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
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
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
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
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
The ever-growing available visual data(i.e.,uploaded videos and pictures by internet users)has attracted the research community’s attention in the computer vision field.Therefore,finding efficient solutions to extrac...The ever-growing available visual data(i.e.,uploaded videos and pictures by internet users)has attracted the research community’s attention in the computer vision field.Therefore,finding efficient solutions to extract knowledge from these sources is imperative.Recently,the BlazePose system has been released for skeleton extraction from images oriented to mobile devices.With this skeleton graph representation in place,a Spatial-Temporal Graph Convolutional Network can be implemented to predict the action.We hypothesize that just by changing the skeleton input data for a different set of joints that offers more information about the action of interest,it is possible to increase the performance of the Spatial-Temporal Graph Convolutional Network for HAR tasks.Hence,in this study,we present the first implementation of the BlazePose skeleton topology upon this architecture for action recognition.Moreover,we propose the Enhanced-BlazePose topology that can achieve better results than its predecessor.Additionally,we propose different skeleton detection thresholds that can improve the accuracy performance even further.We reached a top-1 accuracy performance of 40.1%on the Kinetics dataset.For the NTU-RGB+D dataset,we achieved 87.59%and 92.1%accuracy for Cross-Subject and Cross-View evaluation criteria,respectively.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
Continuous sign language recognition(CSLR)is challenging due to the complexity of video background,hand gesture variability,and temporal modeling difficulties.This work proposes a CSLR method based on a spatialtempora...Continuous sign language recognition(CSLR)is challenging due to the complexity of video background,hand gesture variability,and temporal modeling difficulties.This work proposes a CSLR method based on a spatialtemporal graph attention network to focus on essential features of video series.The method considers local details of sign language movements by taking the information on joints and bones as inputs and constructing a spatialtemporal graph to reflect inter-frame relevance and physical connections between nodes.The graph-based multihead attention mechanism is utilized with adjacent matrix calculation for better local-feature exploration,and short-term motion correlation modeling is completed via a temporal convolutional network.We adopted BLSTM to learn the long-termdependence and connectionist temporal classification to align the word-level sequences.The proposed method achieves competitive results regarding word error rates(1.59%)on the Chinese Sign Language dataset and the mean Jaccard Index(65.78%)on the ChaLearn LAP Continuous Gesture Dataset.展开更多
A lightweight multi-layer residual temporal convolutional network model(RTCN)is proposed to target the highly complex kinematics and temporal correlation of human motion.RTCN uses 1-D convolution to efficiently obtain...A lightweight multi-layer residual temporal convolutional network model(RTCN)is proposed to target the highly complex kinematics and temporal correlation of human motion.RTCN uses 1-D convolution to efficiently obtain the spatial structure information of human motion and extract the correlation in the time series of human motion.The residual structure is applied to the proposed network model to alleviate the problem of gradient disappearance in the deep network.Experiments on the Human 3.6M dataset demonstrate that the proposed method effectively reduces the errors of motion prediction compared with previous methods,especially of long-term prediction.展开更多
Influence Maximization(IM)aims to select a seed set of size k in a social network so that information can be spread most widely under a specific information propagation model through this set of nodes.However,most exi...Influence Maximization(IM)aims to select a seed set of size k in a social network so that information can be spread most widely under a specific information propagation model through this set of nodes.However,most existing studies on the IM problem focus on static social network features,while neglecting the features of temporal social networks.To bridge this gap,we focus on node features reflected by their historical interaction behavior in temporal social networks,i.e.,interaction attributes and self-similarity,and incorporate them into the influence maximization algorithm and information propagation model.Firstly,we propose a node feature-aware voting algorithm,called ISVoteRank,for seed nodes selection.Specifically,before voting,the algorithm sets the initial voting ability of nodes in a personalized manner by combining their features.During the voting process,voting weights are set based on the interaction strength between nodes,allowing nodes to vote at different extents and subsequently weakening their voting ability accordingly.The process concludes by selecting the top k nodes with the highest voting scores as seeds,avoiding the inefficiency of iterative seed selection in traditional voting-based algorithms.Secondly,we extend the Independent Cascade(IC)model and propose the Dynamic Independent Cascade(DIC)model,which aims to capture the dynamic features in the information propagation process by combining node features.Finally,experiments demonstrate that the ISVoteRank algorithm has been improved in both effectiveness and efficiency compared to baseline methods,and the influence spread through the DIC model is improved compared to the IC model.展开更多
