Startups form an information network that reflects their growth trajectories through information flow channels established by shared investors.However,traditional static network metrics overlook temporal dynamics and ...Startups form an information network that reflects their growth trajectories through information flow channels established by shared investors.However,traditional static network metrics overlook temporal dynamics and rely on single indicators to assess startups’roles in predicting future success,failing to comprehensively capture topological variations and structural diversity.To address these limitations,we construct a temporal information network using 14547 investment records from 1013 global blockchain startups between 2004 and 2020,sourced from Crunchbase.We propose two dynamic methods to characterize the information flow:temporal random walk(sTRW)for modeling information flow trajectories and temporal betweenness centrality(tTBET)for identifying key information hubs.These methods enhance walk coverage while ensuring random stability,allowing for more effective identification of influential startups.By integrating sTRW and tTBET,we develop a comprehensive metric to evaluate a startup’s influence within the network.In experiments assessing startups’potential for future success—where successful startups are defined as those that have undergone M&A or IPO—incorporating this metric improves accuracy,recall,and F1 score by 0.035,0.035,and 0.042,respectively.Our findings indicate that information flow from key startups to others diminishes as the network distance increases.Additionally,successful startups generally exhibit higher information inflows than outflows,suggesting that actively seeking investment-related information contributes to startup growth.Our research provides valuable insights for formulating startup development strategies and offers practical guidance for market regulators.展开更多
Essential proteins are an indispensable part of cells and play an extremely significant role in genetic disease diagnosis and drug development.Therefore,the prediction of essential proteins has received extensive atte...Essential proteins are an indispensable part of cells and play an extremely significant role in genetic disease diagnosis and drug development.Therefore,the prediction of essential proteins has received extensive attention from researchers.Many centrality methods and machine learning algorithms have been proposed to predict essential proteins.Nevertheless,the topological characteristics learned by the centrality method are not comprehensive enough,resulting in low accuracy.In addition,machine learning algorithms need sufficient prior knowledge to select features,and the ability to solve imbalanced classification problems needs to be further strengthened.These two factors greatly affect the performance of predicting essential proteins.In this paper,we propose a deep learning framework based on temporal convolutional networks to predict essential proteins by integrating gene expression data and protein-protein interaction(PPI)network.We make use of the method of network embedding to automatically learn more abundant features of proteins in the PPI network.For gene expression data,we treat it as sequence data,and use temporal convolutional networks to extract sequence features.Finally,the two types of features are integrated and put into the multi-layer neural network to complete the final classification task.The performance of our method is evaluated by comparing with seven centrality methods,six machine learning algorithms,and two deep learning models.The results of the experiment show that our method is more effective than the comparison methods for predicting essential proteins.展开更多
To enhance the denoising performance of event-based sensors,we introduce a clustering-based temporal deep neural network denoising method(CBTDNN).Firstly,to cluster the sensor output data and obtain the respective clu...To enhance the denoising performance of event-based sensors,we introduce a clustering-based temporal deep neural network denoising method(CBTDNN).Firstly,to cluster the sensor output data and obtain the respective cluster centers,a combination of density-based spatial clustering of applications with noise(DBSCAN)and Kmeans++is utilized.Subsequently,long short-term memory(LSTM)is employed to fit and yield optimized cluster centers with temporal information.Lastly,based on the new cluster centers and denoising ratio,a radius threshold is set,and noise points beyond this threshold are removed.The comprehensive denoising metrics F1_score of CBTDNN have achieved 0.8931,0.7735,and 0.9215 on the traffic sequences dataset,pedestrian detection dataset,and turntable dataset,respectively.And these metrics demonstrate improvements of 49.90%,33.07%,19.31%,and 22.97%compared to four contrastive algorithms,namely nearest neighbor(NNb),nearest neighbor with polarity(NNp),Autoencoder,and multilayer perceptron denoising filter(MLPF).These results demonstrate that the proposed method enhances the denoising performance of event-based sensors.展开更多
Physics-informed neural networks(PINNs)have become an attractive machine learning framework for obtaining solutions to partial differential equations(PDEs).PINNs embed initial,boundary,and PDE constraints into the los...Physics-informed neural networks(PINNs)have become an attractive machine learning framework for obtaining solutions to partial differential equations(PDEs).PINNs embed initial,boundary,and PDE constraints into the loss function.The performance of PINNs is generally affected by both training and sampling.Specifically,training methods focus on how to overcome the training difficulties caused by the special PDE residual loss of PINNs,and sampling methods are concerned with the location and distribution of the sampling points upon which evaluations of PDE residual loss are accomplished.However,a common problem among these original PINNs is that they omit special temporal information utilization during the training or sampling stages when dealing with an important PDE category,namely,time-dependent PDEs,where temporal information plays a key role in the algorithms used.There is one method,called Causal PINN,that considers temporal causality at the training level but not special temporal utilization at the sampling level.Incorporating temporal knowledge into sampling remains to be studied.To fill this gap,we propose a novel temporal causality-based adaptive sampling method that dynamically determines the sampling ratio according to both PDE residual and temporal causality.By designing a sampling ratio determined by both residual loss and temporal causality to control the number and location of sampled points in each temporal sub-domain,we provide a practical solution by incorporating temporal information into sampling.Numerical experiments of several nonlinear time-dependent PDEs,including the Cahn–Hilliard,Korteweg–de Vries,Allen–Cahn and wave equations,show that our proposed sampling method can improve the performance.We demonstrate that using such a relatively simple sampling method can improve prediction performance by up to two orders of magnitude compared with the results from other methods,especially when points are limited.展开更多
Predicting human motion based on historical motion sequences is a fundamental problem in computer vision,which is at the core of many applications.Existing approaches primarily focus on encoding spatial dependencies a...Predicting human motion based on historical motion sequences is a fundamental problem in computer vision,which is at the core of many applications.Existing approaches primarily focus on encoding spatial dependencies among human joints while ignoring the temporal cues and the complex relationships across non-consecutive frames.These limitations hinder the model’s ability to generate accurate predictions over longer time horizons and in scenarios with complex motion patterns.To address the above problems,we proposed a novel multi-level spatial and temporal learning model,which consists of a Cross Spatial Dependencies Encoding Module(CSM)and a Dynamic Temporal Connection Encoding Module(DTM).Specifically,the CSM is designed to capture complementary local and global spatial dependent information at both the joint level and the joint pair level.We further present DTM to encode diverse temporal evolution contexts and compress motion features to a deep level,enabling the model to capture both short-term and long-term dependencies efficiently.Extensive experiments conducted on the Human 3.6M and CMU Mocap datasets demonstrate that our model achieves state-of-the-art performance in both short-term and long-term predictions,outperforming existing methods by up to 20.3% in accuracy.Furthermore,ablation studies confirm the significant contributions of the CSM and DTM in enhancing prediction accuracy.展开更多
