Search Results (7,708)

Reliable autonomous perception is essential for indoor service machines operating in human-centered environments, where weak textures, repetitive structures, and frequent dynamic interference often degrade localization stability. Conventional RGB-D SLAM systems typically rely on static-scene assumptions or binary semantic masking, which are insufficient for handling persistent and fine-grained environmental dynamics. This paper presents a robust autonomous perception framework based on geometry-aware RGB-D SLAM, with a particular emphasis on probabilistic dynamic modeling at the feature level. The proposed system integrates multi-granularity geometric representations, including point features, parallel-line structures, and planar regions, to enhance geometric observability in low-texture indoor environments. On this basis, a probabilistic dynamic model is introduced to explicitly characterize feature reliability under motion, where dynamic probabilities are initialized by object detection and continuously updated through temporal consistency, spatial propagation, and multi-view geometric verification. Large-scale planar structures further serve as stable anchors to support robust pose estimation. Experimental results on the TUM RGB-D dynamic benchmark demonstrate that the proposed method significantly improves localization robustness, reducing the average ATE RMSE by approximately 66% compared with representative dynamic SLAM baselines. Additional evaluations on a real-world indoor dataset further validate its effectiveness for long-term autonomous perception under dense motion and frequent occlusions. Full article

Corporate financial distress typically emerges through a gradual accumulation process, rendering crisis prediction inherently dynamic and path-dependent. However, many existing studies continue to rely on static cross-sectional data or short-term observations, which limits their ability to capture the temporal evolution of financial risk. To address this issue, this study develops a time-series financial crisis early warning framework based on Recurrent Neural Networks (RNNs) and systematically evaluates the incremental value of temporal information in corporate distress prediction. Using annual data of Chinese A-share listed companies from 2019 to 2023, we construct both single-year cross-sectional datasets and a five-year multi-period time-series dataset under a unified experimental protocol. Within this dual-framework setting, RNNs are compared with Random Forest (RF), Support Vector Machine (SVM), and Backpropagation Neural Network (BPNN) using identical feature sets, training–testing splits, and evaluation criteria. Model performance is assessed through multiple metrics, including Accuracy, Precision, Recall, F1 score, and AUC, complemented by statistical validation using McNemar tests, loss-based comparisons, and bootstrap confidence intervals. The empirical results show that while RF and BPNN exhibit strong robustness in static, single-period prediction tasks, RNNs achieve consistently superior performance when multi-period temporal information is explicitly modeled. Statistical tests indicate that the observed performance advantages of RNNs are systematic and stable, though moderate under the current sample size. This study provides empirical evidence that incorporating temporal structures into financial crisis prediction can substantially enhance predictive effectiveness under constrained labeled data. The findings highlight the importance of time-series modeling for early warning applications and offer practical guidance for selecting appropriate predictive frameworks across different data structures. Full article

Forecasting post-seismic landslide displacement is challenged by the difficulty in distinguishing short-term acceleration from creep and the risk of spatiotemporal leakage. To address this, an interpretable deep-learning framework is developed, integrating SBAS-InSAR time series with an Attention-enhanced Gated Recurrent Unit (Attention-GRU). Prior to modeling, a multi-stage preprocessing strategy, including empirical mode decomposition, is applied to mitigate noise and delineate active deformation zones. Unlike standard architectures, the model’s temporal attention mechanism adaptively amplifies critical precursory acceleration phases. Furthermore, a strict landslide-object-based partitioning strategy is employed to rigorously mitigate spatiotemporal leakage. The framework was evaluated in the Le’an Town landslide cluster using multi-source data. Targeting identified hazardous regions, the method achieved an R² of 0.93 and reduced MAPE by 42.7% relative to the SVR baseline. This reflects a location-specific predictive capability, within active zones rather than regional generalization. SHapley Additive exPlanations (SHAP) further confirmed the model captures physical relationships, such as sensitivity to 25–35° slopes and vegetation degradation. Ultimately, the proposed framework offers a transparent, physically interpretable tool for operational hazard mitigation. Full article

