As a significant city in the Yangtze River Delta regions,Hefei has experienced rapid changes in the sources of air pollution due to its high-speed economic development and urban expansion.However,there has been limite...As a significant city in the Yangtze River Delta regions,Hefei has experienced rapid changes in the sources of air pollution due to its high-speed economic development and urban expansion.However,there has been limited research in recent years on the spatial-temporal distribution and emission of its atmospheric pollutants.To address this,this study conducted mobile observations of urban roads using the Mobile-DOAS instrument from June 2021 to May 2022.The monitoring results exhibit a favourable consistent with TROPOMI satellite data and ground monitoring station data.Temporally,there were pronounced seasonal variations in air pollutants.Spatially,high concentration of HCHO and NO_(2)were closely associated with traffic congestion on roadways,while heightened SO_(2)levels were attributed to winter heating and industrial emissions.The study also revealed that with the implementation of road policies,the average vehicle speed increased by 95.4%,while the NO concentration decreased by 54.4%.In the estimation of urban NO_(x)emission flux,it was observed that in temporal terms,compared with inventory data,the emissions calculated viamobile measurements exhibitedmore distinct seasonal patterns,with the highest emission rate of 349 g/sec in winter and the lowest of 142 g/sec in summer.In spatial terms,the significant difference in emissions between the inner and outer ring roads also suggests the presence of the city’s primary NO_(x)emission sources in the area between these two rings.This study offers data support for formulating the next phase of air pollution control measures in urban areas.展开更多
Image-maps,a hybrid design with satellite images as background and map symbols uploaded,aim to combine the advantages of maps’high interpretation efficiency and satellite images’realism.The usability of image-maps i...Image-maps,a hybrid design with satellite images as background and map symbols uploaded,aim to combine the advantages of maps’high interpretation efficiency and satellite images’realism.The usability of image-maps is influenced by the representations of background images and map symbols.Many researchers explored the optimizations for background images and symbolization techniques for symbols to reduce the complexity of image-maps and improve the usability.However,little literature was found for the optimum amount of symbol loading.This study focuses on the effects of background image complexity and map symbol load on the usability(i.e.,effectiveness and efficiency)of image-maps.Experiments were conducted by user studies via eye-tracking equipment and an online questionnaire survey.Experimental data sets included image-maps with ten levels of map symbol load in ten areas.Forty volunteers took part in the target searching experiments.It has been found that the usability,i.e.,average time viewed(efficiency)and average revisits(effectiveness)of targets recorded,is influenced by the complexity of background images,a peak exists for optimum symbol load for an image-map.The optimum levels for symbol load for different image-maps also have a peak when the complexity of the background image/image map increases.The complexity of background images serves as a guideline for optimum map symbol load in image-map design.This study enhanced user experience by optimizing visual clarity and managing cognitive load.Understanding how these factors interact can help create adaptive maps that maintain clarity and usability,guiding AI algorithms to adjust symbol density based on user context.This research establishes the practices for map design,making cartographic tools more innovative and more user-centric.展开更多
Viral infectious diseases,characterized by their intricate nature and wide-ranging diversity,pose substantial challenges in the domain of data management.The vast volume of data generated by these diseases,spanning fr...Viral infectious diseases,characterized by their intricate nature and wide-ranging diversity,pose substantial challenges in the domain of data management.The vast volume of data generated by these diseases,spanning from the molecular mechanisms within cells to large-scale epidemiological patterns,has surpassed the capabilities of traditional analytical methods.In the era of artificial intelligence(AI)and big data,there is an urgent necessity for the optimization of these analytical methods to more effectively handle and utilize the information.Despite the rapid accumulation of data associated with viral infections,the lack of a comprehensive framework for integrating,selecting,and analyzing these datasets has left numerous researchers uncertain about which data to select,how to access it,and how to utilize it most effectively in their research.This review endeavors to fill these gaps by exploring the multifaceted nature of viral infectious diseases and summarizing relevant data across multiple levels,from the molecular details of pathogens to broad epidemiological trends.The scope extends from the micro-scale to the macro-scale,encompassing pathogens,hosts,and vectors.In addition to data summarization,this review thoroughly investigates various dataset sources.It also traces the historical evolution of data collection in the field of viral infectious diseases,highlighting the progress achieved over time.Simultaneously,it evaluates the current limitations that impede data utilization.Furthermore,we propose strategies to surmount these challenges,focusing on the development and application of advanced computational techniques,AI-driven models,and enhanced data integration practices.By providing a comprehensive synthesis of existing knowledge,this review is designed to guide future research and contribute to more informed approaches in the surveillance,prevention,and control of viral infectious diseases,particularly within the context of the expanding big-data landscape.展开更多
In the current situation of decelerating economic expansion,examining the digital economy(DE)as a novel economic model is beneficial for the local economy’s sustainable and high-quality development(HQD).We analyzed p...In the current situation of decelerating economic expansion,examining the digital economy(DE)as a novel economic model is beneficial for the local economy’s sustainable and high-quality development(HQD).We analyzed panel data from the Yellow River(YR)region from 2013 to 2021 and discovered notable spatial variances in the composite index and coupling coordination of the two systems.Specifically,the downstream region exhibited the highest coupling coordination,while the upstream region had the lowest.We identified that favorable factors such as economic development,innovation,industrial upgrading,and government intervention can bolster the coupling.Our findings provide a valuable framework for promoting DE and HQD in the YR region.展开更多
The suprachiasmatic nucleus in the hypothalamus is the master circadian clock in mammals,coordinating physiological processes with the 24-hour day–night cycle.Comprising various cell types,the suprachiasmatic nucleus...The suprachiasmatic nucleus in the hypothalamus is the master circadian clock in mammals,coordinating physiological processes with the 24-hour day–night cycle.Comprising various cell types,the suprachiasmatic nucleus(SCN)integrates environmental signals to maintain complex and robust circadian rhythms.Understanding the complexity and synchrony within SCN neurons is essential for effective circadian clock function.Synchrony involves coordinated neuronal firing for robust rhythms,while complexity reflects diverse activity patterns and interactions,indicating adaptability.Interestingly,the SCN retains circadian rhythms in vitro,demonstrating intrinsic rhythmicity.This study introduces the multiscale structural complexity method to analyze changes in SCN neuronal activity and complexity at macro and micro levels,based on Bagrov et al.’s approach.By examining structural complexity and local complexities across scales,we aim to understand how tetrodotoxin,a neurotoxin that inhibits action potentials,affects SCN neurons.Our method captures critical scales in neuronal interactions that traditional methods may overlook.Validation with the Goodwin model confirms the reliability of our observations.By integrating experimental data with theoretical models,this study provides new insights into the effects of tetrodotoxin(TTX)on neuronal complexities,contributing to the understanding of circadian rhythms.展开更多