Predicting player performance in sports is a critical challenge with significant implications for team success,fan engagement,and financial outcomes.Although,inMajor League Baseball(MLB),statistical methodologies such...Predicting player performance in sports is a critical challenge with significant implications for team success,fan engagement,and financial outcomes.Although,inMajor League Baseball(MLB),statistical methodologies such as sabermetrics have been widely used,the dynamic nature of sports makes accurate performance prediction a difficult task.Enhanced forecasts can provide immense value to team managers by aiding strategic player contract and acquisition decisions.This study addresses this challenge by employing the temporal fusion transformer(TFT),an advanced and cutting-edge deep learning model for complex data,to predict pitchers’earned run average(ERA),a key metric in baseball performance analysis.The performance of the TFT model is evaluated against recurrent neural network-based approaches and existing projection systems.In experimental results,the TFT based model consistently outperformed its counterparts,demonstrating superior accuracy in pitcher performance prediction.By leveraging the advanced capabilities of TFT,this study contributes to more precise player evaluations and improves strategic planning in baseball.展开更多
Thrust estimation is a significant part of aeroengine thrust control systems.The traditional estimation methods are either low in accuracy or large in computation.To further improve the estimation effect,a thrust esti...Thrust estimation is a significant part of aeroengine thrust control systems.The traditional estimation methods are either low in accuracy or large in computation.To further improve the estimation effect,a thrust estimator based on Multi-layer Residual Temporal Convolutional Network(M-RTCN)is proposed.To solve the problem of dead Rectified Linear Unit(ReLU),the proposed method uses the Gaussian Error Linear Unit(GELU)activation function instead of ReLU in residual block.Then the overall architecture of the multi-layer convolutional network is adjusted by using residual connections,so that the network thrust estimation effect and memory consumption are further improved.Moreover,the comparison with seven other methods shows that the proposed method has the advantages of higher estimation accuracy and faster convergence speed.Furthermore,six neural network models are deployed in the embedded controller of the micro-turbojet engine.The Hardware-in-the-Loop(HIL)testing results demonstrate the superiority of M-RTCN in terms of estimation accuracy,memory occupation and running time.Finally,an ignition verification is conducted to confirm the expected thrust estimation and real-time performance.展开更多
Time series forecasting plays an important role in various fields, such as energy, finance, transport, and weather. Temporal convolutional networks (TCNs) based on dilated causal convolution have been widely used in t...Time series forecasting plays an important role in various fields, such as energy, finance, transport, and weather. Temporal convolutional networks (TCNs) based on dilated causal convolution have been widely used in time series forecasting. However, two problems weaken the performance of TCNs. One is that in dilated casual convolution, causal convolution leads to the receptive fields of outputs being concentrated in the earlier part of the input sequence, whereas the recent input information will be severely lost. The other is that the distribution shift problem in time series has not been adequately solved. To address the first problem, we propose a subsequence-based dilated convolution method (SDC). By using multiple convolutional filters to convolve elements of neighboring subsequences, the method extracts temporal features from a growing receptive field via a growing subsequence rather than a single element. Ultimately, the receptive field of each output element can cover the whole input sequence. To address the second problem, we propose a difference and compensation method (DCM). The method reduces the discrepancies between and within the input sequences by difference operations and then compensates the outputs for the information lost due to difference operations. Based on SDC and DCM, we further construct a temporal subsequence-based convolutional network with difference (TSCND) for time series forecasting. The experimental results show that TSCND can reduce prediction mean squared error by 7.3% and save runtime, compared with state-of-the-art models and vanilla TCN.展开更多
Social networks like Facebook, X (Twitter), and LinkedIn provide an interaction and communication environment for users to generate and share content, allowing for the observation of social behaviours in the digital w...Social networks like Facebook, X (Twitter), and LinkedIn provide an interaction and communication environment for users to generate and share content, allowing for the observation of social behaviours in the digital world. These networks can be viewed as a collection of nodes and edges, where users and their interactions are represented as nodes and the connections between them as edges. Understanding the factors that contribute to the formation of these edges is important for studying network structure and processes. This knowledge can be applied to various areas such as identifying communities, recommending friends, and targeting online advertisements. Several factors, including node popularity and friends-of-friends relationships, influence edge formation and network growth. This research focuses on the temporal activity of nodes and its impact on edge formation. Specifically, the study examines how the minimum age of friends-of-friends edges and the average age of all edges connected to potential target nodes influence the formation of network edges. Discrete choice analysis is used to analyse the combined effect of these temporal factors and other well-known attributes like node degree (i.e., the number of connections a node has) and network distance between nodes. The findings reveal that temporal properties have a similar impact as network proximity in predicting the creation of links. By incorporating temporal features into the models, the accuracy of link prediction can be further improved.展开更多
Traffic flow forecasting plays a crucial role and is the key technology to realize dynamic traffic guidance and active traffic control in intelligent traffic systems(ITS).Aiming at the complex local and global spatial...Traffic flow forecasting plays a crucial role and is the key technology to realize dynamic traffic guidance and active traffic control in intelligent traffic systems(ITS).Aiming at the complex local and global spatial-temporal dynamic characteristics of traffic flow,this paper proposes a new traffic flow forecasting model spatial-temporal attention graph neural network(STA-GNN)by combining at-tention mechanism(AM)and spatial-temporal convolutional network.The model learns the hidden dynamic local spatial correlations of the traffic network by combining the dynamic adjacency matrix constructed by the graph learning layer with the graph convolutional network(GCN).The local tem-poral correlations of traffic flow at different scales are extracted by stacking multiple convolutional kernels in temporal convolutional network(TCN).And the global spatial-temporal dependencies of long-time sequences of traffic flow are captured by the spatial-temporal attention mechanism(STAtt),which enhances the global spatial-temporal modeling and the representational ability of model.The experimental results on two datasets,METR-LA and PEMS-BAY,show the proposed STA-GNN model outperforms the common baseline models in forecasting accuracy.展开更多
Lifelines are critical infrastructure systems characterized by a high level of interdependency that can lead to cascading failures after any disaster.Many approaches can be used to analyze infrastructural interdepende...Lifelines are critical infrastructure systems characterized by a high level of interdependency that can lead to cascading failures after any disaster.Many approaches can be used to analyze infrastructural interdependencies,but they are usually not able to describe the sequence of events during emergencies.Therefore,interdependencies need to be modeled also taking into account the time effects.The methodology proposed in this paper is based on a modified version of the Input-output Inoperability Model and returns the probabilities of failure for each node of the system.Lifelines are modeled using graph theory,while perturbations,representing a natural or man-made disaster,are applied to the elements of the network following predetermined rules.The cascading effects among interdependent networks have been simulated using a spatial multilayer approach,while the use of an adjacency tensor allows to consider the temporal dimension and its effects.The method has been tested on a case study based on the 2011 Fukushima Dai-ichi nuclear disaster.Different configurations of the system have been analyzed and their probability of occurrence evaluated.Two models of the nuclear power plant have been developed to evaluate how different spatial scales and levels of detail affect the results.展开更多
