Search Results (51)

In this work, we study the joint performance of the quality and reliability in terms of quality–reliability (JQR) performance of an intelligent reflecting surface (IRS)-assisted wireless communication system under severe multipath fading and shadowing. The wireless channel model is given by the Inverse Power Lomax (IPL) fading model, representing a heavy-tailed fading channel, which can describe the hyper-Rayleigh fading and is verified using two different experimentally obtained measurement scenarios, namely, the LTE-case for high-frequency, long-range cellular communications and the device-to-device (D2D) case for lower-frequency short-range communications. For the considered channel model and communication scheme, analytical expressions for the outage probability (a metric related to the reliability) and the average bit error rate for both coherent and non-coherent modulation schemes (metrics associated with the quality of the communication system) are provided. By combining the aforementioned expressions, a unified JQR curve, together with its asymptotic forms in the high signal-to-noise ratio regime and asymptotically large number of IRS elements, is derived. It is proved analytically that the use of IRS with infinite elements can remove fading, while for a finite number of IRS elements, a closed-form signal-to-noise ratio (SNR) penalty factor is presented. The numerical analysis demonstrates that coherent modulations outperform non-coherent ones, higher-order quadrature amplitude modulation (QAM) systems are highly sensitive to the multipath fading, and the LTE-case exhibits better performance compared to the D2D-case for equal settings. Moreover, the joint quality–reliability approach highlights the existence of regions where quality is more preferable than reliability, allowing the allocation of resources based on these regions. All expressions have been verified using Monte Carlo simulations with excellent agreement. Full article

Accurate rainfall information is essential for water-related hazard assessment in mountainous regions, where complex terrain and sparse gauge networks limit monitoring reliability. This study evaluated long-term rainfall characteristics and the performance of three satellite precipitation products—CHIRPS, GPM IMERG, and GSMaP—along the National Highway 6 corridor in northern Vietnam. Daily gauge observations from 11 meteorological stations with station-dependent records between 1961 and 2024 were used to characterize rainfall variability and heavy-rainfall frequency. Matched gauge–satellite records from 2001 to 2024 were evaluated using continuous statistical indicators, contingency-table metrics, empirical cumulative distribution functions, and percentile-based analysis. Data from 2025 were additionally examined as an extreme-rainfall case study, supplemented by visual gauge–satellite comparisons; however, these data were not used as an independent satellite-validation period. The long-term gauge records showed marked spatial variability in rainfall magnitude and threshold-exceedance frequency. In 2025, all 11 stations recorded daily rainfall exceeding 50 mm, while eight stations recorded events exceeding 100 mm. Satellite-product performance varied substantially among stations, rainfall thresholds, and evaluation metrics, and no product was uniformly superior. At the 100 mm/day threshold, the probability of detection ranged from 0.024 to 0.276, whereas the false alarm ratio ranged from 0.781 to 0.916. Upper-tail analysis showed contrasting product-specific behavior: at the 99th percentile, CHIRPS and GPM IMERG underestimated gauge rainfall by 20.95 and 8.95 mm, respectively, whereas GSMaP overestimated it by 35.57 mm. These findings demonstrate that local validation, uncertainty assessment, and application-specific adjustment are necessary before satellite precipitation products are used for flash-flood, rainfall-induced landslide, drainage-risk, and transportation-infrastructure assessments in mountainous regions. Full article