The rapid growth of renewable integration and active consumer participation has made modern power grids increasingly complex and dynamic, where maintaining balanced and efficient energy distribution remains a central challenge. This paper introduces a symmetry-aware optimized fuzzy deep reinforcement learning-gated recurrent unit (OF-DRL-GRU) model that exploits the natural symmetry and asymmetry in demand–generation behavior to achieve stable and adaptive load balancing. The proposed architecture consists of four core modules: a fuzzy logic layer that formulates symmetrically distributed membership functions for interpretable and balanced state transitions; a DRL agent that governs decision actions through a symmetry-preserving reward mechanism balancing exploration and exploitation; a GRU network that models temporal symmetries while performing controlled symmetry-breaking during dynamic fluctuations to enhance generalization; and an improved multi-objective biogeography-based optimization (IMOBBO) algorithm that optimizes fuzzy parameters and model hyper-parameters through adaptive migration alternating between symmetry preservation and deliberate asymmetry, ensuring efficient convergence and global diversity. The synergy among these modules forms a unified symmetry-aware optimization paradigm, reflecting how symmetric structures sustain stability while purposeful asymmetry enhances robustness and adaptivity. The proposed framework is evaluated using three benchmark datasets (UK-DALE, Pecan Street, and REDD) and compared against several advanced and competitive models. Experimental outcomes show that the proposed OF-DRL-GRU model achieves 99.23% accuracy, 99.69% recall, and 99.83% area under the curve (AUC), alongside faster runtime, lower variance, and improved convergence stability. These results demonstrate that incorporating symmetry–asymmetry principles within AI-driven optimization significantly enhances interpretability, resilience, and energy efficiency, paving the way for intelligent, self-adaptive load management in next-generation smart grids. Full article

The problem of analyzing the mechanisms of variability in population dynamics caused by the combined influence of the Allee effect, immigration and random fluctuations is addressed. In this study, we explore such a multi-factorial problem based on a Ricker-type population model. For the deterministic version of the model, the transformations of system dynamic regimes caused by changes in parameters of growth rate and intensity of immigration are determined using bifurcation analysis. For the randomly forced population model, the phenomena of stochastic excitement and noise-induced temporal extinction are revealed and investigated. The parametric study of these effects uses statistical data obtained from direct numerical modeling as well as an analytical approach based on the stochastic sensitivity technique and the confidence interval method. Full article

Reliable bearing fault diagnosis under complex operating conditions is often hindered by the loss of critical information during feature extraction, particularly for weak fault signatures embedded in vibration signals. To address this challenge, this work proposes a parallel multi-domain deep learning framework that emphasizes the preservation and complementary exploitation of time-domain, frequency-domain, and time–frequency representations. The proposed framework integrates temporal modeling to capture long-range signal evolution, phase-aware frequency-domain analysis to preserve amplitude–phase coherence, and transient-enhanced time–frequency representations to highlight weak impulsive features in noisy environments. To effectively integrate heterogeneous representations, a dynamic self-attention-based fusion strategy is introduced, enabling adaptive interaction and importance reweighting among multi-domain features. Experimental studies conducted on bearing datasets from Huazhong University of Science and Technology and the University of Cincinnati demonstrate that the proposed method achieves diagnostic accuracies of 99.63% and 99.82%, respectively, significantly outperforming state-of-the-art deep learning and multi-domain diagnostic methods, with accuracy improvements exceeding 20% compared to representative baseline models. Furthermore, ablation and robustness analyses confirm that the coordinated preservation and fusion of multi-domain information significantly enhance diagnostic reliability and generalization performance under complex operating conditions. Full article