The air transportation system has a critical impact on the global economy.While the system reliability is essential for the operational management of air traffic,it remains challenging to understand the network reliab...The air transportation system has a critical impact on the global economy.While the system reliability is essential for the operational management of air traffic,it remains challenging to understand the network reliability of the air transportation system.This paper focuses on how the global air traffic is integrated from local scale along with operational time.The integration process of air traffic into a temporally connected network is viewed as percolation process by increasing the integration time constantly.The critical integration time TPwhich is found during the integration process can measure the global reliability of air traffic.The critical links at TPare also identified,the delay of which will influence the global integration of the airport network.These findings may provide insights on the reliability management for the temporal airport network.展开更多
Intractable delays occur in air traffic due to the imbalance between ever-increasing air traffic demand and limited airspace capacity.As air traffic is associated with complex air transport systems,delays can be magni...Intractable delays occur in air traffic due to the imbalance between ever-increasing air traffic demand and limited airspace capacity.As air traffic is associated with complex air transport systems,delays can be magnified and propagated throughout these systems,resulting in the emergent behavior known as delay propagation.An understanding of delay propagation dynamics is pertinent to modern air traffic management.In this work,we present a complex network perspective of delay propagation dynamics.Specifically,we model air traffic scenarios using spatial–temporal networks with airports as the nodes.To establish the dynamic edges between the nodes,we develop a delay propagation method and apply it to a given set of air traffic schedules.Based on the constructed spatial-temporal networks,we suggest three metrics-magnitude,severity,and speed-to gauge delay propagation dynamics.To validate the effectiveness of the proposed method,we carry out case studies on domestic flights in the Southeastern Asia region(SAR)and the United States.Experiments demonstrate that the propagation magnitude in terms of the number of flights affected by delay propagation and the amount of propagated delays for the US traffic are respectively five and ten times those of the SAR.Experiments further reveal that the propagation speed for US traffic is eight times faster than that of the SAR.The delay propagation dynamics reveal that about six hub airports in the SAR have significant propagated delays,while the situation in the United States is considerably worse,with a corresponding number of around 16.This work provides a potent tool for tracing the evolution of air traffic delays.展开更多
In this paper,we investigate a spectrumsensing system in the presence of a satellite,where the satellite works as a sensing node.Considering the conventional energy detection method is sensitive to the noise uncertain...In this paper,we investigate a spectrumsensing system in the presence of a satellite,where the satellite works as a sensing node.Considering the conventional energy detection method is sensitive to the noise uncertainty,thus,a temporal convolutional network(TCN)based spectrum-sensing method is designed to eliminate the effect of the noise uncertainty and improve the performance of spectrum sensing,relying on the offline training and the online detection stages.Specifically,in the offline training stage,spectrum data captured by the satellite is sent to the TCN deployed on the gateway for training purpose.Moreover,in the online detection stage,the well trained TCN is utilized to perform real-time spectrum sensing,which can upgrade spectrum-sensing performance by exploiting the temporal features.Additionally,simulation results demonstrate that the proposed method achieves a higher probability of detection than that of the conventional energy detection(ED),the convolutional neural network(CNN),and deep neural network(DNN).Furthermore,the proposed method outperforms the CNN and the DNN in terms of a lower computational complexity.展开更多
Different approaches have been established for applications of social and complex networks involving biological systems, passing through collaborative systems in knowledge networks and organizational systems. In this ...Different approaches have been established for applications of social and complex networks involving biological systems, passing through collaborative systems in knowledge networks and organizational systems. In this latter application, we highlight the studies focused on the diffusion of information and knowledge in networks. However, most of the time, the propagation of information in these networks and the resulting process of creation and diffusion of knowledge, have been studied from static perspectives. Additionally, the very concept of diffusion inevitably implies the inclusion of the temporal dimension, due to that it is an essentially dynamic process. Although static analysis provides an important perspective in structural terms, the behavioral view that reflects the evolution of the relationships of the members of these networks over time is best described by temporal networks. Thus, it is possible to analyze both the information flow and the structural changes that occur over time, which influences the dynamics of the creation and diffusion of knowledge. This article describes the computational modeling used to elucidate the creation and diffusion of knowledge in temporal networks formed to execute software maintenance and construction projects, for the period between 2007 and 2013, in the SERVIÇO FEDERAL DE PROCESSAMENTO DE DADOS (FEDERAL DATA PROCESSING SERVICE-SERPRO)—a public organization that provides information and communication technology services. The methodological approach adopted for the study was based on techniques for analyzing social and complex networks and on the complementary extensions that address temporal modeling of these networks. We present an exploratory longitudinal study that enabled a dynamic and structural analysis of the knowledge networks formed by members of software maintenance and development project teams between 2007 and 2013. The study enabled identification of knowledge categories throughout this period, in addition to the determination that the networks have a structure with small-world and scale-free models. Finally, we concluded that, in general, the topologies of the networks studies had characteristics for facilitating the flow of knowledge within the organization.展开更多
Carbon source is an important factor of biological treatment systems, the effects of which on their temporal community assembly patterns are not sufficiently understood currently.In this study, the temporal dynamics a...Carbon source is an important factor of biological treatment systems, the effects of which on their temporal community assembly patterns are not sufficiently understood currently.In this study, the temporal dynamics and driving mechanisms of the communities in three parallel bioreactors for low-concentration coking wastewater(CWW) treatment with differing carbon source concentrations(S0 with no glucose addition, S1 with 200 mg/L glucose addition and S2 with 400 mg/L glucose addition) were comprehensively studied. Highthroughput sequencing and bioinformatics analyses including network analysis and Infer Community Assembly Mechanisms by Phylogenetic bin-based null model(iCAMP) were used. The communities of three systems showed turnover rates of 0.0029~0.0034 every 15days. Network analysis results showed that the S0 network showed higher positive correlation proportion(71.43%) and clustering coefficient(0.33), suggesting that carbon source shortage in S0 promoted interactions and cooperation of microbes. The neutral community model analysis showed that the immigration rate increased from 0.5247 in S0 to 0.6478in S2. The iCAMP analysis results showed that drift(45.89%) and homogeneous selection(31.68%) dominated in driving the assembly of all the investigated microbial communities.The contribution of homogeneous selection increased with the increase of carbon source concentrations, from 27.92% in S0 to 36.08% in S2. The OTUs participating in aerobic respiration and tricarboxylic acid(TCA) cycle were abundant among the bins mainly affected by deterministic processes, while those related to the metabolism of refractory organic pollutants in CWW such as alkanes, benzenes and phenols were abundant in the bins dominated by stochastic processes.展开更多