Failures at large-scale open-pit mines and tailing dams pose critical risks to human life, environmental systems, and economic sustainability. Although Interferometric Synthetic Aperture Radar (InSAR) has proven effective in detecting long-term surface deformation, a scientifically robust early-warning framework has not yet been established because standardized quantitative thresholds that are capable of distinguishing benign consolidation settlement from instability-driven deformation remain unavailable.InSAR has proven effective for detecting long-term surface deformation. However, a scientific early-warning framework has not yet been proposed or developed due to the absence of standardized quantitative thresholds that distinguish benign consolidation settlement from instability-driven deformation. This research proposes a novel InSAR-based Failure-Risk Index (FRI) that integrates displacement, velocity, and, most importantly, deformation acceleration into a single, normalized metric as an early warning system for mining infrastructure instability. The framework that we propose (i) emphasizes acceleration as a leading indicator of change in mechanical regime, (ii) incorporates a statistically guided separation of long-term consolidation settlement from anomalous deformation based on baseline variability, (iii) applies a statistical standardization and change-point detection system. The methodology is validated through a retrospective analysis of the heap leach failure—that occurred in Çöpler Gold Mine in Erzincan, Türkiye, on 13 February 2024—by using a set of Sentinel-1 time-series images collected between 2014 and 2024. The results prove that while displacement and velocity remained within ranges typically interpreted as stable, deformation acceleration exhibited a statistically significant increase that began around 2020, exceeded baseline variability by approximately two orders of magnitude, which is approximately four years before the collapse, and marked the onset of tertiary creep and progressive instability. The proposed FRI framework successfully captures this transition and provides a transferable, meaningful early-warning framework to support proactive risk management and improve the safety of mining infrastructure. Full article

Coral reef ecosystems are increasingly threatened by climate change, pollution, and overfishing, causing major declines in marine megafauna and high-trophic-level fishes. Monitoring these species is vital for conservation, yet traditional survey methods are slow and resource intensive. This study presents a semi-automated monitoring pipeline that integrates deep learning (DL) with human-in-the-loop validation to streamline Baited Remote Underwater Video (BRUV) analyses in the Gita Nada Marine Protected Area (MPA), Indonesia. A total of 244 BRUV deployments from SORCE’s long-term monitoring program in the Gita Nada MPA, comprising 328 h of footage, collected 2023–2025 under Indonesian research oversight through Yayasan SORCE Konservasi Indonesia, were processed using a DL workflow. To address long-tailed species distributions, focal taxa were grouped into six Morphological Groups and detected using a YOLOv12x model trained via transfer learning from the Community Fish Detector. A custom temporal-tracking framework extracted ecological metrics including N, Time to First Visit ($T_{1^{st}}$), and Visit Duration ($T_{visit}$). The pipeline achieved moderate to high detection and tracking performance for several Morphological Groups, achieving object detection F1-scores of up to 0.873 and an overall tracker recall and precision of 0.80 and 0.76, respectively, although performance varied substantially among groups and was substantially limited for data-deficient taxa. As a proof-of-concept, we applied the framework to assess ecological shifts in Cheloniidae and Carangidae across coral-cover gradients. Overall, this semi-automated approach reduces BRUV processing effort and provides a scalable foundation for generating the large datasets needed to detect subtle ecological change. Full article

With the rapid expansion of artificial intelligence infrastructure and cloud computing services, data centres are evolving from rigid electricity loads into flexible resources capable of contributing to renewable energy integration, grid regulation and cross-regional computing power allocation. Addressing the shortcomings in existing research regarding the differences between various types of computing tasks, the mechanisms of green migration under network constraints, and the characterisation of curtailment risks for renewable energy, this paper proposes a risk-aware collaborative optimisation and scheduling method for a power–computing–network–storage coupled system across remote data centres. Firstly, a hierarchical model of multi-type computing tasks is constructed, classifying data centre loads into fixed real-time tasks, online inference tasks, long-duration AI training tasks, and opportunistic elastic tasks, to characterise the differences between these tasks in terms of latency, time-shift, migration, and completion volume constraints. Secondly, a graph-attention-inspired green affinity prior is proposed, mapping grid topological distance, renewable energy availability, data centre PUE, and energy storage regulation capacity into interpretable migration signals, thereby guiding flexible computing power to migrate towards nodes with abundant green electricity and favourable grid support conditions. Subsequently, we introduce the CVaR metric to quantify the tail risk of renewable energy curtailment, establishing a multi-scenario stochastic linear optimisation model that incorporates DC power flow, unit output, renewable energy utilisation, campus energy storage, task SLAs, and cross-node migration constraints. A 24 h simulation based on the IEEE 10-machine, 39-node system demonstrates that the proposed method can reduce the expected curtailment volume from 176.939 MWh to 0 MWh, lower the CVaR curtailment risk from 694.085 MWh to 0 MWh, and increase the proportion of green computing power by 9.283 percentage points compared to the fixed-load baseline, whilst improving the five-tier collaborative score by 4.885 points. Full article

