid evaluation of impedance matching strategies with reduced reliance on electromagnetic simulations. Full article

Accurate user positioning in 6G networks is essential for next-generation mobile services. However, classical approaches such as time-difference-of-arrival (TDoA) remain vulnerable to dense multipath and NLoS conditions commonly found in indoor and industrial environments. This paper proposes an AI-driven RF fingerprinting framework that leverages uplink channel state information (CSI) to achieve robust and privacy-preserving 2D localization. A lightweight convolutional neural network (CNN) extracts location-specific spectral–spatial fingerprints from CSI tensors, while a federated learning (FL) scheme enables distributed training across multiple gNBs without sharing raw channel data. The proposed integration of CSI tensor processing with FL and structured pruning is introduced as a novel solution for practical 6G edge positioning. To further reduce latency and communication costs, a structured pruning mechanism compresses the model by 40–60%, lowering the memory footprint with negligible accuracy loss. A performance evaluation in 3GPP-compliant indoor factory scenarios indicates a median positioning error below 1 m for over 90% of cases, significantly outperforming TDoA. Moreover, the compressed FL model reduces the FL communication load by ~38% and accelerates local training, establishing an efficient, secure, and deployment-ready positioning solution for 6G networks. Full article

Climate-induced flooding is a major issue throughout the globe, resulting in damage to infrastructure, loss of life, and the economy. Therefore, there is an urgent need for sustainable flood risk management. This paper assesses the effectiveness of the hybrid defense system using advanced artificial intelligence (AI) techniques. A data series of energy dissipation (ΔE), flow conditions, roughness, and vegetation density was collected from literature and laboratory experiments. Out of the selected 136 data points, 80 points were collected from literature and 56 from a laboratory experiment. Advanced AI models like Random Forest (RF), Extreme Boosting Gradient (XGBoost) with Particle Swarm Optimization (PSO), Support Vector Regression (SVR) with PSO, and artificial neural network (ANN) with PSO were trained on the collected data series for predicting floodwater energy dissipation. The predictive capability of each model was evaluated through performance indicators, including the coefficient of determination (R²) and root mean square error (RMSE). Further, the relationship between input and output parameters was evaluated using a correlation heatmap, scatter pair plot, and HEC-contour maps. The results demonstrated the superior performance of the Random Forest (RF) model, with a high coefficient of determination (R² = 0.96) and a low RMSE of 3.03 during training. This superiority was further supported by statistical analyses, where ANOVA and t-tests confirmed the significant performance differences among the models, and Taylor’s diagram showed closer agreement between RF predictions and observed energy dissipation. Further, scatter pair plot and HEC-contour maps also supported the result of SHAP analysis, demonstrating greater impact of the roughness condition followed by vegetation density in reducing floodwater energy dissipation under diverse flow conditions. The findings of this study concluded that RF has the capability of modeling flood risk management, indicating the role of AI models in combination with a hybrid defense system for enhanced flood risk management. Full article

Spatially quantifying the soil carbon sequestration potential (SCSP) is crucial for targeting climate change mitigation strategies like carbon farming. However, static mapping approaches often fail by assuming that the drivers of soil organic carbon (SOC) are stationary. We hypothesized that the hierarchy of SOC controllers is fundamentally non-stationary, shifting from intrinsic stabilization capacity (pedology) in stable ecosystems to extrinsic flux kinetics (climate) in dynamic systems. We tested this by developing a land-use-specific (LULC; Cropland, Forest land, Grassland) ensemble machine learning (ML) framework to quantify the soil carbon saturation deficit (SCSD) across Croatia’s pedologically diverse landscape on 622 soil samples. The LULC-stratified ensemble models (SVM, RF, CUB) achieved moderate to good predictive accuracy under cross-validation (R² = 0.41–0.60). Crucially, the feature importance analysis (permutation MSE loss) proved our hypothesis: in Forest land, SOC was superiorly controlled by intrinsic capacity (Soil CEC, Soil pH), defining the mineralogical C-saturation “ceiling”; in Grasslands, control shifted to extrinsic C-input kinetics (Precipitation: Bio19, Bio12), which “fuel” the microbial carbon pump (MCP) via root exudation; and in Croplands, the model revealed a hybrid control, limited by remaining intrinsic capacity (CEC, Clay) but strongly influenced by C-loss kinetics (Temperature: Bio08), which regulates microbial carbon use efficiency (CUE). This study demonstrates that LULC-specific dynamic modeling is a prerequisite for accurately mapping SCSP. By identifying soils with both high intrinsic capacity (high CEC/Clay) and high degradation (high SCSD), our data-driven assessment provides a critical tool for spatially targeting carbon farming interventions for maximum climate mitigation return on investment (ROI). Full article