Spatiotemporal Relationships Research Articles

A Village-Scale Study Regarding Landscape Evolution and Ecological Effects in a Coastal Inner Harbor

The development of inner harbors has been accompanied by the destruction of natural landscapes, which in turn has led to numerous ecological problems. However, the temporal and spatial relationships between changes in the inner harbor landscape and ecological effects are not yet clear, and there are relatively few studies at smaller scales such as villages. In this study, we investigated Xieqian Harbor in Xiangshan County, along the eastern coast of China, and then analyzed the landscape change and evolutionary characteristics of the effects of carbon storage, soil conservation, and water yield at the village scale for the years 2000, 2010, and 2020. We then used the geographically and temporally weighted regression (GTWR) model to explore the spatiotemporal relationships between landscape variables and ecological effects. The results showed that the fragmentation and diversity of landscape patches increased from 2000 to 2020 due to reclamation and aquaculture, tourism development, and harbor construction, as reflected by the edge density (ED) and the Shannon diversity index (SHDI), which increased by 11.31% and 2.82%, respectively. This change resulted in a notable reduction of 572.6 thousand tons in carbon sequestration, 853 million tons in soil conservation, and 19 million cubic meters in water yield over the past 20 years. When temporal non-stationarity and spatial heterogeneity were combined, the relationship between landscape change and ecological effects became highly intricate, with varying responses across different time periods and locations. The area-weighted mean patch shape index (AWMSI) was a key factor affecting the three ecological effects. Our research confirmed that there was significant spatiotemporal heterogeneity in the effects of different landscape variables on ecological effects in inner harbors at the village scale. Compared with larger-scale studies, the results of village-scale studies revealed more precisely the impacts of localized landscape changes on ecological effects, providing support for the sustainable management of inner harbors and providing a new approach to integrating GTWR into landscape ecological time–space analysis research.

Electric Vehicle Charging Demand Prediction Model Based on Spatiotemporal Attention Mechanism

The accurate estimation and prediction of charging demand are crucial for the planning of charging infrastructure, grid layout, and the efficient operation of charging networks. To address the shortcomings of existing methods in utilizing the spatial interdependencies among urban regions, this paper proposes a forecasting approach that integrates dynamic time warping (DTW) with a spatial–temporal attention graph convolutional neural network (ASTGCN). First, this method delves into the correlations between various regions within the target city, establishing intricate coupling relationships among them. Subsequently, the FastDTW algorithm is employed to construct an adjacency matrix, capturing the spatiotemporal correlation among different urban regions. Finally, the ASTGCN model is applied to predict the power load of each region, which can accurately capture the spatiotemporal characteristics of the power load. The experimental results indicate that the proposed model has a more powerful comprehensive ability to capture spatiotemporal relationships and improve accuracy and stability in different prediction steps.

Traffic factor dual-state network: a novel framework for spatial–temporal traffic flow prediction

Accurate traffic forecasting is of vital importance to Intelligent Transportation Systems (ITS). However, current methods often neglect the complex spatiotemporal relationships and environmental factors, thereby limiting the forecasting accuracy. In this study, urban roads are regarded as a complex system, and a traffic flow forecasting model based on a dual-state network of urban traffic factors is proposed, integrating traffic domain knowledge with data-driven approaches. A physical-virtual road network structure is constructed to capture spatiotemporal correlations, and clustering algorithms are employed to classify the dual traffic states. The model segments historical data into time intervals according to the macro and micro states and utilizes a multi-relational graph attention mechanism to learn the embeddings of the network topology. Evaluations based on real-world data demonstrate that the performance of this model is superior to that of traditional models.

Spatiotemporal Relationship Between Landscape Pattern and Ecosystem Service Connectivity in Wetland Environment: Evidence from Yellow River Delta, China

Ecosystem service connectivity (ESC) is the spatial and functional links among and within ecosystems that support unimpeded service flows, and that could play an important role in ecosystem stability enhancement and regional land planning. Understanding the relationships between landscape patterns and ESC is crucial to achieving certain sustainable development goals, but it has not yet received an adequate amount of attention. Here, we evaluated the changes and connectivity of five key types of ecosystem services from 2000 to 2020 and analyzed the correlations and spatial aggregations between the ESCs and landscape metrics in the wetlands of the Yellow River Delta, China. Various research methods, such as the InVEST model, spatial autocorrelation analysis, Spearman’s correlation, and self-organizing map, were applied. The results showed that water yield, water purification, and habitat quality showed high connectivity, but the overall ESC declined along with the restoration of the wetland area. Meanwhile, the High-High ESC cluster of water yield, water purification, and habitat quality had similar spatial distribution patterns, and both were dominated by tidal flats. Moreover, the ESC and landscape metrics showed significant correlations and spatial heterogeneity, and a potential connectivity between water yield and habitat quality was also found. These findings can assist decision-makers in developing effective ecosystem management strategies and provide a reference for future research on ecosystem service connectivity.