Random access is a well-known multiple access method for uncoordinated communication nodes.Existing work mainly focuses on optimizing iterative access protocols,assuming that packets are corrupted once they are collid...Random access is a well-known multiple access method for uncoordinated communication nodes.Existing work mainly focuses on optimizing iterative access protocols,assuming that packets are corrupted once they are collided,or that feedback is available and can be exploited.In practice,a packet may still be able to be recovered successfully even when collided with other packets.System design and performance analysis under such a situation,particularly when the details of collision are taken into consideration,are less known.In this paper,we provide a framework for analytically evaluating the actual detection performance in a random temporal multiple access system where nodes can only transmit.Explicit expressions are provided for collision probability and signal to interference and noise ratio(SINR)when different numbers of packets are collided.We then discuss and compare two receiver options for the AP,and provide detailed receiver design for the premium one.In particular,we propose a synchronization scheme which can largely reduce the preamble length.We also demonstrate that system performance could be a convex function of preamble length both analytically and via simulation,as well as the forward error correction(FEC)coding rate.展开更多
Since the oil production of single well in water flooding reservoir varies greatly and is hard to predict, an oil production prediction method of single well based on temporal convolutional network(TCN) is proposed an...Since the oil production of single well in water flooding reservoir varies greatly and is hard to predict, an oil production prediction method of single well based on temporal convolutional network(TCN) is proposed and verified. This method is started from data processing, the correspondence between water injectors and oil producers is determined according to the influence radius of the water injectors, the influence degree of a water injector on an oil producer in the month concerned is added as a model feature, and a Random Forest(RF) model is built to fill the dynamic data of water flooding. The single well history is divided into 4 stages according to its water cut, that is, low water cut, middle water cut, high water cut and extra-high water cut stages. In each stage, a TCN based prediction model is established, hyperparameters of the model are optimized by the Sparrow Search Algorithm(SSA). Finally, the models of the 4 stages are integrated into one whole-life model of the well for production prediction. The application of this method in Daqing Oilfield, NE China shows that:(1) Compared with conventional data processing methods, the data obtained by this processing method are more close to the actual production, and the data set obtained is more authentic and complete.(2) The TCN model has higher prediction accuracy than other 11 models such as Long Short Term Memory(LSTM).(3) Compared with the conventional full-life-cycle models, the model of integrated stages can significantly reduce the error of production prediction.展开更多
Influence maximization of temporal social networks(IMT)is a problem that aims to find the most influential set of nodes in the temporal network so that their information can be the most widely spread.To solve the IMT ...Influence maximization of temporal social networks(IMT)is a problem that aims to find the most influential set of nodes in the temporal network so that their information can be the most widely spread.To solve the IMT problem,we propose an influence maximization algorithm based on an improved K-shell method,namely improved K-shell in temporal social networks(KT).The algorithm takes into account the global and local structures of temporal social networks.First,to obtain the kernel value Ks of each node,in the global scope,it layers the network according to the temporal characteristic of nodes by improving the K-shell method.Then,in the local scope,the calculation method of comprehensive degree is proposed to weigh the influence of nodes.Finally,the node with the highest comprehensive degree in each core layer is selected as the seed.However,the seed selection strategy of KT can easily lose some influential nodes.Thus,by optimizing the seed selection strategy,this paper proposes an efficient heuristic algorithm called improved K-shell in temporal social networks for influence maximization(KTIM).According to the hierarchical distribution of cores,the algorithm adds nodes near the central core to the candidate seed set.It then searches for seeds in the candidate seed set according to the comprehensive degree.Experiments showthatKTIMis close to the best performing improved method for influence maximization of temporal graph(IMIT)algorithm in terms of effectiveness,but runs at least an order of magnitude faster than it.Therefore,considering the effectiveness and efficiency simultaneously in temporal social networks,the KTIM algorithm works better than other baseline algorithms.展开更多
This paper integrates genetic algorithm and neura l network techniques to build new temporal predicting analysis tools for geographic information system (GIS). These new GIS tools can be readily applied in a practical...This paper integrates genetic algorithm and neura l network techniques to build new temporal predicting analysis tools for geographic information system (GIS). These new GIS tools can be readily applied in a practical and appropriate manner in spatial and temp oral research to patch the gaps in GIS data mining and knowledge discovery functions. The specific achievement here is the integration of related artificial intellig ent technologies into GIS software to establish a conceptual spatial and temporal analysis framework. And, by using this framework to develop an artificial intelligent spatial and tempor al information analyst (ASIA) system which then is fully utilized in the existin g GIS package. This study of air pollutants forecasting provides a geographical practical case to prove the rationalization and justness of the conceptual tempo ral analysis framework.展开更多
基金the funding from the National Natural Science Foundation of China(Grant Nos.42001236,71991481,and 71991480)Young Elite Scientist Sponsor-ship Program by Bast(Grant No.BYESS2023413)。
文摘Startups form an information network that reflects their growth trajectories through information flow channels established by shared investors.However,traditional static network metrics overlook temporal dynamics and rely on single indicators to assess startups’roles in predicting future success,failing to comprehensively capture topological variations and structural diversity.To address these limitations,we construct a temporal information network using 14547 investment records from 1013 global blockchain startups between 2004 and 2020,sourced from Crunchbase.We propose two dynamic methods to characterize the information flow:temporal random walk(sTRW)for modeling information flow trajectories and temporal betweenness centrality(tTBET)for identifying key information hubs.These methods enhance walk coverage while ensuring random stability,allowing for more effective identification of influential startups.By integrating sTRW and tTBET,we develop a comprehensive metric to evaluate a startup’s influence within the network.In experiments assessing startups’potential for future success—where successful startups are defined as those that have undergone M&A or IPO—incorporating this metric improves accuracy,recall,and F1 score by 0.035,0.035,and 0.042,respectively.Our findings indicate that information flow from key startups to others diminishes as the network distance increases.Additionally,successful startups generally exhibit higher information inflows than outflows,suggesting that actively seeking investment-related information contributes to startup growth.Our research provides valuable insights for formulating startup development strategies and offers practical guidance for market regulators.