To improve the path-following performance of an underactuated autonomous underwater vehicle (AUV) under varying path geometries and desired velocities, this study proposes a direct X-rudder control method based on Task-Informed Inductive-Bias Conservative Soft Actor–Critic (TIB-CSAC). The proposed method directly learns the X-rudder control policy from the path-following information of the current and subsequent path segments in a data-driven way, thereby avoiding the complex design and manual tuning of guidance laws and attitude controllers for rudder command generation. To support such two-segment policy learning, a task-informed inductive-bias encoder is proposed to construct structured and conditioned state representations, thereby improving sample efficiency and overall training quality. In addition, given the long-tail characteristics of task difficulty in agent training, a multi-head conservative value evaluation mechanism is incorporated to mitigate return drawdowns induced by challenging tasks in the tail stage of training and to enhance tail-stage convergence stability. The path-following performance is validated in three representative scenarios with different path pitch, path heading variations, and desired surge velocity conditions. The results show that, compared with the baseline soft actor–critic (SAC) method, TIB-CSAC improves multiple vertical and horizontal error metrics, including maximum absolute error, mean absolute error, tail error, and error threshold exceedance ratio. These results indicate that TIB-CSAC not only improves overall adherence to the reference path, but also more effectively suppresses extreme errors and tail errors, thereby demonstrating stronger path-following robustness and reliability. Full article

Kubernetes Horizontal Pod Autoscaler (HPA) primarily relies on resource-based metrics, such as CPU utilization, which are poorly suited to capturing the latency variability of AI inference workloads. In this paper, we propose a custom-metric-driven autoscaling approach that leverages inference latency histograms as first-class scaling signals for Kubernetes HPA. The proposed framework integrates a Prometheus Operator (PO)-based observability stack with the Prometheus Adapter to expose and aggregate per-pod inference latency metrics, enabling workload-aware scaling decisions. We evaluate the approach using four mid-scale transformer-based inference services, comprising two reasoning-like and two latency-stable workloads, under high-concurrency conditions. The experiments analyze latency variation, tail behavior, and replica dynamics across multiple autoscaling policies, including variations in scale-up aggressiveness (3 pods/30 s, 3 pods/60 s, 6 pods/60 s), inference-time thresholds, and stabilization windows. Compared to CPU-based autoscaling, inference-driven policies reduce mean response time by 18–27% for reasoning-like workloads and 12–20% for stable workloads. The results show that latency-variable workloads exhibit wider tails and higher variance, indicating the need for moderately aggressive scale-up strategies to avoid long-lasting latency spikes. Overall, the findings show that inference-latency-driven custom metrics significantly improve autoscaling efficiency and stability for transformer-based inference workloads in cloud-native environments. Full article