Subsurface temperature is an important parameter for characterizing oceanic physical processes, and accurate prediction of subsurface temperature is essential for understanding oceanic changes. Existing methods primarily focus on spatial modeling but offer limited characterization of the spatiotemporal structure and frequency features of sea temperature. They also suffer from restricted receptive fields and limited ability to model long-term dependencies. In this study, we propose a deep learning model named Fourier Window Transformer (FWinFormer), which integrates frequency-domain modeling to predict the three-dimensional subsurface temperature over the next 24 days. The model incorporates both temporal and frequency characteristics to enhance prediction accuracy. It consists of three modules: a Spatial Block Encoder, a Translator, and a Spatial Block Decoder. The spatial encoding and decoding modules are designed to extract spatial features, while the Translator models multi-scale temporal features based on the features extracted by the encoding and decoding modules. The input consists of 24 days of historical satellite observations, including sea-surface temperature (SST), salinity (SSS), eastward velocity (SSU), northward velocity (SSV) and height (SSH). We compared the model predictions with reanalysis data and evaluated performance from the perspectives of temporal evolution, spatial distribution, and vertical structure. Additionally, we validated the predicted temperatures against in situ observations. The results show that the model achieves strong and consistent performance across various temporal scales and spatial regions, with MAE, RMSE, and R² values of 0.529, 0.785, and 0.994, respectively, for the 24-day average prediction. Full article

Balancing food production, water conservation, and carbon emissions (CEs) is critical in Northeast China (NEC), yet food–carbon–water (FCW) interactions remain poorly quantified at pixel scale. Conceptually, we move beyond administrative-unit nexus assessments by providing a crop-explicit, grid-based FCW diagnosis that identifies where crop-specific bottlenecks emerge and supports zoning-oriented interventions. We fused multi-source datasets with process models to estimate CEs, water use efficiency (WUE), and yield for maize, rice, and soybean at 500 m resolution during 2001–2020 and evaluated synergies/trade-offs based on Sen’s slope trends and nexus performance using coupling coordination degree (CCD). Annual mean CE (230.8–37,300 kg CO₂-eq ha⁻¹), yield (0–10,031 kg ha⁻¹), and WUE (0–6 kg C m⁻³) exhibited pronounced spatial heterogeneity. Higher CEs and yield concentrated in the central–southern plains, whereas WUE showed a patchier pattern with localized high values. Temporally, CEs increased for all crops, with rice consistently exhibiting the highest CEs. Soybean showed the most pronounced WUE improvement, reaching >2.0 kg C m⁻³ after the early 2010s. Pixel-wise correlations revealed a robust CE–WUE antagonism for all crops (r = −0.33 to −0.60), while CE–yield coupling was crop-dependent (soybean positive, maize weakly negative, rice non-significant). Trend-based coupling further showed that synchronized CE and yield increases dominated 45.7% of croplands, whereas trade-offs were more common when WUE was involved (CE–WUE: 38.0%; WUE–yield: 41.8%), peaking in rice systems (61.8% and 54.0%, respectively). CCD mapping indicated widespread basic coordination but strong crop contrasts. Rice had the lowest coordination (mean CCD = 0.36 ± 0.17) and the largest shares of moderate-to-severe imbalance, identifying rice as the primary FCW bottleneck, whereas maize and soybean more frequently achieved good-to-high coordination. These results support a zoned strategy that consolidates coordinated maize/soybean areas, prioritizes paddy water-saving and low-emission upgrades, and limits further rice expansion in water-constrained zones. Full article

Sustainable urban development increasingly relies on hyperlocal environmental analytics created by smart city platforms that combine stationary and mobile sensors, Earth observations, meteorology, and land-use data. However, accurate spatio-temporal resolution can provide indirect identification and amplify cybersecurity threats. This article proposes the regulatory and technical mapping that implements the General Data Protection Regulation (GDPR) and the Network and Information Security Directive (NIS2) throughout the lifecycle of environmental data—reception, transport, storage, analytics, sharing, and publication. The methods combine doctrinal legal analysis, a review of the scope of recent research, formalized compliance modeling, modeling with synthetic city-scale datasets, expert identification, and demonstration of integrated analytics. The demonstration links deep evaluation of neural abnormalities (convolutional plus recurrent layers), short-term Fourier transformation of sensor signals, byte-to-image telemetry fingerprints, and protocol event counters, thereby tracking detection to explanatory evidence and to control actions. Deliverables include a matrix aligning lifecycle stages with GDPR principles and rights, as well as with the responsibilities of NIS2; a checklist for assessing the impact on data protection, which takes into account the risks of fairness and stigmatization; a basic set of controls for identification and access, secure design, monitoring, continuity, supplier assurance, and incident reporting; as well as a multi-layered publishing strategy that combines transparency with privacy through aggregation, delayed release, differentiated privacy budgets, and research enclaves. The visualization confirms that technical signals can be included in audit-ready reporting and automated response, while the guidelines legally clarify the relevant bases for common use cases such as air quality assurance networks, noise mapping, citizen sensor applications, and mobility and exposure modeling. The effects of the policy emphasize shared services for small municipalities, supply chain security, and ongoing review to counteract the mosaic effect. Overall, the study shows how cities can maximize environmental and social value based on environmental data, while maintaining privacy, sustainability, and equity by design. Full article