基金the National Natural Science Foundation of China(Nos.11861045 and 62162040)。
文摘Essential proteins are an indispensable part of cells and play an extremely significant role in genetic disease diagnosis and drug development.Therefore,the prediction of essential proteins has received extensive attention from researchers.Many centrality methods and machine learning algorithms have been proposed to predict essential proteins.Nevertheless,the topological characteristics learned by the centrality method are not comprehensive enough,resulting in low accuracy.In addition,machine learning algorithms need sufficient prior knowledge to select features,and the ability to solve imbalanced classification problems needs to be further strengthened.These two factors greatly affect the performance of predicting essential proteins.In this paper,we propose a deep learning framework based on temporal convolutional networks to predict essential proteins by integrating gene expression data and protein-protein interaction(PPI)network.We make use of the method of network embedding to automatically learn more abundant features of proteins in the PPI network.For gene expression data,we treat it as sequence data,and use temporal convolutional networks to extract sequence features.Finally,the two types of features are integrated and put into the multi-layer neural network to complete the final classification task.The performance of our method is evaluated by comparing with seven centrality methods,six machine learning algorithms,and two deep learning models.The results of the experiment show that our method is more effective than the comparison methods for predicting essential proteins.
基金supported by the National Natural Science Foundation of China(No.62134004).
文摘To enhance the denoising performance of event-based sensors,we introduce a clustering-based temporal deep neural network denoising method(CBTDNN).Firstly,to cluster the sensor output data and obtain the respective cluster centers,a combination of density-based spatial clustering of applications with noise(DBSCAN)and Kmeans++is utilized.Subsequently,long short-term memory(LSTM)is employed to fit and yield optimized cluster centers with temporal information.Lastly,based on the new cluster centers and denoising ratio,a radius threshold is set,and noise points beyond this threshold are removed.The comprehensive denoising metrics F1_score of CBTDNN have achieved 0.8931,0.7735,and 0.9215 on the traffic sequences dataset,pedestrian detection dataset,and turntable dataset,respectively.And these metrics demonstrate improvements of 49.90%,33.07%,19.31%,and 22.97%compared to four contrastive algorithms,namely nearest neighbor(NNb),nearest neighbor with polarity(NNp),Autoencoder,and multilayer perceptron denoising filter(MLPF).These results demonstrate that the proposed method enhances the denoising performance of event-based sensors.
基金Project supported by the Key National Natural Science Foundation of China(Grant No.62136005)the National Natural Science Foundation of China(Grant Nos.61922087,61906201,and 62006238)。
文摘Physics-informed neural networks(PINNs)have become an attractive machine learning framework for obtaining solutions to partial differential equations(PDEs).PINNs embed initial,boundary,and PDE constraints into the loss function.The performance of PINNs is generally affected by both training and sampling.Specifically,training methods focus on how to overcome the training difficulties caused by the special PDE residual loss of PINNs,and sampling methods are concerned with the location and distribution of the sampling points upon which evaluations of PDE residual loss are accomplished.However,a common problem among these original PINNs is that they omit special temporal information utilization during the training or sampling stages when dealing with an important PDE category,namely,time-dependent PDEs,where temporal information plays a key role in the algorithms used.There is one method,called Causal PINN,that considers temporal causality at the training level but not special temporal utilization at the sampling level.Incorporating temporal knowledge into sampling remains to be studied.To fill this gap,we propose a novel temporal causality-based adaptive sampling method that dynamically determines the sampling ratio according to both PDE residual and temporal causality.By designing a sampling ratio determined by both residual loss and temporal causality to control the number and location of sampled points in each temporal sub-domain,we provide a practical solution by incorporating temporal information into sampling.Numerical experiments of several nonlinear time-dependent PDEs,including the Cahn–Hilliard,Korteweg–de Vries,Allen–Cahn and wave equations,show that our proposed sampling method can improve the performance.We demonstrate that using such a relatively simple sampling method can improve prediction performance by up to two orders of magnitude compared with the results from other methods,especially when points are limited.
基金supported by the Urgent Need for Overseas Talent Project of Jiangxi Province(Grant No.20223BCJ25040)the Thousand Talents Plan of Jiangxi Province(Grant No.jxsg2023101085)+3 种基金the National Natural Science Foundation of China(Grant No.62106093)the Natural Science Foundation of Jiangxi(Grant Nos.20224BAB212011,20232BAB212008,20242BAB25078,and 20232BAB202051)The Youth Talent Cultivation Innovation Fund Project of Nanchang University(Grant No.XX202506030015)funded by Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2025R759),Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘Predicting human motion based on historical motion sequences is a fundamental problem in computer vision,which is at the core of many applications.Existing approaches primarily focus on encoding spatial dependencies among human joints while ignoring the temporal cues and the complex relationships across non-consecutive frames.These limitations hinder the model’s ability to generate accurate predictions over longer time horizons and in scenarios with complex motion patterns.To address the above problems,we proposed a novel multi-level spatial and temporal learning model,which consists of a Cross Spatial Dependencies Encoding Module(CSM)and a Dynamic Temporal Connection Encoding Module(DTM).Specifically,the CSM is designed to capture complementary local and global spatial dependent information at both the joint level and the joint pair level.We further present DTM to encode diverse temporal evolution contexts and compress motion features to a deep level,enabling the model to capture both short-term and long-term dependencies efficiently.Extensive experiments conducted on the Human 3.6M and CMU Mocap datasets demonstrate that our model achieves state-of-the-art performance in both short-term and long-term predictions,outperforming existing methods by up to 20.3% in accuracy.Furthermore,ablation studies confirm the significant contributions of the CSM and DTM in enhancing prediction accuracy.
