Search Results (548)

Modern fire alarm systems are essential for public safety, yet they often fail to exploit the wealth of historical alarm data and the complex spatiotemporal dependencies inherent in urban environments. Graph Neural Networks (GNNs) are currently among the most popular methods for handling complex spatiotemporal dependencies. While a range of dynamic GNN approaches have been proposed, many existing GNN-based predictors still rely on a static topology, which limits their ability to fully capture the evolving nature of risk propagation. Furthermore, even among dynamic graph methods, most focus on temporal link prediction or social interaction modeling, with limited exploration in safety-critical applications such as fire alarm prediction. DeaGAT dynamically updates inter-building edge weights through an attention mechanism, enabling the graph structure to evolve in response to shifting risk patterns. A margin-based contrastive learning objective further enhances the quality of node embeddings by distinguishing subtle differences in risk states. In addition, DeaGAT jointly models static building attributes and dynamic alarm sequences, effectively integrating long-term semantic context with short-term temporal dynamics. Extensive experiments on real-world datasets, including comparisons with state-of-the-art baselines and comprehensive ablation studies, demonstrate that DeaGAT achieves superior accuracy and F1-score, validating the effectiveness of dynamic graph updating and contrastive learning in enhancing proactive fire early-warning capabilities. Full article

Forecasting pedestrian congestion in urban back streets is challenging due to “shadow areas” where CCTV coverage is absent and trajectory data cannot be directly collected. To address these gaps, we propose the Peak-aware Graph-attention Temporal Fusion Transformer (PGTFT), a lightweight hybrid model that extends the Temporal Fusion Transformer by integrating a non-parametric attention-based Graph Convolutional Network, a peak-aware Gated Residual Network, and a Peak-weighted Quantile Loss. The model leverages both physical connectivity and functional similarity between roads through a fused adjacency matrix, while enhancing sensitivity to high-congestion events. Using real-world trajectory data from 38 CCTVs in Anyang, South Korea, experiments show that PGTFT outperforms LSTM, TFT, and GCN-TFT across different sparsity settings. Under sparse 5 m neighbor conditions, the model achieved the lowest MAE (0.059) and RMSE (0.102), while under denser 30 m settings it maintained superior accuracy with standard quantile loss. Importantly, PGTFT requires only 1.54 million parameters—about half the size of conventional Transformer–GCN hybrids—while delivering equal or better predictive performance. These results demonstrate that PGTFT is both parameter-efficient and robust, offering strong potential for deployment in smart city monitoring, emergency response, and transportation planning, as well as a practical approach to addressing data sparsity in urban sensing systems. Full article

As one of the primary contributors to carbon emissions in China, the transportation sector plays a pivotal role in achieving green and low-carbon development. Considering the spatio-temporal dependency characteristics of transportation carbon emissions driven by economic interactions and population mobility among provinces, this study proposes a predictive framework for transportation carbon emissions based on a spatio-temporal attention mechanism from the perspective of multi-province spatio-temporal synergy. First, the study conducts transportation carbon emission accounting by considering both transportation fuel consumption and electricity usage, followed by feature selection using an enhanced STIRPAT model. Second, it integrates the spatio-temporal attention mechanism with graph convolutional neural networks to construct a multi-province transportation carbon emission collaborative prediction model. Comparative experiments highlight the superior performance of deep learning methods and spatio-temporal correlation modeling in multi-province transportation carbon emission collaborative prediction. Finally, three future development scenarios are designed to analyze the evolution paths of transportation carbon emissions. The results indicate that technological innovation can significantly improve the efficiency of transportation emission reduction. Moreover, given that the eastern region and the central and western regions are at distinct stages of development, it is essential to develop differentiated emission reduction strategies tailored to local conditions to facilitate a green and low-carbon transformation in the transportation sector. Full article

Advances in cardiac regenerative medicine increasingly rely on integrating artificial intelligence with spatial multi-omics technologies to decipher intricate cellular dynamics in cardiomyocyte differentiation. This systematic review, synthetising insights from 88 PRISMA selected studies spanning 2015–2025, explores how deep learning architectures, specifically Graph Neural Networks (GNNs) and Recurrent Neural Networks (RNNs), synergise with multi-modal single-cell datasets, spatially resolved transcriptomics, and epigenomics to advance cardiac biology. Innovations in spatial omics technologies have revolutionised our understanding of the organisation of cardiac tissue, revealing novel cellular communities and metabolic landscapes that underlie cardiovascular health and disease. By synthesising cutting-edge methodologies and technical innovations across these 88 studies, this review establishes the foundation for AI-enabled cardiac regeneration, potentially accelerating the clinical adoption of regenerative treatments through improved therapeutic prediction models and mechanistic understanding. We examine deep learning implementations in spatiotemporal genomics, spatial multi-omics applications in cardiac tissues, cardiomyocyte differentiation challenges, and predictive modelling innovations that collectively advance precision cardiology and next-generation regenerative strategies. Full article