Thick cloud removal is a critical preprocessing step for multitemporal remote sensing images (MTRSIs), as it directly determines the reliability of downstream analysis and applications. In MTRSIs, the same geographic region is observed at different times, and the underlying edge structures often remain physically consistent across temporal observations. Leveraging this intrinsic property, we introduce a Sobel-consistent term that explicitly enforces temporal consistency of edge-related features, thereby improving the reconstruction of fine structures and textures in cloud-obscured regions. Building on this insight, we propose a novel thick cloud removal model that integrates Sobel-based edge consistency with subspace-based spatiospectral low-rank tensor regularization. In this model, intrinsic images derived from subspace representation are organized into a fourth-order tensor, and low-rank constraints are applied to jointly capture the spatial, spectral, and temporal correlations inherent in MTRSIs. To efficiently solve the resulting optimization problem, we introduce an algorithm based on proximal alternating minimization. Experiments on both simulated and real-world MTRSI datasets demonstrate that the proposed method achieves superior reconstruction accuracy and visual fidelity, validating the physical interpretability and effectiveness of the approach. Full article

The spatial and temporal conflicts within terminal maneuvering areas, particularly in multi-airport systems, are growing increasingly complex. Traditional independent processing methods face inherent limitations when dealing with multi-source uncertainties, dynamic weather conditions, and high-density operations. This paper proposes MSTAGNN-MARL that systematically integrates the resolution of spatial conflicts and temporal scheduling issues. This framework is based on four crucial innovations: First, a strategic-tactical-execution hierarchical architecture is constructed that integrates multi-criteria decision optimization with graph neural network-based multi-agent reinforcement learning. Second, an uncertainty perception mechanism is designed that explicitly encodes conflict features as dynamic edge attributes in social graphs, incorporating a real-time dynamic weather model and a Gaussian noise-based perception uncertainty model. Third, develop a compliance automated system for behavior cloning that learns the decision preferences of controllers to achieve human–machine collaboration and provide transparent visualization. Fourth, a robustness assurance mechanism for abnormal scenarios is constructed, employing behavior tree-driven emergency strategies to handle unexpected situations. Experiments demonstrate that the proposed method achieves an 89.3% conflict resolution rate, reduces average delays by 6 min compared to existing methods, and exhibits robust performance under varying traffic densities and dynamic weather conditions. Ablation experiments validate the effectiveness of the four innovations. This framework provides a new research paradigm for scheduling and decision-making in Intelligent Transportation Systems (ITS). Full article

Land subsidence poses a persistent challenge to Tianjin, a major coastal city in China, with implications for urban infrastructure and sustainable development. This study examines the spatiotemporal evolution of ground subsidence in Tianjin from 2003 to 2024 using multi-source SAR observations from Envisat ASAR (C-band), ALOS PALSAR (L-band), and Sentinel-1 (C-band). Surface deformation was derived using SBAS-InSAR with atmospheric phase correction. Due to limitations in data availability, SAR observations are temporally discontinuous; therefore, the long-term subsidence evolution was reconstructed by integrating multi-sensor deformation rates through a model-based time-series fitting approach. The results show pronounced subsidence during 2003–2010 in inland districts such as Wuqing, Beichen, Jinnan, and Jinghai, with maximum rates exceeding 50 mm/yr. After 2017, regional subsidence rates generally declined, while localized deformation became increasingly concentrated in coastal reclamation areas of the Binhai New Area, particularly around Dongjiang Port and Fuzhuang. Spatial and temporal patterns of subsidence exhibit clear correspondence with changes in groundwater use intensity and phases of urban construction and land reclamation. These observations suggest a transition in dominant subsidence controls over time. The results provide a long-term observational perspective on subsidence evolution in Tianjin and offer a geospatial basis for land-use planning and infrastructure risk assessment in coastal cities. Full article