基金supported by SKKU Global Research Platform Research Fund,Sungkyunkwan University,2024-2025.
文摘Predicting player performance in sports is a critical challenge with significant implications for team success,fan engagement,and financial outcomes.Although,inMajor League Baseball(MLB),statistical methodologies such as sabermetrics have been widely used,the dynamic nature of sports makes accurate performance prediction a difficult task.Enhanced forecasts can provide immense value to team managers by aiding strategic player contract and acquisition decisions.This study addresses this challenge by employing the temporal fusion transformer(TFT),an advanced and cutting-edge deep learning model for complex data,to predict pitchers’earned run average(ERA),a key metric in baseball performance analysis.The performance of the TFT model is evaluated against recurrent neural network-based approaches and existing projection systems.In experimental results,the TFT based model consistently outperformed its counterparts,demonstrating superior accuracy in pitcher performance prediction.By leveraging the advanced capabilities of TFT,this study contributes to more precise player evaluations and improves strategic planning in baseball.
基金co-supported by the National Natural Science Foundation of China(Nos.61890920,61890921)。
文摘Thrust estimation is a significant part of aeroengine thrust control systems.The traditional estimation methods are either low in accuracy or large in computation.To further improve the estimation effect,a thrust estimator based on Multi-layer Residual Temporal Convolutional Network(M-RTCN)is proposed.To solve the problem of dead Rectified Linear Unit(ReLU),the proposed method uses the Gaussian Error Linear Unit(GELU)activation function instead of ReLU in residual block.Then the overall architecture of the multi-layer convolutional network is adjusted by using residual connections,so that the network thrust estimation effect and memory consumption are further improved.Moreover,the comparison with seven other methods shows that the proposed method has the advantages of higher estimation accuracy and faster convergence speed.Furthermore,six neural network models are deployed in the embedded controller of the micro-turbojet engine.The Hardware-in-the-Loop(HIL)testing results demonstrate the superiority of M-RTCN in terms of estimation accuracy,memory occupation and running time.Finally,an ignition verification is conducted to confirm the expected thrust estimation and real-time performance.
基金supported by the National Key Research and Development Program of China(No.2018YFB2101300)the National Natural Science Foundation of China(Grant No.61871186)the Dean’s Fund of Engineering Research Center of Software/Hardware Co-Design Technology and Application,Ministry of Education(East China Normal University).
文摘Time series forecasting plays an important role in various fields, such as energy, finance, transport, and weather. Temporal convolutional networks (TCNs) based on dilated causal convolution have been widely used in time series forecasting. However, two problems weaken the performance of TCNs. One is that in dilated casual convolution, causal convolution leads to the receptive fields of outputs being concentrated in the earlier part of the input sequence, whereas the recent input information will be severely lost. The other is that the distribution shift problem in time series has not been adequately solved. To address the first problem, we propose a subsequence-based dilated convolution method (SDC). By using multiple convolutional filters to convolve elements of neighboring subsequences, the method extracts temporal features from a growing receptive field via a growing subsequence rather than a single element. Ultimately, the receptive field of each output element can cover the whole input sequence. To address the second problem, we propose a difference and compensation method (DCM). The method reduces the discrepancies between and within the input sequences by difference operations and then compensates the outputs for the information lost due to difference operations. Based on SDC and DCM, we further construct a temporal subsequence-based convolutional network with difference (TSCND) for time series forecasting. The experimental results show that TSCND can reduce prediction mean squared error by 7.3% and save runtime, compared with state-of-the-art models and vanilla TCN.
文摘Social networks like Facebook, X (Twitter), and LinkedIn provide an interaction and communication environment for users to generate and share content, allowing for the observation of social behaviours in the digital world. These networks can be viewed as a collection of nodes and edges, where users and their interactions are represented as nodes and the connections between them as edges. Understanding the factors that contribute to the formation of these edges is important for studying network structure and processes. This knowledge can be applied to various areas such as identifying communities, recommending friends, and targeting online advertisements. Several factors, including node popularity and friends-of-friends relationships, influence edge formation and network growth. This research focuses on the temporal activity of nodes and its impact on edge formation. Specifically, the study examines how the minimum age of friends-of-friends edges and the average age of all edges connected to potential target nodes influence the formation of network edges. Discrete choice analysis is used to analyse the combined effect of these temporal factors and other well-known attributes like node degree (i.e., the number of connections a node has) and network distance between nodes. The findings reveal that temporal properties have a similar impact as network proximity in predicting the creation of links. By incorporating temporal features into the models, the accuracy of link prediction can be further improved.
基金Supported by the Key R&D Program of Gansu Province(No.23YFGA0063)the National Natural Science Foundation of China(No.62363022,61663021)+1 种基金the Natural Science Foundation of Gansu Province(No.22JR5RA226,23JRRA886)the Gansu Provincial De-partment of Education:Industrial Support Plan Project(No.2023CYZC-35).
文摘Traffic flow forecasting plays a crucial role and is the key technology to realize dynamic traffic guidance and active traffic control in intelligent traffic systems(ITS).Aiming at the complex local and global spatial-temporal dynamic characteristics of traffic flow,this paper proposes a new traffic flow forecasting model spatial-temporal attention graph neural network(STA-GNN)by combining at-tention mechanism(AM)and spatial-temporal convolutional network.The model learns the hidden dynamic local spatial correlations of the traffic network by combining the dynamic adjacency matrix constructed by the graph learning layer with the graph convolutional network(GCN).The local tem-poral correlations of traffic flow at different scales are extracted by stacking multiple convolutional kernels in temporal convolutional network(TCN).And the global spatial-temporal dependencies of long-time sequences of traffic flow are captured by the spatial-temporal attention mechanism(STAtt),which enhances the global spatial-temporal modeling and the representational ability of model.The experimental results on two datasets,METR-LA and PEMS-BAY,show the proposed STA-GNN model outperforms the common baseline models in forecasting accuracy.