Traffic flow prediction is a prominent research area in intelligent transportation systems, significantly contributing to urban traffic management and control. Existing methods or models for traffic flow prediction predominantly rely on a fixed-graph structure to capture spatial correlations within a road network. However, the fixed-graph structure can restrict the representation of spatial information due to varying conditions such as time and road changes. Drawing inspiration from the attention mechanism, a new prediction model based on the mixed-graph neural network is proposed to dynamically capture the spatial traffic flow correlations. This model uses graph convolution and attention networks to adapt to complex and changeable traffic and other conditions by learning the static and dynamic spatial traffic flow characteristics, respectively. Then, their outputs are fused by the gating mechanism to learn the spatial traffic flow correlations. The Transformer encoder layer is subsequently employed to model the learned spatial characteristics and capture the temporal traffic flow correlations. Evaluated on five real traffic flow datasets, the proposed model outperforms the state-of-the-art models in prediction accuracy. Furthermore, ablation experiments demonstrate the strong performance of the proposed model in long-term traffic flow prediction. Full article

Accurate traffic forecasting underpins intelligent transportation systems. We present PTSTG, a compact spatio-temporal forecaster that couples a patch-based Transformer encoder with a data-driven adaptive adjacency and lightweight node graph blocks. The temporal module tokenizes multivariate series into fixed-length patches to capture short- and long-range patterns in a single pass, while the graph module refines node embeddings via learned inter-node aggregation. A horizon-specific head emits all steps simultaneously. On standard benchmarks (METR-LA, PEMS-BAY) and the LargeST (SD) split with horizons $\{3, 6, 12\}\to \{15, 30, 60\}$ minutes, PTSTG delivers competitive point-estimate results relative to recent temporal graph models. On METR-LA/PEMS-BAY, it remains close to strong baselines (e.g., DCRNN) without surpassing them; on LargeST, it attains favorable average RMSE/MAE while trailing the strongest hybrids on some horizons. The design preserves a compact footprint and single-pass, multi-horizon inference, and offers clear capacity-driven headroom without architectural changes. Full article

Anomaly detection in multivariate time series (MTS) remains challenging due to the presence of complex and dynamic spatiotemporal dependencies. To address this, we propose the Dynamic Spatiotemporal Graph Mixed Network (DTS-MixNet), which takes a sliding window data as input to predict the next time series data and determine its state. The model comprises five blocks. The Temporal Graph Structure Learner (TGSL) generates the attention-weighted graphs via two types of neighbor relationships and the multi-head-attention-based neighbor degrees. Then, the Cross-Temporal Dynamic Encoder (CTDE) aggregates the cross-temporal dependencies from attention-weighted graphs, and encodes them into a proxy multivariate sequence (PMS), which is fed into the proposed Cross-Variable Dynamic Encoder (CVDE). Subsequently, the CVDE captures the sensors-among spatial relationship through multiple local spatial graphs and a global spatial graph, and produces a spatial graph sequence (SGS). Finally, the Spatiotemporal Mixer (TSM) mixes PMS and SGS to build a spatiotemporal mixed sequence (TSMS) for downstream tasks, e.g., classification or prediction. We evaluate on two industrial control datasets and discuss applicability to non-industrial multivariate time series. The experimental results on benchmark datasets show that the proposed DTS-MixNet is encouraging. Full article

Dynamic path generation in complex transportation networks is essential for intelligent transportation systems. Traditional methods, such as shortest path algorithms or heuristic-based models, often fail to capture real-world travel behaviors due to their reliance on simplified assumptions and limited ability to handle long-range dependencies or non-linear patterns. To address these limitations, we propose PathGen-LLM, a large language model (LLM) designed to learn spatial–temporal patterns from historical paths without requiring handcrafted features or graph-specific architectures. Exploiting the structural similarity between path sequences and natural language, PathGen-LLM converts spatiotemporal trajectories into text-formatted token sequences by encoding node IDs and timestamps. This enables the model to learn global dependencies and semantic relationships through self-supervised pretraining. The model integrates a hierarchical Transformer architecture with dynamic constraint decoding, which synchronizes spatial node transitions with temporal timestamps to ensure physically valid paths in large-scale road networks. Experimental results on real-world urban datasets demonstrate that PathGen-LLM outperforms baseline methods, particularly in long-distance path generation. By bridging sequence modeling and complex network analysis, PathGen-LLM offers a novel framework for intelligent transportation systems, highlighting the potential of LLMs to address challenges in large-scale, real-time network tasks. Full article