With the rapid advancement of Earth observation technologies and the growing demand for intelligent remote sensing applications, high-resolution remote sensing imagery provides critical data support for a range of downstream applications, including land monitoring and disaster assessment. In this context, multi-label remote sensing image classification has become an important research task, because a single image may contain multiple ground-object categories with complex spatial distributions and semantic co-occurrence relationships. However, challenges such as the coexistence of multiscale objects, complex semantic dependencies, and long-tail category distributions impose significant limitations on existing methods in terms of feature representation capacity and class-balanced modeling. To address these challenges, a Multiscale Dynamic Reasoning Network (MSDR-Net) is proposed. Different from methods that focus on localized optimization for a single challenge, MSDR-Net establishes a task-driven modeling framework that jointly integrates multiscale feature extraction, label-aware semantic reasoning, and long-tail category optimization within an end-to-end architecture. The proposed network consists of three core modules. The Multiscale Feature Enhancement (MSFE) module incorporates a Feature Pyramid Network-based fusion mechanism, integrating deep semantic information with shallow, detailed features to effectively enhance the representation of multiscale objects. The Dynamic Semantic Reasoning (DSR) module introduces a Transformer-based global attention mechanism that models long-range dependencies among image features, enabling the capture of complex global semantic relationships. In the loss optimization stage, a Difficulty-Weighted Loss (DW-Loss) is introduced, which jointly incorporates category frequency weights and prior difficulty coefficients to dynamically regulate the contributions of rare classes and hard samples during training, thereby mitigating bias induced by class imbalance. Experiments conducted on the large-scale Detection in Optical Remote Sensing Images dataset demonstrate that the proposed method achieves superior performance. Ablation studies validate the effectiveness of each component, while comparative experiments indicate that MSDR-Net achieves a mean Average Precision of 95.88%, outperforming existing state-of-the-art methods. An improvement of approximately 1.74% is observed over the strongest baseline, MSCA, with consistent advantages demonstrated across Overall F1 and Class-wise F1 metrics. By unifying multiscale feature extraction, global semantic reasoning, and balanced loss optimization within a single framework, MSDR-Net provides a robust and efficient solution for multi-label classification in complex remote sensing scenarios. Full article

Accurate and efficient semantic segmentation of point cloud data is critical in many application areas involving indoor scene understanding. In particular, fine-grained object categories, high data density, and class imbalance in high-resolution indoor datasets significantly limit class discrimination in 3D semantic segmentation. The multimodal data structure, high-fidelity geometry, and long-tail class distribution of the recently popular ScanNet++ dataset further exacerbate these challenges. This study proposes a novel Long-Tail Aware Cross-Modal Graph Attention Network (LT-CM-GACNet++) to address fine-grained 3D semantic segmentation under long-tail distributions. The proposed method integrates dynamic graph-based geometric feature extraction with a lightweight visual feature extractor based on MobileNetV3, enabling effective fusion of geometric and RGB-based information. The proposed Cross-Modal Graph Attention (CMGA) module facilitates adaptive information transfer between modalities, enabling more effective representation learning of both local and global contextual features. To mitigate the adverse effects of long-tail class distributions, prototype-based representation learning and a class frequency-aware loss function are jointly employed. This strategy improves the learning of rare classes while enhancing the discrimination between visually and geometrically similar categories. In the preprocessing stage, density-based sampling, normal vector estimation, and block-based fixed-size point cloud generation are applied to high-resolution mesh-derived data. The proposed model is evaluated on 50 scenes and 100 semantic classes selected from the ScanNet++ dataset. Experimental results demonstrate that the proposed method achieves significant improvements over existing approaches in terms of both overall segmentation performance and rare-class performance. In particular, notable gains are observed in mean Intersection over Union (mIoU) and rare-class mIoU metrics. These results highlight the effectiveness of cross-modal learning for high-resolution 3D scene segmentation under long-tail distributions. Full article

We employ an empirical framework for real estate securities that incorporates portfolio optimization, return distribution tail diagnostics, risk metrics, modeling of long-range dependence in return volatility, regression against benchmark indices, and option pricing, treating these as necessary layers of a risk-management structure that concentrates on downside risk. Optimization compared mean–variance against downside-sensitive conditional value at risk. Tail behavior was assessed via skewness, kurtosis, and extreme value theory; volatility persistence was examined using ARMA–FIGARCH models. Benchmark dependence was examined via the capital asset pricing model (CAPM), employing endogenous and exogenous market proxies. Insurance instruments via European options were priced using a doubly subordinated normal inverse Gaussian pricing model capable of modeling skewed, heavy-tailed return distributions. Significant findings for the optimized portfolios include return distributions with losses that are heavier-tailed than gains; a transition in time from moderate-to-high long-range dependence in conditional volatility; smaller values of CAPM “alpha” and “beta” for minimum-risk portfolios compared to tangent portfolios; and significant implied volatility values. Full article

