Search Results (2,866)

Accurate and timely precipitation forecasting is critical for climate risk management, agriculture, and hydrological regulation. However, this task remains challenging due to the dynamic evolution of atmospheric systems, heterogeneous environmental factors, and frequent missing data in multi-source observations. To address these issues, we propose DAHG, a novel long-term precipitation forecasting framework based on dynamic augmented heterogeneous graphs with reinforced graph generation, contrastive representation learning, and long short-term memory (LSTM) networks. Specifically, DAHG constructs a temporal heterogeneous graph to model the complex interactions among multiple meteorological variables (e.g., precipitation, humidity, wind) and remote sensing indicators (e.g., NDVI). The forecasting task is formulated as a dynamic spatiotemporal regression problem, where predicting future precipitation values corresponds to inferring attributes of target nodes in the evolving graph sequence. To handle missing data, we present a reinforced dynamic graph generation module that leverages reinforcement learning to complete incomplete graph sequences, enhancing the consistency of long-range forecasting. Additionally, a self-supervised contrastive learning strategy is employed to extract robust representations of multi-view graph snapshots (i.e., temporally adjacent frames and stochastically augmented graph views). Finally, DAHG integrates temporal dependency through long short-term memory (LSTM) networks to capture the evolving precipitation patterns and outputs future precipitation estimations. Experimental evaluations on multiple real-world meteorological datasets show that DAHG reduces MAE by % and improves R² by .02 over state-of-the-art baselines (p < 0.01), confirming significant gains in accuracy and robustness, particularly in scenarios with partially missing observations (e.g., due to sensor outages or cloud-covered satellite readings). Full article

The Retrieval-Augmented Generation (RAG) framework shows great potential in terms of improving the reasoning and knowledge utilization capabilities of language models. However, most existing RAG systems heavily rely on large language models (LLMs) and suffer severe performance degradation when using small language models (SLMs), which limits their efficiency and deployment in resource-constrained environments. To address this challenge, we propose Retrieval-Adaptive-Planning RAG (RAP-RAG), a lightweight and high-efficiency RAG framework with adaptive retrieval task planning that is compatible with both SLMs and LLMs simultaneously. RAP-RAG is built on three key components: (1) a heterogeneous weighted graph index that integrates semantic similarity and structural connectivity; (2) a set of retrieval methods that balance efficiency and reasoning power; and (3) an adaptive planner that dynamically selects appropriate strategies based on query features. Experiments on the LiHua-World, MultiHop-RAG, and Hybrid-SQuAD datasets show that RAP-RAG consistently outperforms representative baseline models such as GraphRAG, LightRAG, and MiniRAG. Compared to lightweight baselines, RAP-RAG achieves 3–5% accuracy improvement while maintaining high efficiency and maintains comparable efficiency in both small and large model settings. In addition, our proposed framework reduces storage size by 15% compared to mainstream frameworks. Component analysis further confirms the necessity of weighted graphs and adaptive programming for robust retrieval under multi-hop reasoning and heterogeneous query conditions. These results demonstrate that RAP-RAG is a practical and efficient framework for retrieval-enhanced generation, suitable for large-scale and resource-constrained scenarios. Full article

Aging involves a progressive decline in physiological functions, increasing vulnerability to disorders, functional decline, and disability. Emphasizing resilience and intrinsic capacity offers a proactive framework for promoting successful aging and quality of life. This narrative review selected significant articles published within the last five years on resilience, especially physical resilience, and intrinsic capacity, along with earlier relevant works. Articles were primarily searched in English using PubMed, Google Scholar, and Scopus, employing relevant terms with Boolean operators (“AND”, “OR”). Inclusion criteria included peer-reviewed conceptual, observational, and interventional studies on resilience and/or intrinsic capacity in adults over 60, published between 2020 and 2025, highlighting how the inclusion of geriatric evaluation improves health outcomes. Studies not focused on older adults, outside the date range, or non-English articles were excluded. Out of 145 references, 43 articles met the inclusion criteria. ResEvidence suggests that resilience (a dynamic response to stressors) and intrinsic capacity (baseline reserves across locomotion, vitality, cognition, sensory, and psychological domains) are interconnected, with resilience being associated with better health outcomes, a lower prevalence of chronic diseases, and greater mental health stability. Incorporating assessments of resilience and intrinsic capacity into clinical workflows could support targeted interventions; routine screening may guide personalized exercise and psychosocial plans to help prevent functional decline. Utilizing brief, validated tools (e.g., Short Physical Performance Battery, handgrip strength, Geriatric Depression Scale, brief cognitive tests, and resilience scales) can inform interventions such as physical activity, nutritional support, deprescribing, and psychosocial engagement, which may support healthier aging trajectories. Full article

