In order to detect the traffic pattern of moving objects in the city more accurately and quickly, a parallel algorithm for detecting traffic patterns using stay points and moving features is proposed. First, the featu...In order to detect the traffic pattern of moving objects in the city more accurately and quickly, a parallel algorithm for detecting traffic patterns using stay points and moving features is proposed. First, the features of the stay points in different traffic patterns are extracted, that is, the stay points of various traffic patterns are identified, respectively, and the clustering algorithm is used to mine the unique features of the stop points to different traffic patterns. Then, the moving features in different traffic patterns are extracted from a trajectory of a moving object, including the maximum speed, the average speed, and the stopping rate. A classifier is constructed to predict the traffic pattern of the trajectory using the stay points and moving features. Finally, a parallel algorithm based on Spark is proposed to detect traffic patterns. Experimental results show that the stay points and moving features can reflect the difference between different traffic modes to a greater extent, and the detection accuracy is higher than those of other methods. In addition, the parallel algorithm can increase the speed of identifying traffic patterns.展开更多
Pattern matching is a fundamental approach to detect malicious behaviors and information over Internet, which has been gradually used in high-speed network traffic analysis. However, there is a performance bottleneck ...Pattern matching is a fundamental approach to detect malicious behaviors and information over Internet, which has been gradually used in high-speed network traffic analysis. However, there is a performance bottleneck for multi-pattern matching on online compressed network traffic(CNT), this is because malicious and intrusion codes are often embedded into compressed network traffic. In this paper, we propose an online fast and multi-pattern matching algorithm on compressed network traffic(FMMCN). FMMCN employs two types of jumping, i.e. jumping during sliding window and a string jump scanning strategy to skip unnecessary compressed bytes. Moreover, FMMCN has the ability to efficiently process multiple large volume of networks such as HTTP traffic, vehicles traffic, and other Internet-based services. The experimental results show that FMMCN can ignore more than 89.5% of bytes, and its maximum speed reaches 176.470MB/s in a midrange switches device, which is faster than the current fastest algorithm ACCH by almost 73.15 MB/s.展开更多
The paper covers analysis and investigation of lighting automation system in low-traffic long-roads. The main objective is to provide optimal solution between expensive safe design that utilizes continuous street ligh...The paper covers analysis and investigation of lighting automation system in low-traffic long-roads. The main objective is to provide optimal solution between expensive safe design that utilizes continuous street lighting system at night for the entire road, or inexpensive design that sacrifices the safety, relying on using vehicles lighting, to eliminate the problem of high cost energy consumption during the night operation of the road. By taking into account both of these factors, smart lighting automation system is proposed using Pattern Recognition Technique applied on vehicle number-plates. In this proposal, the road is sectionalized into zones, and based on smart Pattern Recognition Technique, the control system of the road lighting illuminates only the zone that the vehicles pass through. Economic analysis is provided in this paper to support the value of using this design of lighting control system.展开更多
Introduction: In 21st century, road traffic accidents (RTA) are considered as increasing epidemic of non-communicable disease which is abandoned and needs special attention to prevent them. The aim of this study was t...Introduction: In 21st century, road traffic accidents (RTA) are considered as increasing epidemic of non-communicable disease which is abandoned and needs special attention to prevent them. The aim of this study was to assess the factors and pattern of injuries associated with road traffic accidents. Methods: A cross sectional study was conducted among 112 RTA victims and 56 drivers in Palpa District of Nepal. The association of factors and pattern of injuries with exposure to accidents was assessed using Fisher’s exact test. Bivariate logistic regression examined the