Spatiotemporal association between monthly PM2.5 levels and cardiorespiratory mortality in Thailand (2015–2019)

ABSTRACT This study examines the spatiotemporal relationship between PM2.5 exposure and cardiorespiratory mortality across Thailand from 2015 to 2019, addressing a critical research gap in geographical coverage. Analysis of satellite-based PM2.5 data revealed significant correlations between monthly PM2.5 levels and cardiorespiratory mortality, with stronger effects observed in the central and northern provinces. The association was most pronounced during the dry season (November to April), showing a 6% increase in mortality compared to other months. Areas with monthly PM2.5 levels of 30.1–37.5 μg/m³ and above 37.5 μg/m³ were associated with mortality increases of 3% (95% CI: 1%–5%) and 5% (95% CI: 3%–7%), respectively, relative to the overall mean, while levels below 20 μg/m³ corresponded to a 4% (95% CI: 3%–6%) reduction. These findings underscore the need for region-specific monthly PM2.5 guidelines to mitigate health risks, particularly during high-pollution periods and in vulnerable regions.

Multiplexed spatial mapping of chromatin features, transcriptome and proteins in tissues.

The phenotypic and functional states of cells are modulated by a complex interactive molecular hierarchy of multiple omics layers, involving the genome, epigenome, transcriptome, proteome and metabolome. Spatial omics approaches have enabled the study of these layers in tissue context but are often limited to one or two modalities, offering an incomplete view of cellular identity. Here we present spatial-Mux-seq, a multimodal spatial technology that allows simultaneous profiling of five different modalities: two histone modifications, chromatin accessibility, whole transcriptome and a panel of proteins at tissue scale and cellular level in a spatially resolved manner. We applied this technology to mouse embryos and mouse brains, generating detailed multimodal tissue maps that identified more cell types and states compared to unimodal data. This analysis uncovered spatiotemporal relationships among histone modifications, chromatin accessibility, gene expression and protein levels during neuron differentiation, and revealed a radial glia niche with spatially dynamic epigenetic signals. Collectively, the spatial multi-omics approach heralds a new era for characterizing tissue and cellular heterogeneity that single-modality studies alone could not reveal.

The Spatiotemporal Coupling and Synergistic Evolution of Economic Resilience and Ecological Resilience in Africa

Investigating the spatiotemporal coupling and coordinated evolution of economic and ecological resilience in Africa provides theoretical support and scientific foundation for the continent’s green and high-quality development. From the perspective of evolutionary resilience, this study constructs an evaluation model for Africa’s economic resilience and ecological resilience. Using kernel density models, namely the “economic-ecological” resilience zoning method, the coupling coordination degree model, and the Haken model, this study explores the spatiotemporal alignment, coupling, and synergistic evolution of economic and ecological resilience in Africa in a step-by-step manner. The results show that (1) the overall level of economic resilience in Africa is relatively low, with increasing regional disparities. Spatially, economic resilience exhibits a distribution pattern of “low values widely spread, high values concentrated”; the level of ecological resilience, in contrast, shows a more pronounced dispersion, with a spatial distribution of “low values concentrated, high values dispersed”; (2) based on the “economic-ecological” resilience zoning method, most African countries and regions fall into the low economic resilience category, with weak economic resilience and prominent issues related to economic instability. The seven major high economic resilience zones largely overlap with the high economic resilience-high ecological resilience areas, demonstrating good spatiotemporal alignment between economic and ecological resilience; (3) in terms of the spatiotemporal coupling relationship between economic resilience and ecological resilience, most of Africa falls into the disordered category, with an increasingly obvious polarization trend in the coupling coordination degree; (4) from the perspective of the synergistic relationship between economic resilience and ecological resilience, ecological resilience dominates the symbiotic system formed by economic resilience and ecological resilience. The development of ecological resilience and economic resilience is mutually inhibitive, with prominent contradictions between the economy and the environment. Ecological and economic resilience have formed an internal mechanism of positive feedback in the synergistic system. The regional differences in the synergistic value have expanded, while the differences within regions have narrowed, indicating an emerging trend of spatial differentiation.