The rapid advancement of 5G/6G networks and the Internet of Things has rendered mobile traffic patterns increasingly complex and dynamic, posing significant challenges to achieving precise cell-level traffic forecasting. Traditional deep learning models, such as LSTM and CNN, rely heavily on substantial datasets. When confronted with new base stations or scenarios with sparse data, they often exhibit insufficient generalisation capabilities due to overfitting and poor adaptability to heterogeneous traffic patterns. To overcome these limitations, this paper proposes a meta-learning framework—GMM-MCM-NF. This framework employs a Gaussian mixture model as a probabilistic meta-learner to capture the latent structure of traffic tasks in the frequency domain. It further introduces a multi-component synthesis mechanism for robust weight initialisation and a negative feedback mechanism for dynamic model correction, thereby significantly enhancing model performance in scenarios with small samples and non-stationary conditions. Extensive experiments on the Telecom Italia Milan dataset demonstrate that GMM-MCM-NF outperforms traditional methods and meta-learning baseline models in prediction accuracy, convergence speed, and generalisation capability. This framework exhibits substantial potential in practical applications such as energy-efficient base station management and resilient resource allocation, contributing to the advancement of mobile networks towards more sustainable and scalable operations. Full article

Clustering of aircraft trajectories in terminal airspace is essential for procedure evaluation, flow monitoring, and anomaly detection, yet it is challenged by dense traffic, irregular sampling, and diverse maneuvering behaviors. This study proposes a unified framework that integrates dynamics-aware segmentation, Transformer–Variational Autoencoder (Transformer–VAE)-based representation learning, and density-aware clustering with joint optimization. A dynamic-feature Minimum Description Length (DFE-MDL) algorithm is introduced to preserve maneuver boundaries and reduce reconstruction errors, while the Transformer–VAE encoder captures nonlinear spatiotemporal dependencies and generates compact latent embeddings. Clusters are initialized using Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN) and further refined through Kullback–Leibler (KL) divergence minimization to improve consistency and separability. Experiments on large-scale ADS-B data from Guangzhou Baiyun International Airport, comprising over 27,000 trajectories, demonstrate that the framework outperforms conventional geometric and deep learning baselines. Results show higher reconstruction fidelity, clearer cluster separation, and reduced computation time, enabling interpretable flow structures that reflect operational practices. Overall, the framework provides a data-driven and scalable approach for terminal-area trajectory analysis, offering practical value for STAR/SID compliance monitoring, anomaly detection, and airspace management. Full article

Welding is a critical joining process in modern manufacturing, with defects contributing to 50–80% of structural failures. Traditional inspection methods are often inefficient, subjective, and inconsistent. To address challenges in weld defect detection—including scale variation, morphological complexity, low contrast, and sample imbalance—this paper proposes ADFE-DET, an adaptive dynamic feature enhancement algorithm. The approach introduces three core innovations: the Dynamic Selection Cross-stage Cascade Feature Block (DSCFBlock) captures fine texture features via edge-preserving dynamic selection attention; the Adaptive Hierarchical Spatial Feature Pyramid Network (AHSFPN) achieves adaptive multi-scale feature integration through directional channel attention and hierarchical fusion; and the Multi-Directional Differential Lightweight Head (MDDLH) enables precise defect localization via multi-directional differential convolution while maintaining a lightweight architecture. Experiments on three public datasets (Weld-DET, NEU-DET, PKU-Market-PCB) show that ADFE-DET improves mAP50 by 2.16%, 2.73%, and 1.81%, respectively, over baseline YOLOv11n, while reducing parameters by 34.1%, computational complexity by 4.6%, and achieving 105 FPS inference speed. The results demonstrate that ADFE-DET provides an effective and practical solution for intelligent industrial weld quality inspection. Full article

