Search Results (389)

Industrial-Internet security faces a core challenge: improving detection accuracy for critical minority-class network attacks. The existing intrusion detection methods based on Conditional Generative Adversarial Nets (CGANs) aim to achieve data balance by reconstructing minority-class attack samples. However, they encounter problems such as generating deceptive samples, poor sample quality, vanishing gradients and difficulties in training. This paper proposes an intrusion detection method based on the Multi-Discriminator Conditional Classification Generative Adversarial Network (MDCCGAN), an improved variant of CGAN, which integrates multiple discriminators and an independent classifier into the traditional CGAN framework. The multiple discriminators reduce the probability of generating deceptive samples, the independent classifier decouples the classification loss to clarify the direction of gradient updates, and the introduction of the Wasserstein distance fundamentally addresses the gradient-vanishing problem. Experiments conducted on the NSL-KDD and UNSW-NB15 datasets demonstrate that the proposed method significantly improves the recall, F1-score and accuracy for minority-class attacks. Specifically, on the NSL-KDD dataset, the overall accuracy increases from 74% to 94%, and the F1-score for the extremely rare U2R attack surges from 0% to 77%. Similarly, on the UNSW-NB15 dataset, the accuracy reaches 88%, a 10% improvement over the baseline DNN, and the F1-scores for extreme minority attacks such as Analysis, Backdoor, and Worms improved to 97%, 62%, and 84%, respectively. These results confirm that our method effectively outperforms traditional generation models and common class-balancing methods. It provides reliable technical support for industrial-Internet security. Full article

Soiling of solar panels has a considerable impact on the performance of photo voltaic (PV) systems, emphasizing the importance of developing reliable decision support tools for solar panel cleaning. Although recent convolutional neural network (CNN)-based models, including lightweight architectures such as SolPowNet, have demonstrated high classification accuracy, their performance can be sensitive to dataset variability and domain shifts encountered in real-world PV environments. Motivated by the lightweight design philosophy of SolPowNet, this paper proposes a hybrid and ensemble-based intelligent cleaning decision framework that integrates classical image processing, machine learning, and deep learning techniques. The proposed approach combines physically interpretable handcrafted texture and sharpness features classified using a Random Forest model with a pretrained MobileNetV3-Small CNN through a conservative OR-based ensemble fusion strategy. In addition, a probability-driven Soiling Index (SI) is introduced to translate classification confidence into actionable cleaning decisions, including no cleaning, light cleaning, and full cleaning. Experimental results on multiple PV image datasets demonstrate that, under domain-shift conditions where individual models may experience performance degradation, the proposed ensemble framework achieves an accuracy of up to 85.93% and attains a dusty-panel detection rate of 0.90 on the unseen dataset. On the in-distribution evaluation, the proposed OR-ensemble achieves an average accuracy of 0.9663 ± 0.0177 with dusty recall of 0.9896 ± 0.0104 over repeated stratified runs. Importantly, the conservative fusion strategy minimizes high-risk false negative cases while avoiding excessive misclassification of clean panels. Overall, the proposed framework offers a robust, scalable, and deployment-ready solution for intelligent PV cleaning decision support, advancing CNN-based soiling detection toward practical and risk-aware operation and maintenance systems. Full article

Unilateral or bilateral paired data are often encountered when people receive treatment for paired organs or body parts. Compared with using only unilateral or bilateral data alone, the utilization of combined data can provide additional information. With combined unilateral and bilateral data, this article aims to propose three statistical tests and three confidence interval methods of relative risk ratio in a stratified design under Dallal’s model. Our simulation results show that the score test has a more robust type I error rate compared to other tests in all cases. Meanwhile, the confidence interval method based on the score test always provides coverage probability close to the nominal level and satisfactory coverage width. Finally, two real examples of otolaryngology and myopathy are applied to illustrate the application of the proposed tests and confidence interval methods. Full article