Industrial multivariate time-series data anomaly detection incorporating attention mechanisms and adversarial training

ABSTRACT To address the challenges faced in industrial anomaly detection, including data sample imbalance, lack of anomaly labels, and complex spatiotemporal relationships in high-dimensional data, this paper proposes a novel multi-modal time-series anomaly detection model that combines attention mechanisms and adversarial training. In this model, the first step involves utilizing graph attention mechanisms to extract sequence correlation features from multi-modal time-series data, which are then summed with the original data to form a dual-feature-based data representation. Subsequently, a self-supervised learning approach is employed to input this data representation into a variational autoencoder’s encoding-decoding network for reconstruction. Anomaly detection is performed by analyzing the error between the input and reconstructed data. The model also employs spatiotemporal attention mechanisms and adversarial training during reconstruction to enhance feature extraction and model generalization. By comparing our proposed model to five commonly used baseline models, we demonstrate its effectiveness in detecting anomalies in scenarios involving high-dimensional data and imbalanced abnormal samples, demonstrating superior anomaly detection performance, as well as excellent performance on real industrial production and processing datasets.

Spatiotemporal variation of high-temperature events and its relation to coral bleaching in the Ryukyu Islands, Japan

Coral bleaching occurs when symbiotic dinoflagellate algae leave corals due to warming surface waters. Since the early 1980s, the number and intensity of coral bleaching events have significantly risen globally, and many coral reefs are concerned to undergo irreversible phase shifts due to global warming. In this study, we examine spatiotemporal variations and relationships of high-temperature events, high-temperature anomaly events, and coral bleaching around the Ryukyu Islands, Japan. We also explore the correlation between these occurrences and the large-scale climate variability, El Niño–Southern Oscillation and Indian Ocean Dipole. More than 99% of the high-temperature events occurred from June to October, and more than 80% occurred from July to September, whereas high-temperature anomaly events occurred all year round. Corresponding with high-temperature events, more than 10% of the data reported overall bleaching, and more than 25% reported partial bleaching from June to October. Over 40% of data reported bleaching in August, of which 50% of these reports were categorized as overall bleaching and the remainder as partial. The spatial distribution of coral bleaching also corresponded better with high-temperature events than high-temperature anomaly events. In 2016, extensive and severe coral bleaching was reported around the Okinawa, Miyako, and Yaeyama Islands, where intense high-temperature events had occurred. The central-to-eastern equatorial Pacific displayed a negative sea surface temperature anomaly, and the eastern Indian Ocean did a positive anomaly following high-temperature events near the Ryukyu Islands. These findings indicated that the high-temperature events around the Ryukyu Islands show correlation with La Niña and a negative Indian Ocean Dipole. If the cumulative temperature of high-temperature events exceeds 56 °C-days every three years in the late 2030s, then the corals around the Ryukyu Islands will suffer high mortality within 20 years.

Spatiotemporal Response Relationships Between Changes in Water Conservation Service and Landscape Pattern in Zoige Plateau, China

ABSTRACTUnderstanding the link between landscape pattern and water conservation service (WCS) is crucial for effective water resource conservation and landscape planning. However, the impact of landscape configuration on WCS remains unclear. This study explored the spatiotemporal relationships between WCS and landscape pattern in the Zoige Plateau (ZP), a vital waterhead of the yellow river, from 1990 to 2020. The results showed that woodland and high‐coverage grassland exhibited the highest WCS capacity and contributed the greatest to total WCS, suggesting the importance of protecting coverage and area of woodland and grassland. From 1990 to 2020, the areas of high‐ and medium‐coverage grasslands significantly decreased, implying adverse effects of landscape composition changes on ZP's WCS during the past few decades. The effects of landscape configuration metrics on WCS exhibited significant variability across years, climate scenarios and regions, highlighting the significant role of climatic and underlying surface. Under realistic climatic scenarios, for greater WCS, in most parts of the western and northern ZP, which negatively correlated with aggregation index, patch density, and mean fractal dimension index but positively correlated with shannon's diversity index, it is better to increase the proportion of large patches, reduce landscape fragmentation, and maintain diverse patch types. Conversely, in southeastern part of the central ZP, where WCS showed an opposite correlation with the aforementioned metrics, maintaining simpler patch type diversity and higher landscape connectivity may be useful. These findings provided important insights for identifying sensitive areas where landscape pattern changes affect WCS and optimizing landscapes to sustain ZP's WCS.