Park-level integrated energy systems (IESs) are increasingly challenged by rapid electrification and higher penetration of renewable energy, which exacerbate source–load imbalances and scheduling uncertainty. This study proposes a unified framework that couples high-accuracy cooling and heating load forecasting with day-ahead coordinated optimization for an office park in Tianjin. The forecasting module employs correlation-based feature selection and variational mode decomposition (VMD) to capture multi-scale dynamics, and a sparrow search algorithm (SSA)-driven long short-term memory network (LSTM), with hyperparameters globally tuned by root mean square error to improve generalization and robustness. The scheduling module performs day-ahead optimization across source, grid, load, and storage to minimize either (i) the standard deviation (SD) of purchased power to reduce grid impact, or (ii) the total operating cost (OC) to achieve economic performance. On the case dataset, the proposed method achieves mean absolute percentage errors (MAPEs) of 8.32% for cooling and 5.80% for heating, outperforming several baselines and validating the benefits of multi-scale decomposition combined with intelligent hyperparameter searching. Embedding forecasts into day-ahead scheduling substantially reduces external purchases: on representative days, forecast-driven optimization lowers the SD of purchased electricity from 29.6% to 88.1% across heating and cooling seasons; seasonally, OCs decrease from 6.4% to 15.1% in heating and 3.8% to 11.6% in cooling. Overall, the framework enhances grid friendliness, peak–valley coordination, and the stability, flexibility, and low-carbon economics of park-level IESs. Full article

Background: This study examined the impact of amnestic mild cognitive impairment (aMCI) on dynamic changes in cerebrocortical oxygen saturation (ScO₂) and O₂ extraction during acute, moderately intense, normobaric hypoxia and reoxygenation in elderly adults (71 ± 6 years old). Methods: Thirty-two aMCI and thirty-five control subjects participated. Inspired and expired fractions of O₂ and CO₂ (mass spectrometry), arterial O₂ saturation (SaO₂) and prefrontal ScO₂ (near-infrared spectroscopy), heart rate, tidal volume and breathing frequency were monitored while subjects breathed hypoxic air (fractional inspired O₂ 0.10) for 3–5 min (aMCI: 4.5 ± 0.7 min; control: 4.5 ± 0.6 min) and recovered on room air. Values at the pre-hypoxia baseline, the first and last min of hypoxia and the first min of recovery were compared within and between groups using two-factor ANOVA. Results: Despite a similar baseline SaO₂ in aMCI (97.2 ± 1.6%) and control (97.3 ± 1.3%) subjects, prefrontal ScO₂ was lower (p < 0.05) in the aMCI subjects in both the left (67.0 ± 1.7% vs. 69.6 ± 4.5%) and right (66.8 ± 4.6% vs. 69.4 ± 4.1%) hemispheres. Hypoxia similarly decreased SaO₂ and ScO₂ in both groups (last min hypoxia, aMCI vs. control subjects: SaO₂ 76.6 ± 5.3% vs. 77.4 ± 6.1%, left prefrontal ScO₂ 54.0 ± 4.9% vs. 55.2 ± 6.4%, right prefrontal ScO₂ 56.0 ± 4.3% vs. 58.2 ± 4.4%). Upon the resumption of room-air breathing, ScO₂ recovered at similar rates in aMCI and control subjects. Conclusions: Although it produced a greater deoxygenation in the left vs. the right prefrontal cortex, acute, normobaric, moderate hypoxia was well tolerated by elderly adults, even those with aMCI. Dynamic changes in cerebral oxygenation during hypoxia and recovery were unaltered by aMCI. Brief, moderate hypoxia does not impose more intense cerebrocortical oxygen depletion in elderly adults with aMCI, despite pre-hypoxic cerebrocortical oxygenation below that of their non-MCI counterparts. Full article