association between driving and socio-demographics factors and exposure to road accidents. Results: Of 112 RTA victims, 50% were in the age group of 21 to 40 years and 71.4% were male. Drivers who were in the age less than or equal to 30 years were more likely (OR: 3.6;95% CI: 1.0, 14.3) to expose to an accident than those who were above 30 years. Similarly, those having driving speed less than 40 km/hr were less likely to expose to an accident than those with speed 40 - 60 km/hr (OR: 6.0;95% CI: 0.8, 73.5) and those with speed more than 60 km/hr (OR 7.8;95% CI: 1.0, 100.1). Moreover, the driving experience was also found positively associated (OR: 5.6;95% CI: 1.1, 35.5) with the exposure to an accident. Conclusion: Being in younger age group, male gender, morning time, the driving speed, driving experiences, and driving hours on the road were positively associated with RTA. The efforts should be made to enforce laws in control of speed targeting experienced drivers and those with younger age groups.展开更多
In order to identify any traces of suspicious activities for the networks security, Network Traffic Analysis has been the basis of network security and network management. With the continued emergence of new applicati...In order to identify any traces of suspicious activities for the networks security, Network Traffic Analysis has been the basis of network security and network management. With the continued emergence of new applications and encrypted traffic, the currently available approaches can not perform well for all kinds of network data. In this paper, we propose a novel stream pattern matching technique which is not only easily deployed but also includes the advantages of different methods. The main idea is： first, defining a formal description specification, by which any series of data stream can be unambiguously descrbed by a special stream pattern; then a tree representation is constructed by parsing the stream pattern; at last, a stream pattern engine is constructed with the Non-t-mite automata （S-CG-NFA） and Bit-parallel searching algorithms. Our stream pattern analysis system has been fully prototyped on C programming language and Xilinx Vn-tex2 FPGA. The experimental results show the method could provides a high level of recognition efficiency and accuracy.展开更多
The phenomenon of data explosion represents a severe challenge for the upcoming big data era.However,the current Internet architecture is insufficient for dealing with a huge amount of traffic owing to an increase in ...The phenomenon of data explosion represents a severe challenge for the upcoming big data era.However,the current Internet architecture is insufficient for dealing with a huge amount of traffic owing to an increase in redundant content transmission and the end-point-based communication model.Information-centric networking(ICN)is a paradigm for the future Internet that can be utilized to resolve the data explosion problem.In this paper,we focus on content-centric networking(CCN),one of the key candidate ICN architectures.CCN has been studied in various network environments with the aim of relieving network and server burden,especially in name-based forwarding and in-network caching functionalities.This paper studies the effect of several caching strategies in the CCN domain from the perspective of network and server overhead.Thus,we comprehensively analyze the in-network caching performance of CCN under several popular cache replication methods(i.e.,cache placement).We evaluate the performance with respect to wellknown Internet traffic patterns that follow certain probabilistic distributions,such as the Zipf/Mandelbrot–Zipf distributions,and flashcrowds.For the experiments,we developed an OPNET-based CCN simulator with a realistic Internet-like topology.展开更多
Recognition of ship traffic patterns can provide insights into the rules of navigation,maneuvering,and collision avoidance for ships at sea.This is essential for ensuring safe navigation at sea and improving navigatio...Recognition of ship traffic patterns can provide insights into the rules of navigation,maneuvering,and collision avoidance for ships at sea.This is essential for ensuring safe navigation at sea and improving navigational efficiency.With the popularization of the Automatic Identification System(AIS),numerous studies utilized ship trajectories to identify maritime traffic patterns.However,the current research focuses on the spatiotemporal behavioral feature clustering of ship trajectory points or segments while lacking consideration for multiple factors that