Global climate warming has increased the risk of glacial lake outburst debris flows (GLODFs) in high mountain regions. It is characterized by frequent and clustered occurrences, particularly in the Himalayan region, and represents an inescapable challenge for high mountain areas in the future. GLODF susceptibility assessment is critical to risk mitigation but remains a challenge owing to its complex triggering mechanisms and watershed structure. GLODF is a complex system failure process, including the failure probabilities of multiple glacial lakes in a watershed, the complex flow path of flood, the transition probability from flood to debris flow, and the overlapping of debris flows formed in different branches in the watershed. Therefore, multiple trigger factors, hazard sources and flow paths should be considered in the assessment of susceptibility to GLODFs. In this study, a systematic approach and mapping for GLODF susceptibility assessment are proposed based on the theory of system failure analysis. The main steps include: (1) identification and classification of the potential hazard sources in the target watershed; (2) arrangement of the flow path and abstraction of the key-node diagram; (3) establishment of the system failure structure of a GLODF; and (4) predisposing factor analysis and susceptibility assessment. Moreover, the predisposing indexes of GLODF susceptibility assessment are proposed, combining the main factors affecting both glacial lake outbursts and subsequent debris flows. The proposed model was applied in the Congduipu River basin, Nyalam, Tibet, China, which has more than 6 glacial lakes and 11 gullies, with an area of 366 km², and encountered more than four GLODFs in recent years. The results show that there are one very high-susceptibility glacial lake, two high-susceptibility glacial lakes, and gullies that are in series with high-susceptibility glacial lakes that are mostly medium–highly susceptible to glacial outbursts. The results were verified by historical records and field investigations in the Congduipu River basin. This method is applicable to quickly evaluate the susceptibility to GLODFs at the watershed and regional scales with multiple glacial lakes and gullies. Full article

Understanding local population density and spatial habitat use is essential for wildlife conservation in fragmented mountainous landscapes. This study examined the habitat use patterns of Capra aegagrus in the mountainous regions of Batman, Türkiye, using Kernel Density Estimation (KDE) and spatial regression modeling. Significant spatial autocorrelation (Moran’s I = 0.799, p < 0.001) justified the use of a Spatial Error Model (AIC = −254.59). Built land proportion had a strong negative effect, with a 10% increase associated with a 31% decline in KDE intensity. Elevation also showed a modest negative association with habitat use intensity, whereas slope and bare land proportion were positively associated. The southern stratum exhibited higher relative encounter intensity, and the spatial autoregressive parameter (λ = 0.92) indicated strong spatial structuring. To complement spatial habitat analysis with demographic estimates, population density was assessed using Line Transect Distance Sampling in the northern and southern sub-regions. The estimated local density was 6.47 individuals/km² (95% CI: 4.11–10.16), with overlapping confidence intervals between sub-regions. The variation in detection probability and encounter rate contributed the most to overall uncertainty. Because the surveys were restricted to accessible mountainous terrain, estimates represent local ecological density rather than province-wide abundance. Together, these results provide a spatially explicit baseline linking relative habitat use patterns with locally derived density estimates to support future monitoring and conservation planning. Full article

Continuous authentication is a promising method for protecting computer systems in the event of compromise of primary authentication factors, such as passwords or tokens. Systems employing continuous authentication that rely on biometrics may not be restricted to a single biometric characteristic; rather, they can simultaneously utilize multiple characteristics and subsequently arrive at a conclusive decision based on their collective analysis outcomes. One of the significant challenges researchers encounter when investigating effective fusion in decision-making is the lack of data. At present, data generation primarily involves the creation of feature vectors or attack simulation. This paper introduces a method for directly generating distances derived from a Siamese neural network, utilizing the probability density function of an existing distribution. Through statistical analysis, we successfully generated 5000 samples that correspond to the initial distribution, which were then employed to discover the threshold values at which FAR and FRR were less than 1%. The methods developed can be further applied to identify the most efficient strategies for integrating the results of continuous authentication in systems that incorporate multiple biometric characteristics. Full article