In order to reduce the physical impairment caused by signal distortion,in this paper,we investigate symbol detection with Deep Learning(DL)methods to improve bit-error performance in the optical communication system.M...In order to reduce the physical impairment caused by signal distortion,in this paper,we investigate symbol detection with Deep Learning(DL)methods to improve bit-error performance in the optical communication system.Many DL-based methods have been applied to such systems to improve bit-error performance.Referring to the speech-to-text method of automatic speech recognition,this paper proposes a signal-to-symbol method based on DL and designs a receiver for symbol detection on single-polarized optical communications modes.To realize this detection method,we propose a non-causal temporal convolutional network-assisted receiver to detect symbols directly from the baseband signal,which specifically integrates most modules of the receiver.Meanwhile,we adopt three training approaches for different signal-to-noise ratios.We also apply a parametric rectified linear unit to enhance the noise robustness of the proposed network.According to the simulation experiments,the biterror-rate performance of the proposed method is close to or even superior to that of the conventional receiver and better than the recurrent neural network-based receiver.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
Bus arrival time prediction contributes to the quality improvement of public transport services.Passengers can arrange departure time effectively if they know the accurate bus arrival time in advance.We proposed a mac...Bus arrival time prediction contributes to the quality improvement of public transport services.Passengers can arrange departure time effectively if they know the accurate bus arrival time in advance.We proposed a machine⁃learning approach,RTSI⁃ResNet,to forecast the bus arrival time at target stations.The residual neural network framework was employed to model the bus route temporal⁃spatial information.It was found that the bus travel time on a segment between two stations not only had correlation with the preceding buses,but also had common change trends with nearby downstream/upstream segments.Two features about bus travel time and headway were extracted from bus route including target section in both forward and reverse directions to constitute the route temporal⁃spatial information,which reflects the road traffic conditions comprehensively.Experiments on the bus trajectory data of route No.10 in Shenzhen public transport system demonstrated that the proposed RTSI⁃ResNet outperformed other well⁃known methods(e.g.,RNN/LSTM,SVM).Specifically,the advantage was more significant when the distance between bus and the target station was farther.展开更多
A Long Short-Term Memory(LSTM) Recurrent Neural Network(RNN) has driven tremendous improvements on an acoustic model based on Gaussian Mixture Model(GMM). However, these models based on a hybrid method require a force...A Long Short-Term Memory(LSTM) Recurrent Neural Network(RNN) has driven tremendous improvements on an acoustic model based on Gaussian Mixture Model(GMM). However, these models based on a hybrid method require a forced aligned Hidden Markov Model(HMM) state sequence obtained from the GMM-based acoustic model. Therefore, it requires a long computation time for training both the GMM-based acoustic model and a deep learning-based acoustic model. In order to solve this problem, an acoustic model using CTC algorithm is proposed. CTC algorithm does not require the GMM-based acoustic model because it does not use the forced aligned HMM state sequence. However, previous works on a LSTM RNN-based acoustic model using CTC used a small-scale training corpus. In this paper, the LSTM RNN-based acoustic model using CTC is trained on a large-scale training corpus and its performance is evaluated. The implemented acoustic model has a performance of 6.18% and 15.01% in terms of Word Error Rate(WER) for clean speech and noisy speech, respectively. This is similar to a performance of the acoustic model based on the hybrid method.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
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 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.
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.
文摘The ever-growing available visual data(i.e.,uploaded videos and pictures by internet users)has attracted the research community’s attention in the computer vision field.Therefore,finding efficient solutions to extract knowledge from these sources is imperative.Recently,the BlazePose system has been released for skeleton extraction from images oriented to mobile devices.With this skeleton graph representation in place,a Spatial-Temporal Graph Convolutional Network can be implemented to predict the action.We hypothesize that just by changing the skeleton input data for a different set of joints that offers more information about the action of interest,it is possible to increase the performance of the Spatial-Temporal Graph Convolutional Network for HAR tasks.Hence,in this study,we present the first implementation of the BlazePose skeleton topology upon this architecture for action recognition.Moreover,we propose the Enhanced-BlazePose topology that can achieve better results than its predecessor.Additionally,we propose different skeleton detection thresholds that can improve the accuracy performance even further.We reached a top-1 accuracy performance of 40.1%on the Kinetics dataset.For the NTU-RGB+D dataset,we achieved 87.59%and 92.1%accuracy for Cross-Subject and Cross-View evaluation criteria,respectively.
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.
基金supported by the Key Research&Development Plan Project of Shandong Province,China(No.2017GGX10127).
文摘Continuous sign language recognition(CSLR)is challenging due to the complexity of video background,hand gesture variability,and temporal modeling difficulties.This work proposes a CSLR method based on a spatialtemporal graph attention network to focus on essential features of video series.The method considers local details of sign language movements by taking the information on joints and bones as inputs and constructing a spatialtemporal graph to reflect inter-frame relevance and physical connections between nodes.The graph-based multihead attention mechanism is utilized with adjacent matrix calculation for better local-feature exploration,and short-term motion correlation modeling is completed via a temporal convolutional network.We adopted BLSTM to learn the long-termdependence and connectionist temporal classification to align the word-level sequences.The proposed method achieves competitive results regarding word error rates(1.59%)on the Chinese Sign Language dataset and the mean Jaccard Index(65.78%)on the ChaLearn LAP Continuous Gesture Dataset.