Large-scale disasters can result in chronic pollution of coastal environments with unanticipated and poorly quantified impacts, such as the reshaping of marine connectivity. A recent example is the collapse of the Fundão tailings dam in 2015, which released about 50 million m³ of mine waste into the Doce River, affecting one of Brazil’s largest estuarine–mangrove systems. Here, we combine a high-resolution CROCO hydrodynamic simulation with an individual-based Lagrangian model (Ichthyop) to track the dispersal of mangrove crab (Ucides cordatus) larvae from four estuaries along the southeastern Brazilian margin between 2022 and 2024. Trajectories crossing seasonal msPAF fields derived from in situ water-quality measurements were used to quantify larval exposure to contaminants from mine waste. These fields were based on measured concentrations of As, Ba, Cd, Co, Cr, Cu, Fe, Hg, Mn, Ni, Pb, V, Zn, and Al. Results show that surface shelf flow and mesoscale activity in the vicinity of the Doce River mouth contribute to offshore export of larvae, while the reef-dominated Abrolhos shelf promotes retention. Interannual variability alternates between long-distance export and local retention, associated with regional climate variability. Larval mortality rates caused by offshore advection and lethal temperature are high (65–75%). In addition to these modeled mortality sources, surviving cohorts frequently crossed areas with elevated msPAF values during transport, indicating potential exposure to metal(loid) mixtures. This suggests that the regional connectivity of U. cordatus is under chronic stress that likely compromises the integrity and resilience of coastal populations, since southern estuaries depend strongly on northern larval sources. The integration of Lagrangian simulations with in situ contaminant monitoring and spatially explicit exposure metrics demonstrates that transport pathways regulate not only connectivity among estuaries but also the duration and intensity of larval exposure to pollutants. Full article

This study investigates multi-label movie genre prediction from user-written reviews in which textual content is inherently subjective and the movies reviewed naturally belong to multiple genres. To address extreme class imbalance and label sparsity in the IMDb Large Movie Review Dataset, 234 fine-grained genre labels are consolidated into 35 parent categories using a deterministic genre-mapping strategy. A unified experimental pipeline evaluates traditional feature-based models (TF-IDF vectorization with Logistic Regression and Linear SVM), a sequence-based BiLSTM with self-attention using GloVe embeddings, and transformer-based architectures (DistilBERT and RoBERTa) under consistent evaluation metrics. Experimental analyses indicate that transformer-based architectures outperform alternative approaches, with RoBERTa achieving the best performance (Macro-F1 = 0.518, Micro-F1 = 0.576). The results indicate that genre consolidation enhances robustness under long-tailed label distributions. Moreover, contextualized transformer representations better capture implicit and subjective cues. The results further clarify practical trade-offs between predictive performance and computational efficiency across model families. Full article

During seafloor terrain mapping missions conducted by AUVs, positioning error accumulation occurs inevitably over long distances due to the unavailability of global satellite navigation signals underwater. Moreover, the alternating distribution of flat and undulating regions on the seafloor renders single-constraint-based bathymetric SLAM methods prone to performance degradation in complex environments. To address these challenges, this paper proposes a multi-constraint hybrid strategy SLAM framework for AUV-based seafloor terrain mapping, grounded in an analysis of error accumulation mechanisms and constraint failure characteristics. The framework establishes a hierarchical and progressive constraint architecture to enable collaborative optimization across different spatial scales and topographic conditions. At the foundational pose estimation stage, multi-source trajectory information is fused to ensure continuity and stability in pose computation. In the local consistency constraint stage, an improved point cloud registration method combined with a neighborhood survey-line constraint mechanism is introduced to enhance geometric consistency among survey lines in feature-sparse regions. At the global optimization stage, a loop closure detection strategy is designed based on topographic statistical features, incorporating adaptive thresholds and correlation metrics to achieve robust introduction of global constraints. By flexibly integrating direct registration and feature-matching strategies according to topographic characteristics, the framework fully leverages the advantages of multi-constraint cooperative optimization. The proposed method is validated by the field data. Experimental results on real lake-trial data show that, relative to the baseline configurations evaluated under identical noise-injection conditions, the MCHS-SLAM framework yields more concentrated consistency-error distributions with markedly shorter large-error tails, and exhibits improved error suppression relative to the reference trajectory. This work presents a methodological framework for high-quality seafloor terrain mapping under heterogeneous terrain conditions, providing a basis for future extensions toward onboard real-time deployment. Full article