Parameter estimation of the three-parameter Weibull distribution is an important problem in reliability analysis and statistical modeling. Random right-censored data are widely encountered in engineering practice. Conventional least squares (LS) methods usually construct the empirical cumulative distribution function (CDF) based on rank statistics. However, this empirical assumption cannot adequately capture the nonlinear variation in failure probability with time in the Weibull distribution. To address this limitation, an iterative conditional probability based on conditional failure probability (ICP-CDF) is proposed. The method uses the parameter estimates obtained from the conventional LS approach as initial values, adjusts the ranks of failure data according to conditional failure probabilities, and updates the empirical CDF accordingly. Within a unified least squares estimation framework, an ICP-CDF-LS parameter estimation method is developed, in which both the CDF and distribution parameters are updated iteratively. Simulation studies and case analyses demonstrate that, compared with the LS and MLE methods, the proposed approach achieves superior overall performance in terms of estimation accuracy and stability, making it more suitable for practical engineering applications. Full article

This paper develops simultaneous confidence intervals (SCIs) for pairwise differences of means with zero-inflated Rayleigh (ZIR) distributions, a flexible framework for modeling positively skewed data with excess zeros. Closed-form expressions for the ZIR mean are derived, and several competing interval estimation procedures are investigated, including generalized confidence interval (GCI), parametric bootstrap (PB), method of variance estimates recovery (MOVER), delta-method normal approximation, and highest posterior density (HPD) intervals. The finite-sample performance of the proposed SCIs is examined via extensive Monte Carlo simulations, focusing on empirical coverage probabilities (CPs) and average interval lengths (ALs) over a broad range of parameter configurations and zero-inflation levels. A real data application to road accident fatality counts demonstrates the practical utility of the proposed methodology. The results show that the HPD method consistently achieves the most favorable balance between coverage accuracy and interval efficiency. Overall, this study advances reliable simultaneous inference for zero-inflated models commonly encountered in environmental, biomedical, and reliability studies. Full article

Multimodal multiobjective optimization problems (MMOPs) are widely encountered in real-world applications. While numerous evolutionary algorithms have been developed to locate equivalent Pareto-optimal solutions, existing Multimodal Multiobjective Evolutionary Algorithms (MMOEAs) often struggle to handle large-scale decision variables and sparse Pareto sets due to the curse of dimensionality and unknown sparsity. To address these challenges, this paper proposes a novel approach named MASR-MMEA, which stands for Large-scale Sparse Multimodal Multiobjective Optimization via Multi-stage Search and Reinforcement Learning (RL)-assisted Environmental Selection. Specifically, to enhance search efficiency, a multi-stage framework is established incorporating three key innovations. First, a dual-strategy genetic operator based on improved hybrid encoding is designed, employing sparse-sensing dynamic redistribution for binary vectors and a sparse fuzzy decision framework for real vectors. Second, an affinity-based elite strategy utilizing Mahalanobis distance is introduced to pair real vectors with compatible binary vectors, increasing the probability of generating superior offspring. Finally, an adaptive sparse environmental selection strategy assisted by Multilayer Perceptron (MLP) reinforcement learning is developed. By utilizing the MLP-generated Guiding Vector (GDV) to direct the evolutionary search toward efficient regions and employing an iteration-based adaptive mechanism to regulate genetic operators, this strategy accelerates convergence. Furthermore, it dynamically quantifies population-level sparsity and adjusts selection pressure through a modified crowding distance mechanism to filter structural redundancy, thereby effectively balancing convergence and multimodal diversity. Comparative studies against six state-of-the-art methods demonstrate that MASR-MMEA significantly outperforms existing approaches in terms of both solution quality and convergence speed on large-scale sparse MMOPs. Full article