The construction projects’ dynamic and interconnected nature requires a comprehensive understanding of complexity during pre-construction. Traditional tools such as Gantt charts, CPM, and PERT often overlook uncertai...The construction projects’ dynamic and interconnected nature requires a comprehensive understanding of complexity during pre-construction. Traditional tools such as Gantt charts, CPM, and PERT often overlook uncertainties. This study identifies 20 complexity factors through expert interviews and literature, categorising them into six groups. The Analytical Hierarchy Process evaluated the significance of different factors, establishing their corresponding weights to enhance adaptive project scheduling. A system dynamics (SD) model is developed and tested to evaluate the dynamic behaviour of identified complexity factors. The model simulates the impact of complexity on total project duration (TPD), revealing significant deviations from initial deterministic estimates. Data collection and analysis for reliability tests, including normality and Cronbach alpha, to validate the model’s components and expert feedback. Sensitivity analysis confirmed a positive relationship between complexity and project duration, with higher complexity levels resulting in increased TPD. This relationship highlights the inadequacy of static planning approaches and underscores the importance of addressing complexity dynamically. The study provides a framework for enhancing planning systems through system dynamics and recommends expanding the model to ensure broader applicability in diverse construction projects.展开更多
Accurate traffic flow prediction has a profound impact on modern traffic management. Traffic flow has complex spatial-temporal correlations and periodicity, which poses difficulties for precise prediction. To address ...Accurate traffic flow prediction has a profound impact on modern traffic management. Traffic flow has complex spatial-temporal correlations and periodicity, which poses difficulties for precise prediction. To address this problem, a Multi-head Self-attention and Spatial-Temporal Graph Convolutional Network (MSSTGCN) for multiscale traffic flow prediction is proposed. Firstly, to capture the hidden traffic periodicity of traffic flow, traffic flow is divided into three kinds of periods, including hourly, daily, and weekly data. Secondly, a graph attention residual layer is constructed to learn the global spatial features across regions. Local spatial-temporal dependence is captured by using a T-GCN module. Thirdly, a transformer layer is introduced to learn the long-term dependence in time. A position embedding mechanism is introduced to label position information for all traffic sequences. Thus, this multi-head self-attention mechanism can recognize the sequence order and allocate weights for different time nodes. Experimental results on four real-world datasets show that the MSSTGCN performs better than the baseline methods and can be successfully adapted to traffic prediction tasks.展开更多
Binary sequences constructed by Legendre symbols are widely used in communication and cryptography since they have many good pseudo-random properties.In this paper,we determine the 2-adic complexity of the sum sequenc...Binary sequences constructed by Legendre symbols are widely used in communication and cryptography since they have many good pseudo-random properties.In this paper,we determine the 2-adic complexity of the sum sequence of any k many Legendre sequences and show that the 2-adic complexity of the sum sequences of any k many Legendre sequences reaches the maximum by proving the case of k=2 and 3,which implies that the sum sequences can resist the attack of rational approximation algorithm.展开更多
Numerous studies have examined the impact ofwater quality degradation on bacterial community structure,yet insights into its effects on the bacterial ecological networks remain scarce.In this study,we investigated the...Numerous studies have examined the impact ofwater quality degradation on bacterial community structure,yet insights into its effects on the bacterial ecological networks remain scarce.In this study,we investigated the diversity,composition,assembly patterns,ecological networks,and environmental determinants of bacterial communities across 20 ponds to understand the impact of water quality degradation.Our findings revealed that water quality degradation significantly reduces the α-diversity of bacterial communities in water samples,while sediment samples remain unaffected.Additionally,water quality deterioration increases the complexity of bacterial networks in water samples but reduces it in sediment samples.These shifts in bacterial communities were primarily governed by deterministic processes,with heterogeneous selection being particularly influential.Through redundancy analysis(RDA),multiple regression on matrices(MRM),and Mantel tests,we identified dissolved oxygen(DO),ammonium nitrogen(NH_(4)^(+)-N),and C/N ratio as key factors affecting the composition and network complexity of bacterial communities in both water and sediment.Overall,this study contributes a novel perspective on the effect ofwater quality deterioration on microbial ecosystems and provides valuable insights for improving ecological evaluations and biomonitoring practices related to water quality management.展开更多
Soil microbial communities are key factors in maintaining ecosystem multifunctionality(EMF).However,the distribution patterns of bacterial diversity and how the different bacterial taxa and their diversity dimensions ...Soil microbial communities are key factors in maintaining ecosystem multifunctionality(EMF).However,the distribution patterns of bacterial diversity and how the different bacterial taxa and their diversity dimensions affect EMF remain largely unknown.Here,we investigated variation in three measures of diversity(alpha diversity,community composition and network complexity)among rare,intermediate,and abundant taxa across a latitudinal gradient spanning five forest plots in Yunnan Province,China and examined their contributions on EMF.We aimed to characterize the diversity distributions of bacterial groups across latitudes and to assess the differences in the mechanisms underlying their contributions to EMF.We found that multifaceted diversity(i.e.,diversity assessed by the three different metrics)of rare,intermediate,and abundant bacteria generally decreased with increasing latitude.More importantly,we found that rare bacterial taxa tended to be more diverse,but they contributed less to EMF than intermediate or abundant bacteria.Among the three dimensions of diversity we assessed,only community composition significantly affected EMF across all locations,while alpha diversity had a negative effect,and network complexity showed no significant impact.Our study further emphasizes the importance of intermediate and abundant bacterial taxa as well as community composition to EMF and provides a theoretical basis for investigating the mechanisms by which belowground microorganisms drive EMF along a latitudinal gradient.展开更多
