Search Results (153)

This paper addresses the cold-start problem and rare event prediction challenges in Olympic medal forecasting by proposing a predictive framework that integrates multi-granularity transfer learning with extreme value theory. The framework comprises two main components, a Multi-Granularity Transfer Learning Core (MG-TLC) and a Rare Event Analysis Module (RE-AM), which address multi-level prediction for data-scarce countries and first medal prediction tasks. The MG-TLC incorporates two key components: Dynamic Feature Space Reconstruction (DFSR) and the Hierarchical Adaptive Transfer Strategy (HATS). The RE-AM combines a Bayesian hierarchical extreme value model (BHEV) with piecewise survival analysis (PSA). Experiments based on comprehensive, licensed Olympic data from 1896–2024, where the framework was trained on data up to 2016, validated on the 2020 Games, and tested by forecasting the 2024 Games, demonstrate that the proposed framework significantly outperforms existing methods, reducing MAE by 25.7% for data-scarce countries and achieving an AUC of 0.833 for first medal prediction, 14.3% higher than baseline methods. This research establishes a foundation for predicting the 2028 Los Angeles Olympics and provides new approaches for cold-start and rare event prediction, with potential applicability to similar challenges in other data-scarce domains such as economics or public health. From a symmetry viewpoint, our framework is designed to preserve task-relevant invariances—permutation invariance in set-based country aggregation and scale robustness to macro-covariate units—via distributional alignment between data-rich and data-scarce domains and Olympic-cycle indexing. We treat departures from these symmetries (e.g., host advantage or event-program changes) as structured asymmetries and capture them with a rare event module that combines extreme value and survival modeling. Full article

This paper proposes the lower-bounded Fréchet–log-logistic distribution (LFLD), a probability model designed for robust flood frequency analysis (FFA). The LFLD addresses key limitations of traditional distributions (e.g., generalized extreme value (GEV) and log-Pearson Type III (LP3)) by combining bounded support ($\alpha <x<\infty$) to reflect physical flood thresholds, flexible tail behavior via Fréchet–log-logistic fusion for extreme-value accuracy, and maximum entropy characterization, ensuring optimal parameter estimation. Thus, we obtain the LFLD’s main statistical properties (PDF, CDF, and hazard rate), prove its asymptotic convergence to Fréchet distributions, and validate its superiority through simulation studies showing MLE consistency (bias < 0.02 and mean squared error < 0.0004 for $\alpha$) and empirical flood data tests (52- and 98-year AMS series), where the LFLD outperforms 10 competitors (AIC reductions of 15–40%; Vuong test p < 0.01). The LFLD’s closed-form quantile function enables efficient return period estimation, critical for infrastructure planning. Results demonstrate its applicability to heavy-tailed, bounded hydrological data, offering a 20–30% improvement in flood magnitude prediction over LP3/GEV models. Full article

We analyze extreme gold price movements between 1975 and 2025 using Extreme Value Theory (EVT). Using both the Block-Maxima and Peaks-over-Threshold approaches on a daily return basis, we estimate Value-at-Risk (VaR) and Expected Shortfall (ES) for the entire distribution focusing on a long-term view. Our results demonstrate that models based on the standard normal distribution systematically underestimate extreme risks, whereas EVT provides more reliable measures. In particular, EVT captures not only rare losses, but also sudden positive rallies, highlighting gold’s dual function as a risk and opportunity asset. Asymmetries emerge in the analysis: at the 0.99 quantile, losses appear larger in absolute value than gains. At the 0.995 quantile, in some episodes, upside extremes dominate. Furthermore, we find that geopolitical and economic shocks, including the oil crises, the 2008 financial crisis, and the COVD-19 pandemic, leave distinct signatures in the extremes. By covering five decades, our study provides the most extensive EVT-based assessment of gold risks to date. Our findings contribute to debates on financial stability and provide practical guidance for investors seeking to manage tail risks while recognizing gold’s potential as both a safe haven and a speculative asset. Full article