influence ship behavior,such as ship static and maritime geospatial features,resulting in insufficient precision in ship traffic pattern recognition.This study proposes a ship traffic pattern recognition method that considers multi-attribute trajectory similarity(STPMTS),which considers ship static feature,dynamic feature,port geospatial feature,as well as semantic relationships between these features.First,A ship trajectory reconstruction method based on grid compression was introduced to eliminate redundant data and enhance the efficiency of trajectory similarity measurements.Subsequently,to quantify the degree of similarity of ship trajectories,a trajectory similarity measurement method is proposed that combines ship static and dynamic information with port geospatial features.Furthermore,trajectory clustering with hierarchical methods was applied based on the trajectory similarity matrix for dividing trajectories into different clusters.The quality of the similarity measurement results was evaluated by quality criterion to recognize the optimal number of ship traffic patterns.Finally,the effectiveness of the proposed method was verified using actual port ship trajectory data from the Tianjin Port of China,ranging from September to November 2016.Compared with other methods,the proposed method exhibits significant advantages in identifying traffic patterns of ships entering and leaving the port in terms of geometric features,dynamic features,and adherence to navigation rules.This study could serve as an inspiration for a comprehensive exploration of maritime transportation knowledge from multiple perspectives.展开更多
Although the number of road traffic accidents,fatalities,injuries has been slightly reduced in recent years,HCMC(Ho Chi Minh City)would still face challenges in reducing and restraining road traffic accidents in the f...Although the number of road traffic accidents,fatalities,injuries has been slightly reduced in recent years,HCMC(Ho Chi Minh City)would still face challenges in reducing and restraining road traffic accidents in the future.This paper presents the results of road traffic accident data analysis over the past 3 years that we collected from the Road-Railway Police Bureau in HCMC.Based on the results,we could be able to deeply understand trends,characteristics,and causes of road traffic accidents.Such a deep understanding is a scientific basis to study and formulate synchronous strategy along with specific solutions to solve road traffic accident problems more effectively in the future.展开更多
Traffic emissions have become the major air pollution source in urban areas.Therefore,understanding the highly non-stational and complex impact of traffic factors on air quality is very important for building air qual...Traffic emissions have become the major air pollution source in urban areas.Therefore,understanding the highly non-stational and complex impact of traffic factors on air quality is very important for building air quality prediction models.Using real-world air pollutant data from Taipei City,this study integrates diverse factors,including traffic flow,speed,rainfall patterns,andmeteorological factors.We constructed a Bayesian network probabilitymodel based on rainfall events as a big data analysis framework to investigate understand traffic factor causality relationships and condition probabilities for meteorological factors and air pollutant concentrations.Generalized Additive Model(GAM)verified non-linear relationships between traffic factors and air pollutants.Consequently,we propose a long short term memory(LSTM)model to predict airborne pollutant concentrations.This study propose a new approach of air pollutants and meteorological variable analysis procedure by considering both rainfall amount and patterns.Results indicate improved air quality when controlling vehicle speed above 40 km/h and maintaining an average vehicle flow<1200 vehicles per hour.This study also classified rainfall events into four types depending on its characteristic.Wet deposition from varied rainfall types significantly affects air quality,with TypeⅠrainfall events(long-duration heavy rain)having the most pronounced impact.An LSTM model incorporating GAM and Bayesian network outcomes yields excellent performance,achieving correlation R^(2)>0.9 and 0.8 for first and second order air pollutants,i.e.,CO,NO,NO_(2),and NO_(x);and O_(3),PM_(10),and PM_(2.5),respectively.展开更多