Reliable forecasting of satellite telemetry is critical for spacecraft health management and mission planning. However, conventional data-driven methods often struggle to effectively capture both the long-term dependencies and local dynamics inherent in telemetry data. To tackle these challenges, we introduce FFT1D-Dual, a hybrid Transformer framework that unifies frequency-domain and temporal-domain modeling, effectively capturing both long-term dependencies and local features in telemetry data to enable more accurate satellite forecasting. The encoder replaces computationally expensive self-attention with a novel Dual-Path Mixer encoder that combines one-dimensional Fast Fourier Transform (FFT) and temporal convolutions, adaptively fused via a learnable channel-wise gating mechanism. A standard attention-based decoder with dynamic positional encodings preserves temporal reasoning capability. Experiments on real-world satellite telemetry datasets demonstrate that FFT1D-Dual mostly outperforms baselines across both short- and long-term horizons across three representative telemetry variables while maintaining consistently lower error growth in long-horizon predictions. Ablation studies confirm that the combination of frequency-domain modeling and dual-path fusion jointly contributes to these gains. The proposed approach provides an efficient solution for accurate long-term forecasting in complex satellite telemetry scenarios. Full article

This paper proposes a hybrid deep learning model for robust and interpretable sentiment classification of Twitter data. The model integrates Bidirectional Encoder Representations from Transformers (BERT)-based contextual embeddings, a Bidirectional Long Short-Term Memory (BiLSTM) network, and a custom attention mechanism to classify tweets into four sentiment categories: Positive, Negative, Neutral, and Irrelevant. Addressing the challenges of noisy and multilingual social media content, the model incorporates a comprehensive preprocessing pipeline and data augmentation strategies including back-translation and synonym replacement. An ablation study demonstrates that combining BERT with BiLSTM improves the model’s sensitivity to sequence dependencies, while the attention mechanism enhances both classification accuracy and interpretability. Empirical results show that the proposed model outperforms BERT-only and BERT+BiLSTM baselines, achieving F1-scores (F1) above 0.94 across all sentiment classes. Attention weight visualizations further reveal the model’s ability to focus on sentiment-bearing tokens, providing transparency in decision-making. The proposed framework is well-suited for deployment in real-time sentiment monitoring systems and offers a scalable solution for multilingual and multi-class sentiment analysis in dynamic social media environments. We also include a focused characterization of the dataset via an Exploratory Data Analysis in the Methods section. Full article

In recent years, food nutrition estimation has received growing attention due to its critical role in dietary analysis and public health. Traditional nutrition assessment methods often rely on manual measurements and expert knowledge, which are time-consuming and not easily scalable. With the advancement of computer vision, RGB-based methods have been proposed, and more recently, RGB-D-based approaches have further improved performance by incorporating depth information to capture spatial cues. While these methods have shown promising results, they still face challenges in complex food scenes, such as limited ability to distinguish visually similar items with different ingredients and insufficient modeling of spatial or semantic relationships. To solve these issues, we propose an Ingredient-Guided Semantic Modeling Network (IGSMNet) for food nutrition estimation. The method introduces an ingredient-guided module that encodes ingredient information using a pre-trained language model and aligns it with visual features via cross-modal attention. At the same time, an internal semantic modeling component is designed to enhance structural understanding through dynamic positional encoding and localized attention, allowing for fine-grained relational reasoning. On the Nutrition5k dataset, our method achieves PMAE values of 12.2% for Calories, 9.4% for Mass, 19.1% for Fat, 18.3% for Carb, and 16.0% for Protein. These results demonstrate that our IGSMNet consistently outperforms existing baselines, validating its effectiveness. Full article