This study examined how psychological meaningfulness moderates job complexity and work-family conflict in Nigerian secondary school teachers.This study included 1694 teachers from 17 Nigerian secondary schools(female=6...This study examined how psychological meaningfulness moderates job complexity and work-family conflict in Nigerian secondary school teachers.This study included 1694 teachers from 17 Nigerian secondary schools(female=69.54%,mean age=33.19,SD=6.44 years).The participants completed the Work-family Conflict Scale,Job Complexity Scale,and Psychological Meaningfulness Scale.Study design was cross-sectional.Hayes PROCESS macro analysis results indicate a higher work-family conflict with job complexity among the secondary school teachers.While psychological meaningfulness was not associated with work-family conflict,it moderated the link between job complexity and work-family conflict in secondary school teachers such that a meaningful work endorsement is associated with lower employee’s work-life conflict.Thesefindings point to the importance of job functions to quality of family life.The studyfindings also suggest a need for supporting psychological meaningfulness for healthy work related quality of family life based on balancing work and family role demands.展开更多
BACKGROUND Sigmoid colon cancer faces challenges due to anatomical diversity,including variable inferior mesenteric artery(IMA)branching and tumor localization complexities,which increase intraoperative risks.AIM To c...BACKGROUND Sigmoid colon cancer faces challenges due to anatomical diversity,including variable inferior mesenteric artery(IMA)branching and tumor localization complexities,which increase intraoperative risks.AIM To comprehensively evaluate the impact of three-dimensional(3D)visualization technology on enhancing surgical precision and safety,as well as optimizing perioperative outcomes in laparoscopic sigmoid cancer resection.METHODS A prospective cohort of 106 patients(January 2023 to December 2024)undergoing laparoscopic sigmoid cancer resection was divided into the 3D(n=55)group and the control(n=51)group.The 3D group underwent preoperative enhanced computed tomography reconstruction(3D Slicer 5.2.2&Mimics 19.0).3D reconstruction visualization navigation intraoperatively guided the following key steps:Tumor location,Toldt’s space dissection,IMA ligation level selection,regional lymph node dissection,and marginal artery preservation.Outcomes included operative parameters,lymph node yield,and recovery metrics.RESULTS The 3D group demonstrated a significantly shorter operative time(172.91±20.69 minutes vs 190.29±32.29 minutes;P=0.002),reduced blood loss(31.5±11.8 mL vs 44.1±23.4 mL,P=0.001),earlier postoperative flatus(2.23±0.54 days vs 2.53±0.61 days;P=0.013),shorter hospital length of stay(13.47±1.74 days vs 16.20±7.71 days;P=0.013),shorter postoperative length of stay(8.6±2.6 days vs 10.5±4.9 days;P=0.014),and earlier postoperative exhaust time(2.23±0.54 days vs 2.53±0.61 days;P=0.013).Furthermore,the 3D group exhibited a higher mean number of lymph nodes harvested(16.91±5.74 vs 14.45±5.66;P=0.030).CONCLUSION The 3D visualization technology effectively addresses sigmoid colon anatomical complexity through surgical navigation,improving procedural safety and efficiency.展开更多
Ulva prolifera green tides are becoming aworldwide environmental problem,especially in the Yellow Sea,China.However,the effects of the occurrence of U.prolifera green tides on the community organization and stability ...Ulva prolifera green tides are becoming aworldwide environmental problem,especially in the Yellow Sea,China.However,the effects of the occurrence of U.prolifera green tides on the community organization and stability of surrounding microbiomes have still not been de-termined.Here,the prokaryotic microbial community network stability and assembly char-acteristics were systematically analyzed and compared between the green tide and non-green tide periods.U.prolifera blooms weaken the community complexity and robustness of surrounding microbiomes,increasing fragmentation and decreasing diversity.Bacteria and archaea exhibited distinct community distributions and assembly patterns under the influ-ence of green tides,and bacterial communities were more sensitive to outbreaks of green tides.The bacterial communities exhibited a greater niche breadth and a lower phyloge-netic distance during the occurrence of U.prolifera green tides compared to those during the non-green tide period while archaeal communities remained unchanged,suggesting that the bacterial communities underwent stronger homogeneous selection and more sensitive to green tide blooms than the archaeal communities.Piecewise structural equation model analysis revealed that the different responses of major prokaryotic microbial groups,such as Cyanobacteria,to environmental variables during green tides,were influenced by the variations in pH and nitrate during green tides and correlated with the salinity gradient during the non-green tide period.This study elucidates the response of the adaptability,associations,and stability of surrounding microbiomes to outbreaks of U.prolifera green tides.展开更多
Integrated Sensing and Communication(ISAC)is envisioned as a promising technology for Sixth-Generation(6G)wireless communications,which enables simultaneous high-rate communication and high-precision target localizati...Integrated Sensing and Communication(ISAC)is envisioned as a promising technology for Sixth-Generation(6G)wireless communications,which enables simultaneous high-rate communication and high-precision target localization.Compared to independent sensing and communication modules,dual-function ISAC could leverage the strengths of both communication and sensing in order to achieve cooperative gains.When considering the communication core network,ISAC system facilitates multiple communication devices to collaborate for networked sensing.This paper investigates such kind of cooperative ISAC systems with distributed transmitters and receivers to support non-connected and multi-target localization.Specifically,we introduce a Time of Arrival(TOA)based multi-target localization scheme,which leverages the bi-static range measurements between the transmitter,target,and receiver channels in order to achieve elliptical localization.To obtain the low-complexity localization,a two-stage search-refine localization methodology is proposed.In the first stage,we propose a Successive Greedy Grid-Search(SGGS)algorithm and a Successive-Cancellation-List Grid-Search(SCLGS)algorithm to address the Measurement-to-Target Association(MTA)problem with relatively low computational complexity.In the second stage,a linear approximation refinement algorithm is derived to facilitate high-precision localization.Simulation results are presented to validate the effectiveness and superiority of our proposed multi-target localization method.展开更多
The authors regret that an error occurred during the preparation of their article:One of the official databases,which was used for functional trait collections,contained an incorrect term–'chametophytes'–for...The authors regret that an error occurred during the preparation of their article:One of the official databases,which was used for functional trait collections,contained an incorrect term–'chametophytes'–for the life form category'chamaephytes'.Unfortunately,this incorrect term was used throughout the article following the nomenclature of this official database:in one instance in the main text,in Fig.3 and its caption,in Fig.5,and in two instances in the supplementary material.展开更多
Coastal wetlands store large amounts of soil organic carbon(SOC),and have assumed key roles in mitigating increasing CO_(2)in the atmosphere.The ongoing debate about SOC stabilization mechanisms stems partly from our ...Coastal wetlands store large amounts of soil organic carbon(SOC),and have assumed key roles in mitigating increasing CO_(2)in the atmosphere.The ongoing debate about SOC stabilization mechanisms stems partly from our incomplete understanding of its complex chemical architecture at the molecular scale.Deciphering the molecular composition of soil organic matter is crucial for revealing mechanisms that govern SOC persistence.This study utilized the field sampling data from 2016 and aimed to characterize molecular composition of SOC in typical salt marsh(SM)and freshwater marsh(FM)in Louisiana coastal regions,USA by extending the application of graph networks with pyrolysis-gas chromatography-mass spectrometry,and then to quantify potential links between SOC persistence and molecular diversity and network complexity.The results revealed that SOC predominantly consisted of alkyl compounds(Alkyl),phenol(Ph),lignin(Lg),and aliphatic compounds,constituting 23.21%and 27.85%,17.84%and 21.55%,16.94%and 15.49%,17.20%and 15.93%of total ion chromatogram(TIC)in SM and FM wetlands,respectively.Molecular diversity in SM was higher than that in FM,while the network graph exhibited greater complexity in FM,featuring 167 and 123 nodes,and 1935 and 1982 edges in the network graphs of SOC from SM and FM,respectively.Correlation analysis confirmed positive relations between molecular diversity indices,network complexity,and abundance of stable carbon isotopes(δ^(13)C).The variance partitioning analysis(VPA)supplied that soil nutrients exerted the most significant control on SOC persistence.Molecular diversity and network complexity,when combined with soil nutrients,could explain 34%of the variances in SOC persistence.展开更多