基金the European Research Council under the Grant agreement no.ERC_IDEAL RESCUE_637842 of the project IDEAL RESCUE_Integrated Design and Control of Sustainable Communities during Emergencies.
文摘Lifelines are critical infrastructure systems characterized by a high level of interdependency that can lead to cascading failures after any disaster.Many approaches can be used to analyze infrastructural interdependencies,but they are usually not able to describe the sequence of events during emergencies.Therefore,interdependencies need to be modeled also taking into account the time effects.The methodology proposed in this paper is based on a modified version of the Input-output Inoperability Model and returns the probabilities of failure for each node of the system.Lifelines are modeled using graph theory,while perturbations,representing a natural or man-made disaster,are applied to the elements of the network following predetermined rules.The cascading effects among interdependent networks have been simulated using a spatial multilayer approach,while the use of an adjacency tensor allows to consider the temporal dimension and its effects.The method has been tested on a case study based on the 2011 Fukushima Dai-ichi nuclear disaster.Different configurations of the system have been analyzed and their probability of occurrence evaluated.Two models of the nuclear power plant have been developed to evaluate how different spatial scales and levels of detail affect the results.
基金support from the National Natural Science Foundation of China(Nos.71822101 and 71771009)the Fundamental Research Funds for the Central Universities.
文摘The air transportation system has a critical impact on the global economy.While the system reliability is essential for the operational management of air traffic,it remains challenging to understand the network reliability of the air transportation system.This paper focuses on how the global air traffic is integrated from local scale along with operational time.The integration process of air traffic into a temporally connected network is viewed as percolation process by increasing the integration time constantly.The critical integration time TPwhich is found during the integration process can measure the global reliability of air traffic.The critical links at TPare also identified,the delay of which will influence the global integration of the airport network.These findings may provide insights on the reliability management for the temporal airport network.
基金This work was supported by SUG Research Grant M4082126.050 by the School of Mechanical and Aerospace Engineering(MAE),Nanyang Technological University(NTU),SingaporeNTU-CAAS Research Grant M4062429.052 by the ATM Research Institute,School of MAE,NTU,Singapore.
文摘Intractable delays occur in air traffic due to the imbalance between ever-increasing air traffic demand and limited airspace capacity.As air traffic is associated with complex air transport systems,delays can be magnified and propagated throughout these systems,resulting in the emergent behavior known as delay propagation.An understanding of delay propagation dynamics is pertinent to modern air traffic management.In this work,we present a complex network perspective of delay propagation dynamics.Specifically,we model air traffic scenarios using spatial–temporal networks with airports as the nodes.To establish the dynamic edges between the nodes,we develop a delay propagation method and apply it to a given set of air traffic schedules.Based on the constructed spatial-temporal networks,we suggest three metrics-magnitude,severity,and speed-to gauge delay propagation dynamics.To validate the effectiveness of the proposed method,we carry out case studies on domestic flights in the Southeastern Asia region(SAR)and the United States.Experiments demonstrate that the propagation magnitude in terms of the number of flights affected by delay propagation and the amount of propagated delays for the US traffic are respectively five and ten times those of the SAR.Experiments further reveal that the propagation speed for US traffic is eight times faster than that of the SAR.The delay propagation dynamics reveal that about six hub airports in the SAR have significant propagated delays,while the situation in the United States is considerably worse,with a corresponding number of around 16.This work provides a potent tool for tracing the evolution of air traffic delays.
基金the National Science Foundation of China (No.91738201, 61971440)the Jiangsu Province Basic Research Project (No.BK20192002)+1 种基金the China Postdoctoral Science Foundation (No.2018M632347)the Natural Science Research of Higher Education Institutions of Jiangsu Province (No.18KJB510030)。
文摘In this paper,we investigate a spectrumsensing system in the presence of a satellite,where the satellite works as a sensing node.Considering the conventional energy detection method is sensitive to the noise uncertainty,thus,a temporal convolutional network(TCN)based spectrum-sensing method is designed to eliminate the effect of the noise uncertainty and improve the performance of spectrum sensing,relying on the offline training and the online detection stages.Specifically,in the offline training stage,spectrum data captured by the satellite is sent to the TCN deployed on the gateway for training purpose.Moreover,in the online detection stage,the well trained TCN is utilized to perform real-time spectrum sensing,which can upgrade spectrum-sensing performance by exploiting the temporal features.Additionally,simulation results demonstrate that the proposed method achieves a higher probability of detection than that of the conventional energy detection(ED),the convolutional neural network(CNN),and deep neural network(DNN).Furthermore,the proposed method outperforms the CNN and the DNN in terms of a lower computational complexity.
文摘Different approaches have been established for applications of social and complex networks involving biological systems, passing through collaborative systems in knowledge networks and organizational systems. In this latter application, we highlight the studies focused on the diffusion of information and knowledge in networks. However, most of the time, the propagation of information in these networks and the resulting process of creation and diffusion of knowledge, have been studied from static perspectives. Additionally, the very concept of diffusion inevitably implies the inclusion of the temporal dimension, due to that it is an essentially dynamic process. Although static analysis provides an important perspective in structural terms, the behavioral view that reflects the evolution of the relationships of the members of these networks over time is best described by temporal networks. Thus, it is possible to analyze both the information flow and the structural changes that occur over time, which influences the dynamics of the creation and diffusion of knowledge. This article describes the computational modeling used to elucidate the creation and diffusion of knowledge in temporal networks formed to execute software maintenance and construction projects, for the period between 2007 and 2013, in the SERVIÇO FEDERAL DE PROCESSAMENTO DE DADOS (FEDERAL DATA PROCESSING SERVICE-SERPRO)—a public organization that provides information and communication technology services. The methodological approach adopted for the study was based on techniques for analyzing social and complex networks and on the complementary extensions that address temporal modeling of these networks. We present an exploratory longitudinal study that enabled a dynamic and structural analysis of the knowledge networks formed by members of software maintenance and development project teams between 2007 and 2013. The study enabled identification of knowledge categories throughout this period, in addition to the determination that the networks have a structure with small-world and scale-free models. Finally, we concluded that, in general, the topologies of the networks studies had characteristics for facilitating the flow of knowledge within the organization.