文摘A lightweight multi-layer residual temporal convolutional network model(RTCN)is proposed to target the highly complex kinematics and temporal correlation of human motion.RTCN uses 1-D convolution to efficiently obtain the spatial structure information of human motion and extract the correlation in the time series of human motion.The residual structure is applied to the proposed network model to alleviate the problem of gradient disappearance in the deep network.Experiments on the Human 3.6M dataset demonstrate that the proposed method effectively reduces the errors of motion prediction compared with previous methods,especially of long-term prediction.
基金supported by the Fundamental Research Funds for the Universities of Heilongjiang(Nos.145109217,135509234)the Youth Science and Technology Innovation Personnel Training Project of Heilongjiang(No.UNPYSCT-2020072)the Innovative Research Projects for Postgraduates of Qiqihar University(No.YJSCX2022048).
文摘Influence Maximization(IM)aims to select a seed set of size k in a social network so that information can be spread most widely under a specific information propagation model through this set of nodes.However,most existing studies on the IM problem focus on static social network features,while neglecting the features of temporal social networks.To bridge this gap,we focus on node features reflected by their historical interaction behavior in temporal social networks,i.e.,interaction attributes and self-similarity,and incorporate them into the influence maximization algorithm and information propagation model.Firstly,we propose a node feature-aware voting algorithm,called ISVoteRank,for seed nodes selection.Specifically,before voting,the algorithm sets the initial voting ability of nodes in a personalized manner by combining their features.During the voting process,voting weights are set based on the interaction strength between nodes,allowing nodes to vote at different extents and subsequently weakening their voting ability accordingly.The process concludes by selecting the top k nodes with the highest voting scores as seeds,avoiding the inefficiency of iterative seed selection in traditional voting-based algorithms.Secondly,we extend the Independent Cascade(IC)model and propose the Dynamic Independent Cascade(DIC)model,which aims to capture the dynamic features in the information propagation process by combining node features.Finally,experiments demonstrate that the ISVoteRank algorithm has been improved in both effectiveness and efficiency compared to baseline methods,and the influence spread through the DIC model is improved compared to the IC model.
基金supported by the National Key R&D Program of China under Grant 2018YFB1801500.
文摘In order to reduce the physical impairment caused by signal distortion,in this paper,we investigate symbol detection with Deep Learning(DL)methods to improve bit-error performance in the optical communication system.Many DL-based methods have been applied to such systems to improve bit-error performance.Referring to the speech-to-text method of automatic speech recognition,this paper proposes a signal-to-symbol method based on DL and designs a receiver for symbol detection on single-polarized optical communications modes.To realize this detection method,we propose a non-causal temporal convolutional network-assisted receiver to detect symbols directly from the baseband signal,which specifically integrates most modules of the receiver.Meanwhile,we adopt three training approaches for different signal-to-noise ratios.We also apply a parametric rectified linear unit to enhance the noise robustness of the proposed network.According to the simulation experiments,the biterror-rate performance of the proposed method is close to or even superior to that of the conventional receiver and better than the recurrent neural network-based receiver.
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Sponsored by the Transportation Science and Technology Planning Project of Henan Province,China(Grant No.2019G-2-2).
文摘Bus arrival time prediction contributes to the quality improvement of public transport services.Passengers can arrange departure time effectively if they know the accurate bus arrival time in advance.We proposed a machine⁃learning approach,RTSI⁃ResNet,to forecast the bus arrival time at target stations.The residual neural network framework was employed to model the bus route temporal⁃spatial information.It was found that the bus travel time on a segment between two stations not only had correlation with the preceding buses,but also had common change trends with nearby downstream/upstream segments.Two features about bus travel time and headway were extracted from bus route including target section in both forward and reverse directions to constitute the route temporal⁃spatial information,which reflects the road traffic conditions comprehensively.Experiments on the bus trajectory data of route No.10 in Shenzhen public transport system demonstrated that the proposed RTSI⁃ResNet outperformed other well⁃known methods(e.g.,RNN/LSTM,SVM).Specifically,the advantage was more significant when the distance between bus and the target station was farther.
基金supported by the Ministry of Trade,Industry & Energy(MOTIE,Korea) under Industrial Technology Innovation Program (No.10063424,'development of distant speech recognition and multi-task dialog processing technologies for in-door conversational robots')
文摘A Long Short-Term Memory(LSTM) Recurrent Neural Network(RNN) has driven tremendous improvements on an acoustic model based on Gaussian Mixture Model(GMM). However, these models based on a hybrid method require a forced aligned Hidden Markov Model(HMM) state sequence obtained from the GMM-based acoustic model. Therefore, it requires a long computation time for training both the GMM-based acoustic model and a deep learning-based acoustic model. In order to solve this problem, an acoustic model using CTC algorithm is proposed. CTC algorithm does not require the GMM-based acoustic model because it does not use the forced aligned HMM state sequence. However, previous works on a LSTM RNN-based acoustic model using CTC used a small-scale training corpus. In this paper, the LSTM RNN-based acoustic model using CTC is trained on a large-scale training corpus and its performance is evaluated. The implemented acoustic model has a performance of 6.18% and 15.01% in terms of Word Error Rate(WER) for clean speech and noisy speech, respectively. This is similar to a performance of the acoustic model based on the hybrid method.
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.