An automated construction method of 3D knowledge graph based on multi-agent systems in virtual geographic scene

ABSTRACT Virtual geographic scenes can significantly facilitate the visualization and comprehension of the real world. However, the multitude of object types and complex relationships they contain make it challenging to display embedded geographic knowledge. Knowledge graphs help organize object entities and their relationships within scenes, which makes it easier to store and express geographic knowledge. Current methods for constructing knowledge graphs for virtual geographic scenes suffer from issues such as weak automation, low dimensionality, and poor cognitive efficiency. Thus, this paper presents a method for automatically constructing knowledge graphs by integrating intelligent systems. The method involves designing a multiagent system to extract entities and relationships hidden in virtual geographic scenes. In addition, a three-dimensional visualization approach is proposed for knowledge graphs constrained by spatiotemporal relationships. A virtual scene containing 2,183 objects was selected as the experimental area for constructing and displaying the knowledge graph. The results demonstrate that the method constructs a knowledge graph with 12,958 relationships within 300 s in common network and hardware settings. In addition, a knowledge graph offers better completeness at small scales compared to other geographic knowledge graphs, and it can also enhance the cognitive efficiency of understanding scene relationships.

Leveraging deep learning for robust EEG analysis in mental health monitoring.

Mental health monitoring utilizing EEG analysis has garnered notable interest due to the non-invasive characteristics and rich temporal information encoded in EEG signals, which are indicative of cognitive and emotional conditions. Conventional methods for EEG-based mental health evaluation often depend on manually crafted features or basic machine learning approaches, like support vector classifiers or superficial neural networks. Despite the potential of these approaches, they often fall short in capturing the intricate spatiotemporal relationships within EEG data, leading to lower classification accuracy and poor adaptability across various populations and mental health scenarios. To overcome these limitations, we introduce the EEG Mind-Transformer, an innovative deep learning architecture composed of a Dynamic Temporal Graph Attention Mechanism (DT-GAM), a Hierarchical Graph Representation and Analysis (HGRA) module, and a Spatial-Temporal Fusion Module (STFM). The DT-GAM is designed to dynamically extract temporal dependencies within EEG data, while the HGRA models the brain's hierarchical structure to capture both localized and global interactions among different brain regions. The STFM synthesizes spatial and temporal elements, generating a comprehensive representation of EEG signals. Our empirical results confirm that the EEG Mind-Transformer significantly surpasses conventional approaches, achieving an accuracy of 92.5%, a recall of 91.3%, an F1-score of 90.8%, and an AUC of 94.2% across several datasets. These findings underline the model's robustness and its generalizability to diverse mental health conditions. Moreover, the EEG Mind-Transformer not only pushes the boundaries of state-of-the-art EEG-based mental health monitoring but also offers meaningful insights into the underlying brain functions associated with mental disorders, solidifying its value for both research and clinical settings.

Application of Decomposition Expression in Digital Video Object Segmentation

In the field of actual Video Object Segmentation (VOS), traditional techniques have poor adaptability and insufficient segmentation results. Therefore, based on existing problems, an Unsupervised Video Object Segmentation (UVOS) technique based on convolutional networks is proposed. Firstly, the method of decomposing expressions is used to handle the spatiotemporal relationship between the reference frame and the target frame, and video object reconstruction is achieved through similarity calculation. For target segmentation in motion scenes, a Single Linear Bottleneck Operator (SLBO) is introduced for feature extraction, and pooling compensation is used to optimize feature information loss. For general scene segmentation, a spatiotemporal similarity segmentation technique is introduced to achieve target video segmentation for complex scenes. In the foreground segmentation test of sports scenes, the Change Detection Benchmark Dataset 2014 (CDNet.20I4SM) dataset was selected to test the model's loss performance in different scenarios. In adverse weather scenario training, the proposed model tends to converge after 40 iterations, with a loss value of 0.276, which is superior to the Foreground image Segmentation (FgSegNet_), the Convolutional Networks for Biomedical Image Segmentation (MU Net), Cascade Convolutional Neural Network (Cascade CNN) models; In the accuracy test, the proposed FS-LBPC model tended to converge after 50 iterations, with a precision P-value of 0.963. It performed the best among the four segmentation models the FgSegNet_, MU Net, Cascade CNN, and a real-time Foreground Segmentation network based on single Linear Bottleneck and Pooling Compensation (FS-LBPC). Usually, the Densely Annotated VIdeo Segmentation (DAVIS16) dataset is selected for video scene segmentation, which has the best segmentation performance in horse racing and animal flight scenes, with segmentation accuracy of 0.976 and 0.965, respectively. In summary, the VOS technology has excellent application effects in practical scenarios, providing important technical references for the improvement of image and video processing and segmentation technology