Thrust vectoring technology significantly improves the manoeuvrability and environmental adaptability of unmanned aerial vehicles by dynamically regulating the direction and magnitude of thrust. In this paper, the principles and applications of mechanical thrust vectoring technology, fluidic thrust vectoring technology and the distributed electric propulsion system are systematically reviewed. It is shown that the mechanical vector nozzle can achieve high-precision control but has structural burdens, the fluidic thrust vectoring technology improves the response speed through the design of no moving parts but is accompanied by the loss of thrust, and the distributed electric propulsion system improves the hovering efficiency compared with the traditional helicopter. Addressing multi-physics coupling and non-linear control challenges in unmanned aerial vehicles, this paper elucidates the disturbance compensation advantages of self-disturbance rejection control technology and the optimal path generation capabilities of an enhanced path planning algorithm. These two approaches offer complementary technical benefits: the former ensures stable flight attitude, while the latter optimises flight trajectory efficiency. Through case studies such as the Skate demonstrator, the practical value of these technologies in enhancing UAV manoeuvrability and adaptability is further demonstrated. However, thermal management in extreme environments, energy efficiency and lack of standards are still bottlenecks in engineering. In the future, breakthroughs in high-temperature-resistant materials and intelligent control architectures are needed to promote the development of UAVs towards ultra-autonomous operation. This paper provides a systematic reference for the theory and application of thrust vectoring technology. Full article

The growing complexity of distribution-level virtual power plants (VPPs) demands a rethinking of how flexible demand is modeled, aggregated, and dispatched under uncertainty. Traditional optimization frameworks often rely on deterministic or homogeneous assumptions about end-user behavior, thereby overestimating controllability and underestimating risk. In this paper, we propose a behavior-aware, two-stage stochastic dispatch framework for VPPs that explicitly models heterogeneous user participation via integrated behavioral economics and social interaction structures. At the behavioral layer, user responses to demand response (DR) incentives are captured using a Prospect Theory-based utility function, parameterized by loss aversion, nonlinear gain perception, and subjective probability weighting. In parallel, social influence dynamics are modeled using a peer interaction network that modulates individual participation probabilities through local contagion effects. These two mechanisms are combined to produce a high-dimensional, time-varying participation map across user classes, including residential, commercial, and industrial actors. This probabilistic behavioral landscape is embedded within a scenario-based two-stage stochastic optimization model. The first stage determines pre-committed dispatch quantities across flexible loads, electric vehicles, and distributed storage systems, while the second stage executes real-time recourse based on realized participation trajectories. The dispatch model includes physical constraints (e.g., energy balance, network limits), behavioral fatigue, and the intertemporal coupling of flexible resources. A scenario reduction technique and the Conditional Value-at-Risk (CVaR) metric are used to ensure computational tractability and robustness against extreme behavior deviations. Full article

The generalized extreme value (GEV) distribution has been extensively applied in predicting extreme events across diverse fields, enabling accurate estimation of extreme quantiles of maxima. Although the mean and variance of the GEV can be expressed as functions of its parameters, a reparameterization that directly uses the mean and standard deviation as parameters provides interpretative advantages. This is particularly useful in regression-based models, as it allows a more straightforward interpretation of how covariates influence the mean and the standard deviation of the data. The proposed models are estimated within the Bayesian framework, assuming normal prior distributions for the regression coefficients. In this work, we introduce a reparameterization of the GEV distribution in terms of the mean and standard deviation, and apply it to minimum humidity data from the northeast region of Brazil. The results highlight the benefits of the proposed methodology, demonstrating clearer interpretability and practical relevance for extreme value modeling, where the influence of seasonal and locality variables on the mean and variance of minimum humidity can be accurately assessed. Full article

In many real-life processes, data with high positive skewness are very common. Moreover, these data tend to exhibit heterogeneous characteristics in such a manner that using one parametric univariate probability distribution becomes inadequate to model such data. When the heterogeneity of such data can be appropriately separated into two components—the main innovation component, where the bulk of data is centered, and the tail component which contains some few extreme observations—in such a way, and without a loss in generality, that the data possesses high skewness to the right, the use of hybrid models to model the data becomes very viable. In this paper, a new two-component hybrid model which combines the half-normal distribution for the main innovation of a positive and highly right-skewed data with the generalized Pareto distribution (GPD) for the observations in the data above a certain threshold is proposed. To enhance efficiency in the estimation of the parameters of the hybrid model, an unsupervised iterative algorithm (UIA) is adopted. The hybrid model is applied to model the intensity of rainfall which triggered some debris flow events in the South Tyrol region of Italy. Results from Monte Carlo simulations, as well as from the model’s application to the real data, clearly show how the UIA enhances the estimation of the free parameters of the hybrid model to offer good fits to positive and highly right-skewed data. Application results of the hybrid model are also compared with the results of other two-component hybrid models and graphical threshold selection methodologies in extreme value theory. Full article