Visual question answering(VQA)is a multimodal task,involving a deep understanding of the image scene and the question’s meaning and capturing the relevant correlations between both modalities to infer the appropriate...Visual question answering(VQA)is a multimodal task,involving a deep understanding of the image scene and the question’s meaning and capturing the relevant correlations between both modalities to infer the appropriate answer.In this paper,we propose a VQA system intended to answer yes/no questions about real-world images,in Arabic.To support a robust VQA system,we work in two directions:(1)Using deep neural networks to semantically represent the given image and question in a fine-grainedmanner,namely ResNet-152 and Gated Recurrent Units(GRU).(2)Studying the role of the utilizedmultimodal bilinear pooling fusion technique in the trade-o.between the model complexity and the overall model performance.Some fusion techniques could significantly increase the model complexity,which seriously limits their applicability for VQA models.So far,there is no evidence of how efficient these multimodal bilinear pooling fusion techniques are for VQA systems dedicated to yes/no questions.Hence,a comparative analysis is conducted between eight bilinear pooling fusion techniques,in terms of their ability to reduce themodel complexity and improve themodel performance in this case of VQA systems.Experiments indicate that these multimodal bilinear pooling fusion techniques have improved the VQA model’s performance,until reaching the best performance of 89.25%.Further,experiments have proven that the number of answers in the developed VQA system is a critical factor that a.ects the effectiveness of these multimodal bilinear pooling techniques in achieving their main objective of reducing the model complexity.The Multimodal Local Perception Bilinear Pooling(MLPB)technique has shown the best balance between the model complexity and its performance,for VQA systems designed to answer yes/no questions.展开更多
This paper investigates the spatial-temporal cooperative guidance problem for multiple flight vehicles without relying on time-to-go information.First,a two-stage cooperative guidance strategy,namely the cooperative g...This paper investigates the spatial-temporal cooperative guidance problem for multiple flight vehicles without relying on time-to-go information.First,a two-stage cooperative guidance strategy,namely the cooperative guidance and the Proportional Navigation Guidance(PNG)stage strategy,is developed to realize the spatial-temporal constraints in two dimensions.At the former stage,two controllers are designed and superimposed to satisfy both impact time consensus and impact angle constraints.Once the convergent conditions are satisfied,the flight vehicles will switch to the PNG stage to ensure zero miss distance.To further extend the results to three dimensions,a planar pursuit guidance stage is additionally imposed at the beginning of guidance.Due to the inde-pendence of time-to-go estimation,the proposed guidance strategy possesses great performance in satisfying complex spatial-temporal constraints even under flight speed variation.Finally,several numerical simulations are implemented to verify the effectiveness and advantages of the proposed results under different scenarios.展开更多
Forest fires pose a significant threat to human life and property,so the utilization of unmanned aircraft systems provides new ways for forest firefighting.Given the constrained load capacities of these aircraft,aeria...Forest fires pose a significant threat to human life and property,so the utilization of unmanned aircraft systems provides new ways for forest firefighting.Given the constrained load capacities of these aircraft,aerial refueling becomes crucial to extend their operational time and range.In order to address the complexities of firefighting missions involving multi-receiver and multi-tanker deployed from various airports,first,a fuel consumption calculation model for aerial refueling scheduling is established based on the receiver path.Then,two distinct methods,including an integrated one and a decomposed one,are designed to address the challenges of establishing refueling airspace and allocating tasks for tankers.Both methods aim to optimize total fuel consumption of the receivers and tankers within the aerial refueling scheduling framework.The optimization problem is established as nonlinear optimization models along with restrictions.The integrated method seamlessly combines refueling rendezvous point scheduling and tanker task allocation into unified process.It has a complete solution space and excels in optimizing total fuel consumption.The decomposed method,through the separation of rendezvous point scheduling and task allocation,achieves a reduced computational complexity.However,this comes at the cost of sacrificing optimality by excluding specific feasible solutions.Finally,numerical simulations are carried out to verify the feasibility and effectiveness of the proposed methods.These simulations yield insights crucial for the practical engineering application of both the integrated and decomposed methods in real-world scenarios.This comprehensive approach aims to enhance the efficiency of forest firefighting operations,mitigating the risks posed by forest fires to human life and property.展开更多
In the Industrial Internet of Things(IIoT),sensors generate time series data to reflect the working state.When the systems are attacked,timely identification of outliers in time series is critical to ensure security.A...In the Industrial Internet of Things(IIoT),sensors generate time series data to reflect the working state.When the systems are attacked,timely identification of outliers in time series is critical to ensure security.Although many anomaly detection methods have been proposed,the temporal correlation of the time series over the same sensor and the state(spatial)correlation between different sensors are rarely considered simultaneously in these methods.Owing to the superior capability of Transformer in learning time series features.This paper proposes a time series anomaly detection method based on a spatial-temporal network and an improved Transformer.Additionally,the methods based on graph neural networks typically include a graph structure learning module and an anomaly detection module,which are interdependent.However,in the initial phase of training,since neither of the modules has reached an optimal state,their performance may influence each other.This scenario makes the end-to-end training approach hard to effectively direct the learning trajectory of each module.This interdependence between the modules,coupled with the initial instability,may cause the model to find it hard to find the optimal solution during the training process,resulting in unsatisfactory results.We introduce an adaptive graph structure learning method to obtain the optimal model parameters and graph structure.Experiments on two publicly available datasets demonstrate that the proposed method attains higher anomaly detection results than other methods.展开更多
基金supported by the National Natural Science Foundation of China(Nos.U19A2044,42105132,42030609,41975037,and 42105133)the National Key Research and Development Program of China(No.2022YFC3703502)+1 种基金the Plan for Anhui Major Provincial Science&Technology Project(No.202203a07020003)Hefei Ecological Environment Bureau Project(No.2020BFFFD01804).