Spatial-temporal evolution of the allometric relationship between urban economic and health resources in the Yangtze River Delta urban agglomeration.

The evolution of the spatiotemporal relationship between urban economic growth and health resources within the Yangtze River Delta urban agglomeration provides an important context for understanding the regional development dynamics in China. Previous studies focused on equity in health-resource allocation and service efficiency, often overlooking the allometric growth relationships between health resources and economic variables. This study employs an allometric growth model to elucidate the changing interactions between the number of medical beds, doctors, and urban economic indicators in the Yangtze River Delta region from 2009 to 2022. Employing Zipf's law and allometric growth modeling, this study analyzed growth trends and revealed significant differences in resource allocation and size changes over time. The main findings suggest that, although resource centralization is a general trend, differences persist, especially in less economically developed regions. This study innovatively introduces an allometric growth model that offers a new perspective on understanding the mechanisms of regional health-resource growth and underscores the significant influence of economic factors on health-resource allocation. This study significantly contributes to the sustainability of urban health systems and provides theoretical support for policy formulations aimed at optimizing the allocation of health resources and strengthening regional economic strategies in the Yangtze River Delta region.

The Relationship Between Carbon Emissions and Ecosystem Services in Guangdong Province, China: The Perspective of Ecological Function Zones

Ecosystem carbon sinks can offset part of the carbon emissions from human activities, playing a significant role in the carbon neutrality process. Clarifying the relationship between carbon emissions and ecosystem services is crucial for achieving the dual goals of carbon neutrality and ecological environmental protection. Effective ecosystem management is a prerequisite for controlling carbon emissions, as well as for ecosystem conservation and restoration, making a significant contribution to emission reduction and the enhancement of ecosystem services. Therefore, this study takes Guangdong Province as an example, starting with ecological functional zones—units that can enhance the effectiveness of ecosystem management—combining multi-source data and localized methods to develop annual carbon emissions (CEs) and ecosystem service value (ESV) data from 2000 to 2020, and reveals the spatiotemporal relationships between CEs and the ESV. The results showed the following from 2000 to 2020: (1) The net CEs increased from 203.73 to 482.80 million tons, representing an increase of 279.07 million tons, or 136.98%. The metropolitan residential security zone (MRSZ) was the dominant carbon source area, accounting for more than 60% of the total net CEs. (2) The total ESV gradually decreased from CNY 596.95 to 504.56 billion, representing a decline of CNY 92.39 billion, or 15.48%. The WCZ had the highest ESV, accounting for more than 50% of the total in all periods. (3) Temporally, the net CEs were negatively correlated with the total ESV in the study area, especially in the MRSZ, while a positive correlation was observed in the agricultural products provision zone (APZ). Spatially, the main clusters were Low–Low and High–Low clusters, primarily distributed in the APZ and MRSZ. This study explores and reveals the spatiotemporal relationship between CEs and the ESV, providing valuable references for related research in Guangdong Province and other regional comparative studies.