To address stability and safety issues in hydraulic support design under inclined–declined and large-dip-angle working conditions, this paper proposes a design-driven dynamic pose–load co-evolution solution method based on the physical entity of the ZFY12000/21/36D hydraulic support. The feasibility of the proposed method is demonstrated through theoretical analysis, spatial modeling, and experimental verification. First, a spatial coordinate system describing hydraulic support pose is established based on Denavit–Hartenberg (DH) theory, constructing a “physical space-geometric coordinate system-DH parameter space” pose mapping model via DH principles, matrix iteration, and kinematic simulation. Second, a load-bearing characteristic analytical method is developed through systematic coupling analysis of dip angle, pose, and load distribution. Finally, coal mine field data collection and hydraulic support test platform experiments analyze load-bearing characteristics under varying poses and loads. Results show Root Mean Square Error (RMSE) values of 0.836° for the front link inclination, 0.756° for the rear link, 0.114° for the balance ram, and 0.372° for the column; load-bearing state evolution under pose–load synergy aligns with theoretical models, confirming method feasibility. This approach fills a domain gap in hydraulic support dip–pose–load co-solving and provides critical references for designing hydraulic support products under extreme dip-angle operations. Full article

Radio frequency (RF) fingerprinting, as an emerging physical layer security technology, demonstrates significant potential in the field of Internet of Things (IoT) security. However, most existing methods operate under a ‘closed-set’ assumption, failing to effectively address the continuous emergence of unknown devices in real-world scenarios. To tackle this challenge, this paper proposes an open-set radio frequency fingerprint identification (RFFI) method based on Multi-Task Prototype Learning (MTPL). The core of this method is a multi-task learning framework that simultaneously performs discriminative classification, generative reconstruction, and prototype clustering tasks through a deep network that integrates an encoder, a decoder, and a classifier. Specifically, the classification task aims to learn discriminative features with class separability, the generative reconstruction task aims to preserve intrinsic signal characteristics and enhance detection capability for out-of-distribution samples, and the prototype clustering task aims to promote compact intra-class distributions for known classes by minimizing the distance between samples and their class prototypes. This synergistic multi-task optimization mechanism effectively shapes a feature space highly conducive to open-set recognition. After training, instead of relying on direct classifier outputs, we propose to adopt extreme value theory (EVT) to statistically model the tail distribution of the minimum distances between known class samples and their prototypes, thereby adaptively determining a robust open-set discrimination threshold. Comprehensive experiments on a real-world dataset with 16 Wi-Fi devices show that the proposed method outperforms five mainstream open-set recognition methods, including SoftMax thresholding, OpenMax, and MLOSR, achieving a mean AUROC of 0.9918. This result is approximately 1.7 percentage points higher than the second-best method, demonstrating the effectiveness and superiority of the proposed approach for building secure and robust wireless authentication systems. This validates the effectiveness and superiority of our approach in building secure and robust wireless authentication systems. Full article

This paper develops a novel entropy-based framework to quantify tail risk and detect speculative bubbles in financial markets. By integrating extreme value theory with information theory, I introduce the Tail-Weighted Entropy (TWE) measure, which captures how information scales with extremeness in asset price distributions. I derive explicit bounds for TWE under heavy-tailed models and establish its connection to tail index parameters, revealing a phase transition in entropy decay rates during bubble formation. Empirically, I demonstrate that TWE-based signals detect crises in equities, commodities, and cryptocurrencies days earlier than traditional variance-ratio tests, with Bitcoin’s 2021 collapse identified weeks prior to the peak. The results show that entropy decay—not volatility explosions—serves as the primary precursor to systemic risk, offering policymakers a robust tool for preemptive crisis management. Full article