文摘As a significant city in the Yangtze River Delta regions,Hefei has experienced rapid changes in the sources of air pollution due to its high-speed economic development and urban expansion.However,there has been limited research in recent years on the spatial-temporal distribution and emission of its atmospheric pollutants.To address this,this study conducted mobile observations of urban roads using the Mobile-DOAS instrument from June 2021 to May 2022.The monitoring results exhibit a favourable consistent with TROPOMI satellite data and ground monitoring station data.Temporally,there were pronounced seasonal variations in air pollutants.Spatially,high concentration of HCHO and NO_(2)were closely associated with traffic congestion on roadways,while heightened SO_(2)levels were attributed to winter heating and industrial emissions.The study also revealed that with the implementation of road policies,the average vehicle speed increased by 95.4%,while the NO concentration decreased by 54.4%.In the estimation of urban NO_(x)emission flux,it was observed that in temporal terms,compared with inventory data,the emissions calculated viamobile measurements exhibitedmore distinct seasonal patterns,with the highest emission rate of 349 g/sec in winter and the lowest of 142 g/sec in summer.In spatial terms,the significant difference in emissions between the inner and outer ring roads also suggests the presence of the city’s primary NO_(x)emission sources in the area between these two rings.This study offers data support for formulating the next phase of air pollution control measures in urban areas.
基金National Natural Science Foundation of China(No.42301518)Hubei Key Laboratory of Regional Development and Environmental Response(No.2023(A)002)Key Laboratory of the Evaluation and Monitoring of Southwest Land Resources(Ministry of Education)(No.TDSYS202304).
文摘Image-maps,a hybrid design with satellite images as background and map symbols uploaded,aim to combine the advantages of maps’high interpretation efficiency and satellite images’realism.The usability of image-maps is influenced by the representations of background images and map symbols.Many researchers explored the optimizations for background images and symbolization techniques for symbols to reduce the complexity of image-maps and improve the usability.However,little literature was found for the optimum amount of symbol loading.This study focuses on the effects of background image complexity and map symbol load on the usability(i.e.,effectiveness and efficiency)of image-maps.Experiments were conducted by user studies via eye-tracking equipment and an online questionnaire survey.Experimental data sets included image-maps with ten levels of map symbol load in ten areas.Forty volunteers took part in the target searching experiments.It has been found that the usability,i.e.,average time viewed(efficiency)and average revisits(effectiveness)of targets recorded,is influenced by the complexity of background images,a peak exists for optimum symbol load for an image-map.The optimum levels for symbol load for different image-maps also have a peak when the complexity of the background image/image map increases.The complexity of background images serves as a guideline for optimum map symbol load in image-map design.This study enhanced user experience by optimizing visual clarity and managing cognitive load.Understanding how these factors interact can help create adaptive maps that maintain clarity and usability,guiding AI algorithms to adjust symbol density based on user context.This research establishes the practices for map design,making cartographic tools more innovative and more user-centric.
基金supported by the National Natural Science Foundation of China(32370703)the CAMS Innovation Fund for Medical Sciences(CIFMS)(2022-I2M-1-021,2021-I2M-1-061)the Major Project of Guangzhou National Labora-tory(GZNL2024A01015).
文摘Viral infectious diseases,characterized by their intricate nature and wide-ranging diversity,pose substantial challenges in the domain of data management.The vast volume of data generated by these diseases,spanning from the molecular mechanisms within cells to large-scale epidemiological patterns,has surpassed the capabilities of traditional analytical methods.In the era of artificial intelligence(AI)and big data,there is an urgent necessity for the optimization of these analytical methods to more effectively handle and utilize the information.Despite the rapid accumulation of data associated with viral infections,the lack of a comprehensive framework for integrating,selecting,and analyzing these datasets has left numerous researchers uncertain about which data to select,how to access it,and how to utilize it most effectively in their research.This review endeavors to fill these gaps by exploring the multifaceted nature of viral infectious diseases and summarizing relevant data across multiple levels,from the molecular details of pathogens to broad epidemiological trends.The scope extends from the micro-scale to the macro-scale,encompassing pathogens,hosts,and vectors.In addition to data summarization,this review thoroughly investigates various dataset sources.It also traces the historical evolution of data collection in the field of viral infectious diseases,highlighting the progress achieved over time.Simultaneously,it evaluates the current limitations that impede data utilization.Furthermore,we propose strategies to surmount these challenges,focusing on the development and application of advanced computational techniques,AI-driven models,and enhanced data integration practices.By providing a comprehensive synthesis of existing knowledge,this review is designed to guide future research and contribute to more informed approaches in the surveillance,prevention,and control of viral infectious diseases,particularly within the context of the expanding big-data landscape.
基金supported by the National Office for Philosophy and Social Sciences(grant reference 22&ZD067).
文摘In the current situation of decelerating economic expansion,examining the digital economy(DE)as a novel economic model is beneficial for the local economy’s sustainable and high-quality development(HQD).We analyzed panel data from the Yellow River(YR)region from 2013 to 2021 and discovered notable spatial variances in the composite index and coupling coordination of the two systems.Specifically,the downstream region exhibited the highest coupling coordination,while the upstream region had the lowest.We identified that favorable factors such as economic development,innovation,industrial upgrading,and government intervention can bolster the coupling.Our findings provide a valuable framework for promoting DE and HQD in the YR region.
基金Project supported by the National Natural Science Foundation of China(Grant Nos.12275179,11875042,and 12150410309)the Natural Science Foundation of Shanghai(Grant No.21ZR1443900).