This paper introduces a novel extension of the classical Lindley distribution, termed the X-Lindley model, obtained by a specific mixture of exponential and Lindley distributions, thereby substantially enriching the distributional flexibility. To enhance its inferential scope, a comprehensive reliability analysis is developed under a generalized progressive hybrid censoring scheme, which unifies and extends several traditional censoring mechanisms and allows practitioners to accommodate stringent experimental and cost constraints commonly encountered in reliability and life-testing studies. Within this unified censoring framework, likelihood-based estimation procedures for the model parameters and key reliability characteristics are derived. Fisher information is obtained, enabling the establishment of asymptotic properties of the frequentist estimators, including consistency and normality. A Bayesian inferential paradigm using Markov chain Monte Carlo techniques is proposed by assigning a conjugate gamma prior to the model parameter under the squared error loss, yielding point estimates, highest posterior density credible intervals, and posterior reliability summaries with enhanced interpretability. Extensive Monte Carlo simulations, conducted under a broad range of censoring configurations and assessed using four precision-based performance criteria, demonstrate the stability and efficiency of the proposed estimators. The results reveal low bias, reduced mean squared error, and shorter interval lengths for the XLindley parameter estimates, while maintaining accurate coverage probabilities. The practical relevance of the proposed methodology is further illustrated through two real-life data applications from engineering and physical sciences, where the XLindley model provides a markedly improved fit and more realistic reliability assessment. By integrating an innovative lifetime model with a highly flexible censoring strategy and a dual frequentist–Bayesian inferential framework, this study offers a substantive contribution to modern survival theory. Full article

Articles are among the most frequently encountered words during reading; however, it is not clear how deeply they are usually processed. This study examines whether native Spanish speakers use parafoveal article–noun agreement information to guide eye movements during reading. Using the gaze-contingent boundary paradigm, we manipulated the parafoveal preview of articles across two experiments. In Experiment 1, we manipulated gender agreement between the previews readers received of definite articles and the subsequent nouns (e.g., la mesa vs. el* mesa). In Experiment 2, we manipulated grammatical gender and number agreement between parafoveal article previews and the subsequent nouns jointly (e.g., los* mesa vs. una mesa). We found no evidence that parafoveal article–noun gender or number agreement affected article skipping probability, suggesting that initial parafoveal processing of articles does not extend to their grammatical properties. However, we observed increased total viewing time on the noun following mismatching previews, suggesting that, while the decision of whether to skip an article is taken largely without considering the grammatical properties of the upcoming words, readers do need more time to recover from the grammatical mismatch afterwards. We discuss the results in the context of current models of eye-movement control during reading. Full article

Reliable detection of unknown signals is essential for ensuring the robustness of underwater acoustic sensing systems, particularly in maritime security and autonomous navigation. However, Conventional deep learning models often exhibit overconfidence when encountering unknown signals and are unable to quantify predictive uncertainty due to their deterministic inference process. To address these limitations, this study proposes a novelty detection framework that integrates an out-of-distribution detector for neural networks (ODIN) with Monte Carlo (MC) dropout. ODIN mitigates model overconfidence and enhances the separability between known and unknown signals through softmax probability calibration, while MC dropout introduces stochasticity via multiple forward passes to estimate predictive uncertainty—an element critical for stable sensing in real-world underwater environments. The resulting probabilistic outputs are modeled using Gaussian mixture models fitted to ODIN-calibrated softmax distributions of known classes. The Kullback–Leibler divergence is then employed to quantify deviations of test samples from known class behavior. Experimental evaluations on the DeepShip dataset demonstrate that the proposed method achieves, on average, a 9.5% and 5.39% increase in area under the receiver operating characteristic curve, and a 7.82% and 2.63% reduction in false positive rate at 95% true positive rate, compared to the MC dropout and ODIN baseline, respectively. These results confirm that integrating stochastic inference with ODIN significantly enhances the stability and reliability of novelty detection in underwater acoustic environments. Full article