As social infrastructure intensively developed during the high economic growth period of the 1970s faces simultaneous aging, there is an urgent need to transition from conventional reactive maintenance to preventive maintenance utilizing various data (data-driven asset management. However, the greatest barrier in practice is that inspection data is unevenly distributed in analog formats such as paper and unstructured files, and heavily relies on the subjective visual evaluation of expert engineers (e.g., discrete graded evaluations from A to D). The intervention of this “Assessor Bias” makes it difficult to ensure the robustness required for direct statistical analysis. This paper serves as a bridge between this analog expert knowledge and quantitative data science. It formulates human cognitive conflicts (true state, peer pressure, avoidance of cognitive load) using the distance-decay model of the Analytic Hierarchy Process (AHP) and the Softmax function, constructing a micro-macro link model accompanied by stochastic variations. Through large-scale multi-agent simulations ($N={10}^7$) validating the model’s convergence, it was demonstrated that in long-tail distributions formed under peer pressure, macroscopic statistical distance metrics such as the Kullback-Leibler (KL) divergence ignore the fact that a small number of true signals are non-linearly suppressed, causing a statistical misinterpretation that “the error is within an acceptable range”. This implies that as long as macroscopic statistical indicators are over-trusted, signs of critical deterioration (minorities) will be structurally marginalized. Returning to the debate on “Homogeneity (Homogenität)” in German social statistics, this paper advocates that in order to realize objective “Micro-segmentation of Homogeneous Statistical Populations,” a paradigm shift from qualitative methods relying on human intuition to quantitative methods incorporating multi-criteria decision making is essential, rather than simply expanding the sample size. Full article

In intensive care units, large-scale clinical time-series data are continuously accumulated through electronic medical records and bedside monitoring systems. However, direct utilization of such data for clinical decision-making remains challenging due to irregular sampling, pervasive missingness, unstructured diagnostic information, and incomplete ICD labeling. Automated ICD coding constitutes an extreme multi-class classification problem with thousands of long-tailed categories, while intervention prediction tasks, such as mechanical ventilation management, involve rare transition events and severe class imbalance. To address these challenges, we propose CAGE, a hierarchical Clinical Decision Support System framework that integrates diagnosis, time-series signals, and intervention prediction. The framework first infers admission-level diagnostic context using a partial-label Automated ICD Coding module that combines DCNv2 with an Adaptive CLPL loss, producing probability-weighted diagnostic embeddings. These embeddings are subsequently fused with ICU time-series tensors and processed by a multi-branch Temporal Convolutional Network equipped with an ICD-conditioned gating mechanism to predict future ventilation state transitions. The experimental results demonstrate that DCNv2 achieves consistent superiority across all hit@k and probability concentration metrics for ICD coding. For intervention prediction, the proposed method substantially outperforms existing baselines, achieving a Macro-AUC of 98.2, Macro-AUPRC of 77.4, and F1-score of 79.4. These findings indicate that reinjecting diagnostic context as a conditioning variable, together with imbalance-aware loss design, effectively enhances rare-event detection and improves the practical applicability of clinical decision support systems. Full article