文摘The suprachiasmatic nucleus in the hypothalamus is the master circadian clock in mammals,coordinating physiological processes with the 24-hour day–night cycle.Comprising various cell types,the suprachiasmatic nucleus(SCN)integrates environmental signals to maintain complex and robust circadian rhythms.Understanding the complexity and synchrony within SCN neurons is essential for effective circadian clock function.Synchrony involves coordinated neuronal firing for robust rhythms,while complexity reflects diverse activity patterns and interactions,indicating adaptability.Interestingly,the SCN retains circadian rhythms in vitro,demonstrating intrinsic rhythmicity.This study introduces the multiscale structural complexity method to analyze changes in SCN neuronal activity and complexity at macro and micro levels,based on Bagrov et al.’s approach.By examining structural complexity and local complexities across scales,we aim to understand how tetrodotoxin,a neurotoxin that inhibits action potentials,affects SCN neurons.Our method captures critical scales in neuronal interactions that traditional methods may overlook.Validation with the Goodwin model confirms the reliability of our observations.By integrating experimental data with theoretical models,this study provides new insights into the effects of tetrodotoxin(TTX)on neuronal complexities,contributing to the understanding of circadian rhythms.
文摘The construction projects’ dynamic and interconnected nature requires a comprehensive understanding of complexity during pre-construction. Traditional tools such as Gantt charts, CPM, and PERT often overlook uncertainties. This study identifies 20 complexity factors through expert interviews and literature, categorising them into six groups. The Analytical Hierarchy Process evaluated the significance of different factors, establishing their corresponding weights to enhance adaptive project scheduling. A system dynamics (SD) model is developed and tested to evaluate the dynamic behaviour of identified complexity factors. The model simulates the impact of complexity on total project duration (TPD), revealing significant deviations from initial deterministic estimates. Data collection and analysis for reliability tests, including normality and Cronbach alpha, to validate the model’s components and expert feedback. Sensitivity analysis confirmed a positive relationship between complexity and project duration, with higher complexity levels resulting in increased TPD. This relationship highlights the inadequacy of static planning approaches and underscores the importance of addressing complexity dynamically. The study provides a framework for enhancing planning systems through system dynamics and recommends expanding the model to ensure broader applicability in diverse construction projects.
基金supported by the National Natural Science Foundation of China(Grant Nos.62472149,62376089,62202147)Hubei Provincial Science and Technology Plan Project(2023BCB04100).
文摘Accurate traffic flow prediction has a profound impact on modern traffic management. Traffic flow has complex spatial-temporal correlations and periodicity, which poses difficulties for precise prediction. To address this problem, a Multi-head Self-attention and Spatial-Temporal Graph Convolutional Network (MSSTGCN) for multiscale traffic flow prediction is proposed. Firstly, to capture the hidden traffic periodicity of traffic flow, traffic flow is divided into three kinds of periods, including hourly, daily, and weekly data. Secondly, a graph attention residual layer is constructed to learn the global spatial features across regions. Local spatial-temporal dependence is captured by using a T-GCN module. Thirdly, a transformer layer is introduced to learn the long-term dependence in time. A position embedding mechanism is introduced to label position information for all traffic sequences. Thus, this multi-head self-attention mechanism can recognize the sequence order and allocate weights for different time nodes. Experimental results on four real-world datasets show that the MSSTGCN performs better than the baseline methods and can be successfully adapted to traffic prediction tasks.
文摘Binary sequences constructed by Legendre symbols are widely used in communication and cryptography since they have many good pseudo-random properties.In this paper,we determine the 2-adic complexity of the sum sequence of any k many Legendre sequences and show that the 2-adic complexity of the sum sequences of any k many Legendre sequences reaches the maximum by proving the case of k=2 and 3,which implies that the sum sequences can resist the attack of rational approximation algorithm.
基金supported by Zhejiang Provincial Natural Science Foundation of China(No.LTGS24D010004)the National Natural Science Foundation of China grant(No.42307064)+2 种基金the National Students’platform for innovation and entrepreneurship training program(No.202410346054)Hangzhou“Young science and technology talent cultivation”project(No.4305F45623004)the Fundamental Research Funds for Climbing Project from Hangzhou Normal University(No.KYQD-2023-217).
文摘Numerous studies have examined the impact ofwater quality degradation on bacterial community structure,yet insights into its effects on the bacterial ecological networks remain scarce.In this study,we investigated the diversity,composition,assembly patterns,ecological networks,and environmental determinants of bacterial communities across 20 ponds to understand the impact of water quality degradation.Our findings revealed that water quality degradation significantly reduces the α-diversity of bacterial communities in water samples,while sediment samples remain unaffected.Additionally,water quality deterioration increases the complexity of bacterial networks in water samples but reduces it in sediment samples.These shifts in bacterial communities were primarily governed by deterministic processes,with heterogeneous selection being particularly influential.Through redundancy analysis(RDA),multiple regression on matrices(MRM),and Mantel tests,we identified dissolved oxygen(DO),ammonium nitrogen(NH_(4)^(+)-N),and C/N ratio as key factors affecting the composition and network complexity of bacterial communities in both water and sediment.Overall,this study contributes a novel perspective on the effect ofwater quality deterioration on microbial ecosystems and provides valuable insights for improving ecological evaluations and biomonitoring practices related to water quality management.
基金supported by the Fundamental Research Funds of Chinese Academy of Forestry(Nos.CAFYBB2022SY037,CAFYBB2021ZA002 and CAFYBB2022QC002)the Basic Research Foundation of Yunnan Province(Grant No.202201AT070264).
文摘Soil microbial communities are key factors in maintaining ecosystem multifunctionality(EMF).However,the distribution patterns of bacterial diversity and how the different bacterial taxa and their diversity dimensions affect EMF remain largely unknown.Here,we investigated variation in three measures of diversity(alpha diversity,community composition and network complexity)among rare,intermediate,and abundant taxa across a latitudinal gradient spanning five forest plots in Yunnan Province,China and examined their contributions on EMF.We aimed to characterize the diversity distributions of bacterial groups across latitudes and to assess the differences in the mechanisms underlying their contributions to EMF.We found that multifaceted diversity(i.e.,diversity assessed by the three different metrics)of rare,intermediate,and abundant bacteria generally decreased with increasing latitude.More importantly,we found that rare bacterial taxa tended to be more diverse,but they contributed less to EMF than intermediate or abundant bacteria.Among the three dimensions of diversity we assessed,only community composition significantly affected EMF across all locations,while alpha diversity had a negative effect,and network complexity showed no significant impact.Our study further emphasizes the importance of intermediate and abundant bacterial taxa as well as community composition to EMF and provides a theoretical basis for investigating the mechanisms by which belowground microorganisms drive EMF along a latitudinal gradient.