This study investigates the multi-locality and multi-temporal characteristics of mobility destinations in Zanjan, Iran, throughout a typical day. Existing approaches often overlook critical geographical concepts, including the influence of multiple motivational factors on destination choice behavior, the clustering of destinations, and the spatiotemporal dynamics of preferred destinations. To address these gaps, Agent-Based Modeling (ABM) was employed to simulate individual daily flows to preferred destinations. An integrated pattern recognition approach combining machine learning clustering (k-means), hotspot analysis, and 3D mapping was utilized to facilitate visual analytics of individual destination choices, with special emphasis on applications for transportation planning. Four optimal destination clusters were identified, with hotspot analysis revealing a concentration of preferred destinations in Cluster 1, located within the Central Business District (CBD), suggesting a monocentric spatial structure. Temporal analysis demonstrated that destination clusters exhibit dynamic spatial and temporal changes over the course of the day. These findings provide new insights into managing travel behavior and offer practical implications for urban planning and transportation policy regarding individuals’ daily movement strategies. Full article

Rolling bearings are crucial components in CNC machine tool spindles, and their health condition directly affects machining precision and operational reliability. To address the significant challenges of bearing fault diagnosis in industrial environments, this paper proposes an adaptive shapelet-based deep learning model for bearing fault diagnosis. The proposed model integrates three key components: (1) an adaptive multi-scale shapelet extraction module for discriminative pattern learning, (2) a gated parallel CNN with depthwise separable convolutions for multi-scale spatial feature extraction, (3) an enhanced bidirectional long short-term memory network with residual connections for temporal dependency modeling. A composite loss function combining cross-entropy, supervised contrastive learning, and multi-scale consistency regularization is employed for training. To simulate real-world industrial noise conditions, Gaussian, uniform, and impulse noise were injected into the signals. Experiments conducted on the CWRU and IMS datasets demonstrate that, compared with state-of-the-art methods, the proposed approach achieves stronger noise robustness, higher fault classification accuracy, and more stable performance under severe noise contamination. Full article

Predictive maintenance (PdM) is a strategic enabler of healthcare digitalization, yet its deployment remains constrained by methodological weaknesses in model evaluation. Biomedical maintenance data, structured around equipment life cycles and repeated interventions, violate the independence and stationarity assumptions of conventional random cross-validation. This work presents an empirical analysis of internal validation protocol design using a real-world, multi-hospital dataset comprising 3403 maintenance interventions. Three classification models (logistic regression, random forest, histogram-based gradient boosting) are evaluated under four validation schemes: random K-fold, equipment-grouped K-fold, temporal holdout, and roll-forward validation. The results reveal a consistent decrease in apparent predictive performance as validation constraints are progressively strengthened. Random cross-validation overestimates AUROC by approximately 0.03–0.06 compared with temporally constrained protocols. Under deployment-aligned temporal validation, model performance stabilizes at an AUROC of approximately 0.83–0.84. Equipment-grouped and temporal validation effectively mitigate structural bias and yield more stable and interpretable models. These findings highlight the critical role of validation protocol choice in the credible assessment of predictive maintenance models and provide practical guidance for the deployment of PdM systems based on real-world data in resource-limited healthcare environments. The analysis is limited to public hospitals within a single national context and relies on a class-balanced experimental subset, which may affect the direct transferability of absolute performance estimates to other healthcare systems or operational settings. Full article