基金supported by the National Natural Science Fund Youth Project of China (No. 52100067)。
文摘Carbon source is an important factor of biological treatment systems, the effects of which on their temporal community assembly patterns are not sufficiently understood currently.In this study, the temporal dynamics and driving mechanisms of the communities in three parallel bioreactors for low-concentration coking wastewater(CWW) treatment with differing carbon source concentrations(S0 with no glucose addition, S1 with 200 mg/L glucose addition and S2 with 400 mg/L glucose addition) were comprehensively studied. Highthroughput sequencing and bioinformatics analyses including network analysis and Infer Community Assembly Mechanisms by Phylogenetic bin-based null model(iCAMP) were used. The communities of three systems showed turnover rates of 0.0029~0.0034 every 15days. Network analysis results showed that the S0 network showed higher positive correlation proportion(71.43%) and clustering coefficient(0.33), suggesting that carbon source shortage in S0 promoted interactions and cooperation of microbes. The neutral community model analysis showed that the immigration rate increased from 0.5247 in S0 to 0.6478in S2. The iCAMP analysis results showed that drift(45.89%) and homogeneous selection(31.68%) dominated in driving the assembly of all the investigated microbial communities.The contribution of homogeneous selection increased with the increase of carbon source concentrations, from 27.92% in S0 to 36.08% in S2. The OTUs participating in aerobic respiration and tricarboxylic acid(TCA) cycle were abundant among the bins mainly affected by deterministic processes, while those related to the metabolism of refractory organic pollutants in CWW such as alkanes, benzenes and phenols were abundant in the bins dominated by stochastic processes.
基金supported by National Natural Science Foundation of China (No. 61271236)Major Projects of Natural Science Research of Jiangsu Provincial Universities (No. 17KJA510004)Postgraduate Research & Practice Innovation Program of Jiangsu Province (No. KYCX17_0763, No.KYCX18_0907)
文摘Random access is a well-known multiple access method for uncoordinated communication nodes.Existing work mainly focuses on optimizing iterative access protocols,assuming that packets are corrupted once they are collided,or that feedback is available and can be exploited.In practice,a packet may still be able to be recovered successfully even when collided with other packets.System design and performance analysis under such a situation,particularly when the details of collision are taken into consideration,are less known.In this paper,we provide a framework for analytically evaluating the actual detection performance in a random temporal multiple access system where nodes can only transmit.Explicit expressions are provided for collision probability and signal to interference and noise ratio(SINR)when different numbers of packets are collided.We then discuss and compare two receiver options for the AP,and provide detailed receiver design for the premium one.In particular,we propose a synchronization scheme which can largely reduce the preamble length.We also demonstrate that system performance could be a convex function of preamble length both analytically and via simulation,as well as the forward error correction(FEC)coding rate.
基金Major Unified Construction Project of Petro China(2019-40210-000020-02)。
文摘Since the oil production of single well in water flooding reservoir varies greatly and is hard to predict, an oil production prediction method of single well based on temporal convolutional network(TCN) is proposed and verified. This method is started from data processing, the correspondence between water injectors and oil producers is determined according to the influence radius of the water injectors, the influence degree of a water injector on an oil producer in the month concerned is added as a model feature, and a Random Forest(RF) model is built to fill the dynamic data of water flooding. The single well history is divided into 4 stages according to its water cut, that is, low water cut, middle water cut, high water cut and extra-high water cut stages. In each stage, a TCN based prediction model is established, hyperparameters of the model are optimized by the Sparrow Search Algorithm(SSA). Finally, the models of the 4 stages are integrated into one whole-life model of the well for production prediction. The application of this method in Daqing Oilfield, NE China shows that:(1) Compared with conventional data processing methods, the data obtained by this processing method are more close to the actual production, and the data set obtained is more authentic and complete.(2) The TCN model has higher prediction accuracy than other 11 models such as Long Short Term Memory(LSTM).(3) Compared with the conventional full-life-cycle models, the model of integrated stages can significantly reduce the error of production prediction.
基金Thiswork is supported by theYouth Science and Technology Innovation Personnel Training Project of Heilongjiang(No.UNPYSCT-2020072)the FundamentalResearch Funds for the Universities of Heilongjiang(Nos.145109217,135509234)+1 种基金the Education Science Fourteenth Five-Year Plan 2021 Project of Heilongjiang(No.GJB1421344)the Innovative Research Projects for Postgraduates of Qiqihar University(No.YJSCX2022048).
文摘Influence maximization of temporal social networks(IMT)is a problem that aims to find the most influential set of nodes in the temporal network so that their information can be the most widely spread.To solve the IMT problem,we propose an influence maximization algorithm based on an improved K-shell method,namely improved K-shell in temporal social networks(KT).The algorithm takes into account the global and local structures of temporal social networks.First,to obtain the kernel value Ks of each node,in the global scope,it layers the network according to the temporal characteristic of nodes by improving the K-shell method.Then,in the local scope,the calculation method of comprehensive degree is proposed to weigh the influence of nodes.Finally,the node with the highest comprehensive degree in each core layer is selected as the seed.However,the seed selection strategy of KT can easily lose some influential nodes.Thus,by optimizing the seed selection strategy,this paper proposes an efficient heuristic algorithm called improved K-shell in temporal social networks for influence maximization(KTIM).According to the hierarchical distribution of cores,the algorithm adds nodes near the central core to the candidate seed set.It then searches for seeds in the candidate seed set according to the comprehensive degree.Experiments showthatKTIMis close to the best performing improved method for influence maximization of temporal graph(IMIT)algorithm in terms of effectiveness,but runs at least an order of magnitude faster than it.Therefore,considering the effectiveness and efficiency simultaneously in temporal social networks,the KTIM algorithm works better than other baseline algorithms.
文摘This paper integrates genetic algorithm and neura l network techniques to build new temporal predicting analysis tools for geographic information system (GIS). These new GIS tools can be readily applied in a practical and appropriate manner in spatial and temp oral research to patch the gaps in GIS data mining and knowledge discovery functions. The specific achievement here is the integration of related artificial intellig ent technologies into GIS software to establish a conceptual spatial and temporal analysis framework. And, by using this framework to develop an artificial intelligent spatial and tempor al information analyst (ASIA) system which then is fully utilized in the existin g GIS package. This study of air pollutants forecasting provides a geographical practical case to prove the rationalization and justness of the conceptual tempo ral analysis framework.