文摘This study examined how psychological meaningfulness moderates job complexity and work-family conflict in Nigerian secondary school teachers.This study included 1694 teachers from 17 Nigerian secondary schools(female=69.54%,mean age=33.19,SD=6.44 years).The participants completed the Work-family Conflict Scale,Job Complexity Scale,and Psychological Meaningfulness Scale.Study design was cross-sectional.Hayes PROCESS macro analysis results indicate a higher work-family conflict with job complexity among the secondary school teachers.While psychological meaningfulness was not associated with work-family conflict,it moderated the link between job complexity and work-family conflict in secondary school teachers such that a meaningful work endorsement is associated with lower employee’s work-life conflict.Thesefindings point to the importance of job functions to quality of family life.The studyfindings also suggest a need for supporting psychological meaningfulness for healthy work related quality of family life based on balancing work and family role demands.
基金Supported by the Health Commission of Fuyang City,Anhui,China,No.FY2023-45Fuyang Municipal Science and Technology Bureau,Anhui,China,No.FK20245505+1 种基金Anhui Provincial Health Commission,No.AHWJ2023Baa20164Bengbu Medical University,No.2023byzd215.
文摘BACKGROUND Sigmoid colon cancer faces challenges due to anatomical diversity,including variable inferior mesenteric artery(IMA)branching and tumor localization complexities,which increase intraoperative risks.AIM To comprehensively evaluate the impact of three-dimensional(3D)visualization technology on enhancing surgical precision and safety,as well as optimizing perioperative outcomes in laparoscopic sigmoid cancer resection.METHODS A prospective cohort of 106 patients(January 2023 to December 2024)undergoing laparoscopic sigmoid cancer resection was divided into the 3D(n=55)group and the control(n=51)group.The 3D group underwent preoperative enhanced computed tomography reconstruction(3D Slicer 5.2.2&Mimics 19.0).3D reconstruction visualization navigation intraoperatively guided the following key steps:Tumor location,Toldt’s space dissection,IMA ligation level selection,regional lymph node dissection,and marginal artery preservation.Outcomes included operative parameters,lymph node yield,and recovery metrics.RESULTS The 3D group demonstrated a significantly shorter operative time(172.91±20.69 minutes vs 190.29±32.29 minutes;P=0.002),reduced blood loss(31.5±11.8 mL vs 44.1±23.4 mL,P=0.001),earlier postoperative flatus(2.23±0.54 days vs 2.53±0.61 days;P=0.013),shorter hospital length of stay(13.47±1.74 days vs 16.20±7.71 days;P=0.013),shorter postoperative length of stay(8.6±2.6 days vs 10.5±4.9 days;P=0.014),and earlier postoperative exhaust time(2.23±0.54 days vs 2.53±0.61 days;P=0.013).Furthermore,the 3D group exhibited a higher mean number of lymph nodes harvested(16.91±5.74 vs 14.45±5.66;P=0.030).CONCLUSION The 3D visualization technology effectively addresses sigmoid colon anatomical complexity through surgical navigation,improving procedural safety and efficiency.
基金supported by the National Key Research and Development Program of China(No.2022YFC2807500)Laoshan Laboratory(No.LSKJ202203201)+1 种基金the National Natural Science Foundation of China(Nos.42206147,42120104006 and 42176111)the Natural Science Foundation of Shandong Province(Nos.ZR2022QD046,ZR2021QD051).
文摘Ulva prolifera green tides are becoming aworldwide environmental problem,especially in the Yellow Sea,China.However,the effects of the occurrence of U.prolifera green tides on the community organization and stability of surrounding microbiomes have still not been de-termined.Here,the prokaryotic microbial community network stability and assembly char-acteristics were systematically analyzed and compared between the green tide and non-green tide periods.U.prolifera blooms weaken the community complexity and robustness of surrounding microbiomes,increasing fragmentation and decreasing diversity.Bacteria and archaea exhibited distinct community distributions and assembly patterns under the influ-ence of green tides,and bacterial communities were more sensitive to outbreaks of green tides.The bacterial communities exhibited a greater niche breadth and a lower phyloge-netic distance during the occurrence of U.prolifera green tides compared to those during the non-green tide period while archaeal communities remained unchanged,suggesting that the bacterial communities underwent stronger homogeneous selection and more sensitive to green tide blooms than the archaeal communities.Piecewise structural equation model analysis revealed that the different responses of major prokaryotic microbial groups,such as Cyanobacteria,to environmental variables during green tides,were influenced by the variations in pH and nitrate during green tides and correlated with the salinity gradient during the non-green tide period.This study elucidates the response of the adaptability,associations,and stability of surrounding microbiomes to outbreaks of U.prolifera green tides.
文摘Integrated Sensing and Communication(ISAC)is envisioned as a promising technology for Sixth-Generation(6G)wireless communications,which enables simultaneous high-rate communication and high-precision target localization.Compared to independent sensing and communication modules,dual-function ISAC could leverage the strengths of both communication and sensing in order to achieve cooperative gains.When considering the communication core network,ISAC system facilitates multiple communication devices to collaborate for networked sensing.This paper investigates such kind of cooperative ISAC systems with distributed transmitters and receivers to support non-connected and multi-target localization.Specifically,we introduce a Time of Arrival(TOA)based multi-target localization scheme,which leverages the bi-static range measurements between the transmitter,target,and receiver channels in order to achieve elliptical localization.To obtain the low-complexity localization,a two-stage search-refine localization methodology is proposed.In the first stage,we propose a Successive Greedy Grid-Search(SGGS)algorithm and a Successive-Cancellation-List Grid-Search(SCLGS)algorithm to address the Measurement-to-Target Association(MTA)problem with relatively low computational complexity.In the second stage,a linear approximation refinement algorithm is derived to facilitate high-precision localization.Simulation results are presented to validate the effectiveness and superiority of our proposed multi-target localization method.
文摘The authors regret that an error occurred during the preparation of their article:One of the official databases,which was used for functional trait collections,contained an incorrect term–'chametophytes'–for the life form category'chamaephytes'.Unfortunately,this incorrect term was used throughout the article following the nomenclature of this official database:in one instance in the main text,in Fig.3 and its caption,in Fig.5,and in two instances in the supplementary material.