Influence of Narrative Specificity and Voice Quality When Listening to Audio Descriptions:

Audio description (AD) serves as a vital means to make visual media accessible to non-sighted and visually impaired audiences. This study systematically investigates the impact of narrative specificity and voice quality on imageability and comprehension in both sighted and non-sighted populations. Twenty non-sighted participants, including congenitally blind individuals and those who lost their sight early in life, were compared with a group of 20 sighted participants, matched for verbal working memory capabilities. Participants listened to 50 short event descriptions, describing spatiotemporal relations with varying levels of narrative specificity, presented in both typical and dysphonic voices. After each event description, participants rated their ability to imagine the content, overall comprehension, listening effort, and listening enjoyment. Results indicate that high narrative specificity enhanced imageability in non-sighted individuals, especially for scenarios involving changes in motion, and, to some extent, for visuospatial relations, irrespective of sightedness. Additionally, dysphonic voices increased listening effort and reduced enjoyment for non-sighted participants only. These findings underscore the importance of considering voice quality and narrative specificity in AD for non-sighted users and have implications for both professional audio describers and the development of automated AD systems. Lay summary Imagine you're watching a movie but instead of seeing the scenes, you're listening to someone describe them to you. This is what audio description (AD) does - it makes movies, TV shows, and other visual media accessible for people who can't see or have trouble seeing. But not all descriptions are created equal. Think about the difference between someone telling you "a person walks into a room" versus "a tall, anxious man in a red shirt bursts into a sunlit, cluttered room, glancing over his shoulder." The second description paints a much clearer picture in your mind, doesn't it? This study looked at how specific these descriptions are (like our detailed scene above) and the quality of the voice telling the story, to see how they affect people's ability to imagine and understand what's being described. We worked with 40 people - half of whom have never been able to see or lost their sight when they were very young, and the other half who can see. Everyone listened to 50 short stories about different events. These stories varied in how detailed they were and were told in either a clear voice or a voice that was hard to listen to (a hoarse voice). After hearing each story, participants judged how well they could picture what was described, how well they understood it, how hard they had to work to listen, and how much they enjoyed listening. The results were interesting. When the stories were really detailed, people who couldn't see were better able to "see" the action in their minds, especially if the story involved movement or where things were located. This was true for everyone, regardless of whether they could see or not. But, when the voice telling the story was hard to listen to, it made it tougher for people who couldn't see to follow along and enjoy the story. What this tells us is that for audio descriptions to be really helpful and enjoyable for everyone, especially those who rely on them, it's important to not only choose the right words but also the right voice. This insight is valuable not just for people who create audio descriptions but also for developing technology that can automatically generate them. Making movies and TV shows more enjoyable and accessible for everyone is the goal, and we hope that this study help getting us there. Declaration of use of AI: ChatGPT4 was used to construct this lay-text based on the abstract from the original manuscript

A hybrid dynamic graph neural network framework for real-time anomaly detection

ABSTRACT The timely and robust detection of anomalies is essential for resilient and secure operations of critical water infrastructures against operational faults or malicious actions. However, real-world systems exhibit diverse and evolving spatiotemporal relationships among their components, posing an intricate challenge in anomaly detection task. This study proposes a hybrid dynamic graph neural network (GNN) that jointly maps long- and short-term spatiotemporal relationships in multivariate data streams. Those relationships are encoded via a hybrid graph, comprising an optimally learned static subgraph for persistent structural relationships and a complementary dynamic subgraph for dynamically shifting relationships. Additionally, an attention mechanism captures time-varying relational importances and shifts the model's focus towards significant relationships, while minimising contributions of less importance to the final outputs. The proposed architecture is showcased through a synthetic case study of a water distribution system with multivariate data streams from both on-site and soft sensors, and shows strong detection and localisation accuracy against all scenarios of operational faults and malicious actions explored. A comparative analysis with an equivalent static graph model indicates that the addition of the hybrid dynamic component enhances detection accuracy and reduces false alarm rates through more robust characterisation of behaviours, thus allowing actionable insights for more resilient and secure operations.

PSTFormer: A novel parallel spatial-temporal transformer for remaining useful life prediction of aeroengine