China’s Yellow River basin encounters widespread risks of reduced runoff and intensified hydrological drought. This study focuses on the middle and upper reaches of the Dahei River, the Yellow River’s primary tributary. In this region, the Soil & Water Assessment Tool (SWAT) hydrological model was employed to simulate hydrological processes, identify runoff changes and hydrological drought characteristics, and conduct attribution analysis from 1983 to 2022, as well as to project trends over the next 40 years. The results indicate that total runoff during the impact period (1999–2022) decreased by 55.26% compared to the baseline period (1983–1998). Climate change accounted for a contribution rate of 38.6% to this decline, while human activities accounted for 61.4%. Additionally, climate primarily altered surface runoff (SURQ) and lateral groundwater flow (LATQ) through precipitation changes, while land use had a predominant influence on total runoff volume by modifying SURQ. Both factors exhibited relatively minor effects on LATQ. Moreover, human activities contribute to hydrological drought at a rate of 36.11% to 94.25%. Drought probability is significantly influenced by climate through precipitation and temperature changes, while land use primarily mitigates hydrological drought by impacting the three runoff components. It is predicted that over the next 40 years, total runoff will decrease by 2.08% to 60.16%, along with hydrological droughts that are more frequent, longer in average duration, and more intense; however, the Maximum Drought Duration is anticipated to shorten. In the east and northeast, hydrological drought presents a trend of intensification, with central and western regions exhibiting weaker or declining changes. Full article

Estimating extreme quantiles and the number of future exceedances is an important task in financial risk management. More important than estimating the quantile itself is to insure zero coverage error, which implies the quantile estimate should, on average, reflect the desired probability of exceedance. In this research, we show that for unconditional distributions isomorphic to the exponential, a Bayesian quantile estimate results in zero coverage error. This compares to the traditional maximum likelihood method, where the coverage error can be significant under small sample sizes even though the quantile estimate is unbiased. More generally, we prove a sufficient condition for an unbiased quantile estimator to result in coverage error and we show our result holds by virtue of using a Jeffreys prior for the unknown parameters and is independent of the true prior. We derive a new, predictive distribution, and the moments, for the number of quantile exceedances, and highlight its superior performance. We extend our results to the conditional tail of distributions with asymptotic Paretian tails and, in particular, those in the Fréchet maximum domain of attraction which are typically encountered in finance. We illustrate our results using simulations for a variety of light and heavy-tailed distributions. Full article

The adoption of green production technologies is crucial for achieving sustainable agricultural development. However, farmers often encounter obstacles including technological complexity, budgetary constraints, and information asymmetry during the promotion. Digital technology adoption on a large scale provides a practical way to get over these challenges. This study utilizes survey data from 432 family farms in Jiangxi Province’s primary citrus-producing regions to systematically examine the impact of digital technology usage on farmers’ adoption of water-fertilizer integration technology within green production practices. It focuses on adoption probability, duration, and scale while exploring underlying mechanisms. Benchmark regression results indicate that digital technology usage significantly increases farmers’ probability of adopting water-fertilizer integration by 23.5% to 39.8%, extends adoption duration by 42.7% to 57.4%, and expands adoption scale by 16.7% to 29.1%. A series of robustness tests consistently supports these findings. Regarding the mechanism: Digital technology usage increases the adoption of water-fertilizer integration by enhancing farmers’ perceptions of economic, social, and environmental benefits. Heterogeneity analysis reveals that the promotional effect of digital technology on water-fertilizer integration is more significant among farmers who are highly educated and young, with lower capital (total capital expenditures on saplings and agricultural machinery) and lower land fragmentation levels. Furthermore, the promotional effect of digital technology on water-fertilizer integration adoption is only significant in the small-scale operation sample group. According to the study, a three-pronged strategy—digital empowerment, socialized services, and skills training—can hasten the widespread adoption of water-fertilizer integration in important citrus-producing regions. Full article