基金Under the auspices of National Natural Science Foundation of China(No.42371061,U20A2083)。
文摘Coastal wetlands store large amounts of soil organic carbon(SOC),and have assumed key roles in mitigating increasing CO_(2)in the atmosphere.The ongoing debate about SOC stabilization mechanisms stems partly from our incomplete understanding of its complex chemical architecture at the molecular scale.Deciphering the molecular composition of soil organic matter is crucial for revealing mechanisms that govern SOC persistence.This study utilized the field sampling data from 2016 and aimed to characterize molecular composition of SOC in typical salt marsh(SM)and freshwater marsh(FM)in Louisiana coastal regions,USA by extending the application of graph networks with pyrolysis-gas chromatography-mass spectrometry,and then to quantify potential links between SOC persistence and molecular diversity and network complexity.The results revealed that SOC predominantly consisted of alkyl compounds(Alkyl),phenol(Ph),lignin(Lg),and aliphatic compounds,constituting 23.21%and 27.85%,17.84%and 21.55%,16.94%and 15.49%,17.20%and 15.93%of total ion chromatogram(TIC)in SM and FM wetlands,respectively.Molecular diversity in SM was higher than that in FM,while the network graph exhibited greater complexity in FM,featuring 167 and 123 nodes,and 1935 and 1982 edges in the network graphs of SOC from SM and FM,respectively.Correlation analysis confirmed positive relations between molecular diversity indices,network complexity,and abundance of stable carbon isotopes(δ^(13)C).The variance partitioning analysis(VPA)supplied that soil nutrients exerted the most significant control on SOC persistence.Molecular diversity and network complexity,when combined with soil nutrients,could explain 34%of the variances in SOC persistence.
文摘Visual question answering(VQA)is a multimodal task,involving a deep understanding of the image scene and the question’s meaning and capturing the relevant correlations between both modalities to infer the appropriate answer.In this paper,we propose a VQA system intended to answer yes/no questions about real-world images,in Arabic.To support a robust VQA system,we work in two directions:(1)Using deep neural networks to semantically represent the given image and question in a fine-grainedmanner,namely ResNet-152 and Gated Recurrent Units(GRU).(2)Studying the role of the utilizedmultimodal bilinear pooling fusion technique in the trade-o.between the model complexity and the overall model performance.Some fusion techniques could significantly increase the model complexity,which seriously limits their applicability for VQA models.So far,there is no evidence of how efficient these multimodal bilinear pooling fusion techniques are for VQA systems dedicated to yes/no questions.Hence,a comparative analysis is conducted between eight bilinear pooling fusion techniques,in terms of their ability to reduce themodel complexity and improve themodel performance in this case of VQA systems.Experiments indicate that these multimodal bilinear pooling fusion techniques have improved the VQA model’s performance,until reaching the best performance of 89.25%.Further,experiments have proven that the number of answers in the developed VQA system is a critical factor that a.ects the effectiveness of these multimodal bilinear pooling techniques in achieving their main objective of reducing the model complexity.The Multimodal Local Perception Bilinear Pooling(MLPB)technique has shown the best balance between the model complexity and its performance,for VQA systems designed to answer yes/no questions.
基金the National Science Fund for Distinguished Young Scholars of China (No.62025301)the National Natural Science Foundation of China (Nos.62273043 and 62373055)+1 种基金the China National Postdoctoral Program for Innovative Talents (No.BX20230461)the China Postdoctoral Science Foundation (No.2023M740249)。
文摘This paper investigates the spatial-temporal cooperative guidance problem for multiple flight vehicles without relying on time-to-go information.First,a two-stage cooperative guidance strategy,namely the cooperative guidance and the Proportional Navigation Guidance(PNG)stage strategy,is developed to realize the spatial-temporal constraints in two dimensions.At the former stage,two controllers are designed and superimposed to satisfy both impact time consensus and impact angle constraints.Once the convergent conditions are satisfied,the flight vehicles will switch to the PNG stage to ensure zero miss distance.To further extend the results to three dimensions,a planar pursuit guidance stage is additionally imposed at the beginning of guidance.Due to the inde-pendence of time-to-go estimation,the proposed guidance strategy possesses great performance in satisfying complex spatial-temporal constraints even under flight speed variation.Finally,several numerical simulations are implemented to verify the effectiveness and advantages of the proposed results under different scenarios.
基金This work was supported by the National Natural Science Foundation of China(Nos.61833013,61473012 and 62103335)Key Research Program of Jiangxi Province in China(No.20192BBEL50005).
文摘Forest fires pose a significant threat to human life and property,so the utilization of unmanned aircraft systems provides new ways for forest firefighting.Given the constrained load capacities of these aircraft,aerial refueling becomes crucial to extend their operational time and range.In order to address the complexities of firefighting missions involving multi-receiver and multi-tanker deployed from various airports,first,a fuel consumption calculation model for aerial refueling scheduling is established based on the receiver path.Then,two distinct methods,including an integrated one and a decomposed one,are designed to address the challenges of establishing refueling airspace and allocating tasks for tankers.Both methods aim to optimize total fuel consumption of the receivers and tankers within the aerial refueling scheduling framework.The optimization problem is established as nonlinear optimization models along with restrictions.The integrated method seamlessly combines refueling rendezvous point scheduling and tanker task allocation into unified process.It has a complete solution space and excels in optimizing total fuel consumption.The decomposed method,through the separation of rendezvous point scheduling and task allocation,achieves a reduced computational complexity.However,this comes at the cost of sacrificing optimality by excluding specific feasible solutions.Finally,numerical simulations are carried out to verify the feasibility and effectiveness of the proposed methods.These simulations yield insights crucial for the practical engineering application of both the integrated and decomposed methods in real-world scenarios.This comprehensive approach aims to enhance the efficiency of forest firefighting operations,mitigating the risks posed by forest fires to human life and property.
基金This work is partly supported by the National Key Research and Development Program of China(Grant No.2020YFB1805403)the National Natural Science Foundation of China(Grant No.62032002)the 111 Project(Grant No.B21049).
文摘In the Industrial Internet of Things(IIoT),sensors generate time series data to reflect the working state.When the systems are attacked,timely identification of outliers in time series is critical to ensure security.Although many anomaly detection methods have been proposed,the temporal correlation of the time series over the same sensor and the state(spatial)correlation between different sensors are rarely considered simultaneously in these methods.Owing to the superior capability of Transformer in learning time series features.This paper proposes a time series anomaly detection method based on a spatial-temporal network and an improved Transformer.Additionally,the methods based on graph neural networks typically include a graph structure learning module and an anomaly detection module,which are interdependent.However,in the initial phase of training,since neither of the modules has reached an optimal state,their performance may influence each other.This scenario makes the end-to-end training approach hard to effectively direct the learning trajectory of each module.This interdependence between the modules,coupled with the initial instability,may cause the model to find it hard to find the optimal solution during the training process,resulting in unsatisfactory results.We introduce an adaptive graph structure learning method to obtain the optimal model parameters and graph structure.Experiments on two publicly available datasets demonstrate that the proposed method attains higher anomaly detection results than other methods.