Socialized services for rural characteristic industries are becoming a key support for promoting rural industries’ transformation and upgrading. They are permeating the development process of modern agricultural service technologies, achieving significant progress in specialized fields such as mechanized operations and plant-protection services. However, challenges remain, including low efficiency in matching service resources and limited spatiotemporal coordination capabilities. With the deep integration of spatiotemporal information technology and knowledge graph technology, the enormous potential of semantic-level feature spatial representation in intelligent scheduling of service resources has been fully demonstrated, providing a new technical pathway to solve the above problem. This paper systematically analyzes the technological evolution trends of socialized services for rural characteristic industries and proposes a collaborative scheduling framework based on semantic feature space and spatiotemporal maps for characteristic industry service resources. At the technical architecture level, the paper aims to construct a spatiotemporal graph model integrating geographic knowledge graphs and temporal tree technology to achieve semantic-level feature matching between service demand and supply. Regarding implementation pathways, the model significantly improves the spatiotemporal allocation efficiency of service resources through cloud service platforms that integrate spatial semantic matching algorithms and dynamic optimization technologies. This paper conducts in-depth discussions and analyses on technical details such as agricultural semantic feature extraction, dynamic updates of rural service resources, and the collaboration of semantic matching and spatio-temporal matching of supply and demand relationships. It also presents relevant implementation methods to enhance technical integrity and logic, which is conducive to the engineering implementation of the proposed methods. The effectiveness of the proposed collaborative scheduling framework for service resources is proved by the synthesis of principal analysis, logical deduction and case comparison. We have proposed a practical “three-step” implementation path conducive to realizing the proposed method. Regarding application paradigms, this technical system will promote the transformation of rural industry services from traditional mechanical operations to an intelligent service model of “demand perception–intelligent matching–precise scheduling”. In the field of socialized services for rural characteristic industries, it is suggested that relevant institutions promote this technical framework and pay attention to the development trends of new technologies such as knowledge services, spatio-temporal services, the Internet of Things, and unmanned farms so as to promote the sustainable development of rural characteristic industries. Full article

Providing age-friendly metro service substantially enhances the elderly’s mobility and well-being. Despite recent progress in user profiling and mobility prediction, the prediction of the elderly’s metro travel patterns remains limited. To fill this gap, this study proposes a framework integrating user profiling and knowledge graph embedding to predict the elderly’s activity types at metro trip destinations, utilizing 180,143 smart card records and 885,072 points of interest (POI) records from Chongqing, China in 2019. First, an elderly metro travel profile (EMTP) tag system is developed to capture the elderly’s spatiotemporal metro travel behaviors and preferences. Subsequently, an elderly metro travel knowledge graph (EMTKG) is constructed to support semantic reasoning, transforming the activity types prediction problem into a knowledge graph completion problem. To solve the completion problem, the Temporal and Non-Temporal ComplEx (TNTComplEx) model is introduced to embed entities and relations into a complex vector space and distinguish between time-sensitive and time-insensitive behavioral patterns. Fact plausibility within the graph is evaluated by a scoring function. Numerical experiments validate that the proposed model outperforms the best-performing baselines by 13.37% higher Accuracy@1 and 52.40% faster training time per epoch, and ablation studies further confirm component effectiveness. This study provides an enlightening and scalable approach for enhancing age-friendly metro system service. Full article

Background: The emission of air pollutants into the atmosphere is a global issue as it contributes to global warming and climate-related issues. Human activities like the burning of fossil fuel influence changes in weather patterns—resulting in issues such as a rise in sea levels, among other things. Identifying road network routes within Northern Cape Province in South Africa that are less exposed to air pollutants like carbon monoxide is the issue this study seeks to address. Methods: The method used for our predictions is based on a graph convolutional network (GCN) and long short-term memory (LSTM). The GCN extracts geospatial characteristics, and the LSTM captures both nonlinear relationships and temporal dependencies in an air pollutant and meteorological dataset. Furthermore, an A* search strategy identifies the path from one location to another with the lowest carbon monoxide concentrations within a road network. The explainable artificial intelligence (xAI) technique is used to describe the nonlinear relationship between the target variable and features. Meteorological and air pollutant data in the form of statistical mean, minimum, and maximum values were leveraged, and a random sampling technique was utilized to fill the data gap to help train the predictive model (GCN-LSTM-A*). Results: The predictive model was evaluated with mean squared error (MSE) and root mean squared error (RMSE) values within two multi-time steps (8 and 16 h) with MSEs of 0.1648 and 0.1701, respectively. The LIME technique, which provides explanations of features, shows that Wind_speed and NO₂ and NOx concentrations decreased the predicted CO, whereas PM_2.5, PM₁₀, relative humidity, and O₃ increased the predicted CO of the route. Full article