One of the significant tasks in aeroengine remaining useful life (RUL) prediction is to address both temporal dependencies and spatial dependencies in multivariate time series (MTS) monitoring data. However, it is difficult for traditional transformer-based methods simultaneously extract both temporal and spatial dependencies due to their mutual interference, limiting the further improvement of prediction performance. To address these issues, this paper proposes a novel Parallel Spatial-Temporal Transformer (PSTFormer) for aeroengine RUL prediction with multi-sensor monitoring data. First, a novel parallel spatial–temporal attention mechanism (PSTAM) is designed, which consists of a temporal attention module (TAM) and a spatial attention module (SAM), to simultaneously capture temporal and spatial dependencies from MTS data. TAM employs multiscale convolution to learn the temporal dependencies at different time scales, while SAM adopts a self-attention mechanism to learn the spatial dependencies among different sensor parameter. Parallel connection between TAM and SAM can effectively avoid the mutual interference between temporal and spatial dependencies, improving the modeling ability of complex spatiotemporal relationships. Second, a task-guided spatiotemporal feature fusion (TG-STFF) module is designed, which adaptively fuses temporal and spatial features according to downstream task. Specifically, based on the RUL prediction characteristic, TG-STFF converts spatial features into attention weights and fuses them with temporal features to extract more representative degradation features. Finally, the effectiveness of PSTFormer is validated by a series of experimental comparisons on the public C-MAPSS dataset. Compared with SOTA methods, PSTFormer exhibits more outstanding prediction performance, and it can effectively address the aforementioned challenges in RUL prediction tasks. Therfore, the development of PSTFormer provides an innovative and effective method for aeroengine RUL prediction, significantly enhancing the efficiency and safety of aeroengine maintenance and operation.

MGSAN: multimodal graph self-attention network for skeleton-based action recognition

Due to the emergence of graph convolutional networks (GCNs), the skeleton-based action recognition has achieved remarkable results. However, the current models for skeleton-based action analysis treat skeleton sequences as a series of graphs, aggregating features of the entire sequence by alternately extracting spatial and temporal features, i.e., using a 2D (spatial features) plus 1D (temporal features) approach for feature extraction. This undoubtedly overlooks the complex spatiotemporal fusion relationships between joints during motion, making it challenging for models to capture the connections between different temporal frames and joints. In this paper, we propose a Multimodal Graph Self-Attention Network (MGSAN), which combines GCNs with self-attention to model the spatiotemporal relationships between skeleton sequences. Firstly, we design graph self-attention (GSA) blocks to capture the intrinsic topology and long-term temporal dependencies between joints. Secondly, we propose a multi-scale spatio-temporal convolutional network for channel-wise topology modeling (CW-TCN) to model short-term smooth temporal information of joint movements. Finally, we propose a multimodal fusion strategy to fuse joint, joint movement, and bone flow, providing the model with a richer set of multimodal features to make better predictions. The proposed MGSAN achieves state-of-the-art performance on three large-scale skeleton-based action recognition datasets, with accuracy of 93.1% on NTU RGB+D 60 cross-subject benchmark, 90.3% on NTU RGB+D 120 cross-subject benchmark, and 97.0% on the NW-UCLA dataset. Code is available at https://github.com/lizaowo/MGSAN.

A novel spatial heteroscedastic generalized additive distributed lag model for the spatiotemporal relation between PM2.5and cardiovascular hospitalization

Many studies have examined the impact of air pollution on cardiovascular hospitalization (CVH), but few have looked at the delayed effects of air pollution on CVH. Additionally, there has been no research on the spatial and temporal differences in how environmental pollutants affect CVH. This study seeks to identify spatial heteroscedasticity in the relation between PM2.5 and CVH by developing a Generalized Additive Distributed Lag (GADL) model. Data on hospitalization due to cardiovascular disease were collected from the Hospital Information System (HIS) of Mashhad University of Medical Science from 2017 to 2020. Air pollution data from 22 air quality monitoring (AQM) stations were obtained from the Environmental Pollution Monitoring Center of Mashhad administrates. Markov Random Field (MRF) smoother was utilized in the GADL model to account for spatial heteroscedasticity in the observations. This developed model is a Spatial Heteroscedastic Generalized Additive Distributed Lag (SHGADL) model. Our use of GADL allowed us to discover a significant relationship between PM2.5 exposures and the risk of CVH at lags 0 and 1 in all districts. Our results reveal heteroscedasticity in the Relative Risks (RR) of PM2.5 on CVH across different districts. After accounting for this spatial heteroscedasticity, we found that the RR of PM2.5 on CVH at lags 0 and 1 were 1.0102 (95% CI: 1.0034, 1.0170) and 1.0043 (95% CI: 1.0009, 1.0078) respectively. The central and southeastern districts showed higher RR for CVH. The developed SHGADL model provides evidence of a significant lagged effect of PM2.5 exposures on CVH, and identifies low- and high-risk districts for CVH in Mashhad. This finding can assist decision-makers in allocating resources and planning strategically, with a focus on local interventions to manage ambient air pollution and providing emergency care for CVH.