Simultaneous Localization and Mapping (SLAM) utilizes sensor data to concurrently construct environmental maps and estimate its own position, finding wide application in scenarios like robotic navigation and augmented reality. SLAM systems based on 3D Gaussian Splatting (3DGS) have garnered significant attention due to their real-time, high-fidelity rendering capabilities. However, in real-world environments containing dynamic objects, existing 3DGS-SLAM methods often suffer from mapping errors and tracking drift due to dynamic interference. To address this challenge, this paper proposes BDGS-SLAM—a Bayesian Dynamic Gaussian Splatting SLAM framework specifically designed for dynamic environments. During the tracking phase, the system integrates semantic detection results from YOLOv5 to build a dynamic prior probability model based on Bayesian filtering, enabling accurate identification of dynamic Gaussians. In the mapping phase, a multi-view probabilistic update mechanism is employed, which aggregates historical observation information from co-visible keyframes. By introducing an exponential decay factor to dynamically adjust weights, this mechanism effectively restores static Gaussians that were mistakenly culled. Furthermore, an adaptive dynamic Gaussian optimization strategy is proposed. This strategy applies penalizing constraints to suppress the negative impact of dynamic Gaussians on rendering while avoiding the erroneous removal of static Gaussians and ensuring the integrity of critical scene information. Experimental results demonstrate that, compared to baseline methods, BDGS-SLAM achieves comparable tracking accuracy while generating fewer artifacts in rendered results and realizing higher-fidelity scene reconstruction. Full article

Conventional power load forecasting frameworks face limitations in dynamic spatial topology capture and long-term dependency modeling. To address these issues, this study proposes a hybrid GAT-CNN-LSTM architecture for enhanced short-term power load forecasting. The model integrates three core components synergistically: Graph Attention Network (GAT) dynamically captures spatial correlations via adaptive node weighting, resolving static topology constraints; a CNN-LSTM module extracts multi-scale temporal features—convolutional kernels decompose load fluctuations, while bidirectional LSTM layers model long-term trends; and a gated fusion mechanism adaptively weights and fuses spatio-temporal features, suppressing noise and enhancing sensitivity to critical load periods. Experimental validations on multi-city datasets show significant improvements: the model outperforms baseline models by a notable margin in error reduction, exhibits stronger robustness under extreme weather, and maintains superior stability in multi-step forecasting. This study concludes that the hybrid model balances spatial topological analysis and temporal trend modeling, providing higher accuracy and adaptability for STLF in complex power grid environments. Full article

Dynamic and efficient resource allocation is critical for Software-Defined Networking (SDN) enabled sixth-generation (6G) networks to ensure adaptability and optimized utilization of network resources. This paper proposes a reinforcement learning (RL)-based framework that integrates an actor–critic model with a modular SDN interface for fine-grained, queue-level bandwidth scheduling. The framework further incorporates a stochastic traffic generator for training and a virtualized multi-slice platform testbed for a realistic beyond-5G/6G evaluation. Experimental results show that the proposed RL model significantly outperforms a baseline forecasting model: it converges faster, showing notable improvements after 240 training epochs, achieves higher cumulative rewards, and reduces packet drops under dynamic traffic conditions. Moreover, the RL-based scheduling mechanism exhibits improved adaptability to traffic fluctuations, although both approaches face challenges under node outage conditions. These findings confirm that queue-level reinforcement learning enhances responsiveness and reliability in 6G networks, while also highlighting open challenges in fault-tolerant scheduling. Full article

Background/Objectives: It has become a major direction of research in affective computing to explore the brain-information-processing mechanisms based on physiological signals such as electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS). However, existing research has mostly focused on feature- and decision-level fusion, with little investigation into the causal relationship between these two modalities. Methods: In this paper, we propose a novel emotion recognition framework for the simultaneous acquisition of EEG and fNIRS signals. This framework integrates the Granger causality (GC) method and a modality–frequency attention mechanism within a convolutional neural network backbone (MFA-CNN). First, we employed GC to quantify the causal relationships between the EEG and fNIRS signals. This revealed emotional-processing mechanisms from the perspectives of neuro-electrical activity and hemodynamic interactions. Then, we designed a 1D2D-CNN framework that fuses temporal and spatial representations and introduced the MFA module to dynamically allocate weights across modalities and frequency bands. Results: Experimental results demonstrated that the proposed method outperforms strong baselines under both single-modal and multi-modal conditions, showing the effectiveness of causal features in emotion recognition. Conclusions: These findings indicate that combining GC-based cross-modal causal features with modality–frequency attention improves EEG–fNIRS-based emotion recognition and provides a more physiologically interpretable view of emotion-related brain activity. Full article