The growing demand for real-time human motion reconstruction in Virtual Reality (VR), Augmented Reality (AR), and the Metaverse requires high accuracy with minimal hardware. This paper presents SSR-HMR, a skeleton-aware, sparse node-based method for full-body motion reconstruction from limited inputs. The approach incorporates a lightweight spatiotemporal graph convolutional module, a torso pose refinement design to mitigate orientation drift, and kinematic tree-based optimization to enhance end-effector positioning accuracy. Smooth motion transitions are achieved via a multi-scale velocity loss. Experiments demonstrate that SSR-HMR achieves high-accuracy reconstruction, with mean joint and end-effector position errors of 1.06 cm and 0.52 cm, respectively, while operating at 267 FPS on a CPU. Full article

Ultra-short-term photovoltaic (PV) cluster power prediction (PCPP) is crucial for intra-day energy dispatch. However, it faces significant challenges due to the chaotic nature of atmospheric systems and errors in meteorological forecasting. To address this, we propose a novel ultra-short-term PCPP strategy that introduces a dynamic smoothing mechanism for PV clusters. This strategy introduces a smoothing convergence function to quantify sequence fluctuations and employs dynamic clustering based on this function to identify PV stations with complementary smoothing effects. We model the similarities in fluctuation amplitude, trend correlation, and degree correlation among sub-cluster nodes using a spatiotemporal heterogeneous dynamic graph convolutional neural network (STHDGCN). Three dynamic heterogeneous graphs are constructed to represent these spatiotemporal evolutionary relationships. Furthermore, a bidirectional temporal convolutional neural network (BITCN) is integrated to capture the temporal dependencies within each sub-cluster, ultimately predicting the output of each node. Experimental results using real-world data demonstrate that the proposed method reduces the normalized root mean square error (NRMSE) and normalized mean absolute error (NMAE) by an average of 6.90% and 4.15%, respectively, while improving the coefficient of determination (R²) by 34.36%, compared to conventional cluster prediction approaches. Full article

Skeleton-based action recognition networks have widely adopted the approach of Graph Convolutional Networks (GCN) due to their superior capabilities in modeling data topology, but several key issues still require further investigation. Firstly, the graph convolutional network extracts action features by applying temporal convolution to each key point, which causes the model to ignore the temporal connections between different important points. Secondly, the local receptive field of graph convolutional networks limits their ability to capture correlations between non-adjacent joints. Motivated by the State Space Model (SSM), we propose an Action Spatio-temporal Aggregation Network, named ActionMamba. Specifically, we introduce a novel embedding module called the Action Characteristic Encoder (ACE), which enhances the coupling of temporal and spatial information in skeletal features by combining intrinsic spatio-temporal encoding with extrinsic space encoding. Additionally, we design an Action Perception Model (APM) based on Mamba and GCN. By effectively combining the excellent feature processing capabilities of GCN with the outstanding global information modeling capabilities of Mamba, APM is able to comprehend the hidden features between different joints and selectively filter information from various joints. Extensive experimental results demonstrate that ActionMamba achieves highly competitive performance on three challenging benchmark datasets: NTU-RGB+D 60, NTU-RGB+D 120, and UAV–Human. Full article

With the advancement of new power system construction, thermostatically controlled loads represented by regional air conditioning systems are being extensively integrated into the grid, leading to a surge in the number of user nodes. This large-scale integration of new loads creates challenges for the grid, as the resulting load data exhibits strong periodicity and randomness over time. These characteristics are influenced by factors like temperature and user behavior. At the same time, spatially adjacent nodes show similarities and clustering in electricity usage. This creates complex spatiotemporal coupling features. These complex spatiotemporal characteristics challenge traditional forecasting methods. Their high model complexity and numerous parameters often lead to overfitting or the curse of dimensionality, which hinders both prediction accuracy and efficiency. To address this issue, this paper proposes a load forecasting method based on spatiotemporal partitioning and collaborative cross-regional attention. First, a spatiotemporal similarity matrix is constructed using the Shape Dynamic Time Warping (ShapeDTW) algorithm and an adaptive Gaussian kernel function based on the Haversine distance. Spectral clustering combined with the Gap Statistic criterion is then applied to adaptively determine the optimal number of partitions, dividing all load nodes in the power grid into several sub-regions with homogeneous spatiotemporal characteristics. Second, for each sub-region, a local Spatiotemporal Graph Convolutional Network (STGCN) model is built. By integrating gated temporal convolution with spatial feature extraction, the model accurately captures the spatiotemporal evolution patterns within each sub-region. On this basis, a cross-regional attention mechanism is designed to dynamically learn the correlation weights among sub-regions, enabling collaborative fusion of global features. Finally, the proposed method is evaluated on a multi-node load dataset. The effectiveness of the approach is validated through comparative experiments and ablation studies (that is, by removing key components of the model to evaluate their contribution to the overall performance). Experimental results demonstrate that the proposed method achieves excellent performance in short-term load forecasting tasks across multiple nodes. Full article