Extreme value theory comprises a set of techniques for inference at the tail of distributions, where data are scarce or non-existent. The tail index is the main parameter, with risk measures such as value at risk or expected shortfall depending on it. In this study, we will analyze a method for estimating the tail index through a simulation study. This will allow for an application using real data including the estimation of the mentioned risk measures. Full article

As investment portfolios become increasingly diversified and financial asset risks grow more complex, accurately forecasting the risk of multiple asset classes through mathematical modeling and identifying their heterogeneity has emerged as a critical topic in financial research. This study examines the volatility and tail risk of gold, crude oil, Bitcoin, and selected stock markets. Methodologically, we propose two improved Value at Risk (VaR) forecasting models that combine the autoregressive (AR) model, Exponential Generalized Autoregressive Conditional Heteroskedasticity (EGARCH) model, Extreme Value Theory (EVT), skewed heavy-tailed distributions, and a rolling window estimation approach. The model’s performance is evaluated using the Kupiec test and the Christoffersen test, both of which indicate that traditional VaR models have become inadequate under current complex risk conditions. The proposed models demonstrate superior accuracy in predicting VaR and are applicable to a wide range of financial assets. Empirical results reveal that Bitcoin and the Chinese stock market exhibit no leverage effect, indicating distinct risk profiles. Among the assets analyzed, Bitcoin and crude oil are associated with the highest levels of risk, gold with the lowest, and stock markets occupy an intermediate position. The findings offer practical implications for asset allocation and policy design. Full article

The bimodal generalized extreme value (BGEV) distribution was first introduced in 2023. This distribution offers greater flexibility than the generalized extreme value (GEV) distribution for modeling extreme and heterogeneous (bimodal) events. However, applying this model requires a data-centering technique, as it lacks a location parameter. In this work, we investigate the properties of the BGEV distribution as redefined in 2024, which incorporates a location parameter, thereby enhancing its flexibility in practical applications. We derive explicit expressions for the probability density, the hazard rate, and the quantile function. Furthermore, we establish the identifiability property of this new class of BGEV distributions and compute expressions for the moments, the moment-generating function, and entropy. The applicability of the new model is illustrated using climate data. Full article

This study presents an innovative data-driven approach to optimally design water distribution networks (WDNs). The methodology comprises five key stages: Generation of 600 synthetic WDNs with diverse properties, optimized to determine optimal component diameters; Extraction of 80 topological and hydraulic features from the optimized WDNs using graph theory; preprocessing and preparing the extracted features using established data science methods; Application of six feature selection methods (Variance Threshold, k-best, chi-squared, Light Gradient-Boosting Machine, Permutation, and Extreme Gradient Boosting) to identify the most relevant features for describing optimal diameters; and Integration of the selected features with four machine learning models (Random Forest, Support Vector Machine, Bootstrap Aggregating, and Light Gradient-Boosting Machine), resulting in 24 ensemble models. The Extreme Gradient Boosting-Light Gradient-Boosting Machine (Xg-LGB) model emerged as the optimal choice, achieving R², MAE, and RMSE values of 0.98, 0.017, and 0.02, respectively. When applied to a benchmark WDN, this model accurately predicted optimal diameters, with R², MAE, and RMSE values of 0.94, 0.054, and 0.06, respectively. These results highlight the developed model’s potential for the accurate and efficient optimal design of WDNs. Full article

Group anomaly detection is a subfield of pattern recognition that aims at detecting anomalous groups rather than individual anomalous points. However, existing approaches mainly target the unusual aggregate of points in high-density regions. In this way, unusual group behavior with a number of points located in low-density regions is not fully detected. In this paper, we propose a systematic approach based on extreme value theory (EVT), a field of statistics adept at modeling the tails of a distribution where data are sparse, and one-class support measure machines (OCSMMs) to quantify anomalous group behavior comprehensively. First, by applying EVT to a point process model, we construct an analytical model describing the likelihood of an aggregate within a group with respect to low-density regions, aimed at capturing anomalous group behavior in such regions. This model is then combined with a calibrated OCSMM, which provides probabilistic outputs to characterize anomalous group behavior in high-density regions, enabling improved assessment of overall anomalous group behavior. Extensive experiments on simulated and real-world data demonstrate that our method outperforms existing group anomaly detectors across diverse scenarios, showing its effectiveness in quantifying and interpreting various types of anomalous group behavior. Full article