Based on Gaussian mixture models（GMM）, speed, flow and occupancy are used together in the cluster analysis of traffic flow data. Compared with other clustering and sorting techniques, as a structural model, the GMM ...Based on Gaussian mixture models（GMM）, speed, flow and occupancy are used together in the cluster analysis of traffic flow data. Compared with other clustering and sorting techniques, as a structural model, the GMM is suitable for various kinds of traffic flow parameters. Gap statistics and domain knowledge of traffic flow are used to determine a proper number of clusters. The expectation-maximization （E-M） algorithm is used to estimate parameters of the GMM model. The clustered traffic flow pattems are then analyzed statistically and utilized for designing maximum likelihood classifiers for grouping real-time traffic flow data when new observations become available. Clustering analysis and pattern recognition can also be used to cluster and classify dynamic traffic flow patterns for freeway on-ramp and off-ramp weaving sections as well as for other facilities or things involving the concept of level of service, such as airports, parking lots, intersections, interrupted-flow pedestrian facilities, etc.展开更多
In order to classify the Intemet traffic of different Internet applications more quickly, two open Internet traffic traces, Auckland I1 and UNIBS traffic traces, are employed as study objects. Eight earliest packets w...In order to classify the Intemet traffic of different Internet applications more quickly, two open Internet traffic traces, Auckland I1 and UNIBS traffic traces, are employed as study objects. Eight earliest packets with non-zero flow payload sizes are selected and their payload sizes are used as the early-stage flow features. Such features can be easily and rapidly extracted at the early flow stage, which makes them outstanding. The behavior patterns of different Intemet applications are analyzed by visualizing the early-stage packet size values. Analysis results show that most Internet applications can reflect their own early packet size behavior patterns. Early packet sizes are assumed to carry enough information for effective traffic identification. Three classical machine learning classifiers, classifier, naive Bayesian trees, i. e., the naive Bayesian and the radial basis function neural networks, are used to validate the effectiveness of the proposed assumption. The experimental results show that the early stage packet sizes can be used as features for traffic identification.展开更多
加密技术的广泛应用给恶意活动提供了藏匿的机会,对网络安全监测体系带来了巨大挑战.现有的加密流量检测方法主要是在单个数据包级别提取统计流量特征,因此可能会由于潜在的IP分片而破坏原始连续通信行为中隐含的特征.此外,大多数方法...加密技术的广泛应用给恶意活动提供了藏匿的机会,对网络安全监测体系带来了巨大挑战.现有的加密流量检测方法主要是在单个数据包级别提取统计流量特征,因此可能会由于潜在的IP分片而破坏原始连续通信行为中隐含的特征.此外,大多数方法对于网络流的交互模式建模粒度较粗,未能深入挖掘对等实体间的通信意图,难以适应新型恶意软件通信行为和通信量的变化.本文以交互为分析粒度,提出了方法 ISG-Net(interaction state graphnet).该方法基于状态转换构建流量交互状态图,并引入了融合流量时序信息的自注意力编码模型.特别地,本文通过交互状态图获取蕴含全局信息的交互状态表示,然后对每次交互进行细粒度的特征提取,以融合得到会话(双向流)的表示.在3个数据集上的实验结果表明,在加密恶意流量检测任务中,本文方法在准确性、鲁棒性和容错性均优于现有算法.展开更多
Travel time through a ring road with a total length of 80 km has been predicted by a viscoelastic traffic model(VEM), which is developed in analogous to the non-Newtonian fluid flow. The VEM expresses a traffic pressu...Travel time through a ring road with a total length of 80 km has been predicted by a viscoelastic traffic model(VEM), which is developed in analogous to the non-Newtonian fluid flow. The VEM expresses a traffic pressure for the unfree flow case by space headway, ensuring that the pressure can be determined by the assumption that the relevant second critical sound speed is exactly equal to the disturbance propagation speed determined by the free flow speed and the braking distance measured by the average vehicular length. The VEM assumes that the sound speed for the free flow case depends on the traffic density in some specific aspects, which ensures that it is exactly identical to the free flow speed on an empty road. To make a comparison, the open Navier-Stokes type model developed by Zhang(ZHANG, H. M. Driver memory, traffic viscosity and a viscous vehicular traffic flow model. Transp. Res. Part B, 37, 27–41(2003)) is adopted to predict the travel time through the ring road for providing the counterpart results.When the traffic free flow speed is 80 km/h, the braking distance is supposed to be 45 m,with the jam density uniquely determined by the average length of vehicles l ≈ 5.8 m. To avoid possible singular points in travel time prediction, a distinguishing period for time averaging is pre-assigned to be 7.5 minutes. It is found that the travel time increases monotonically with the initial traffic density on the ring road. Without ramp effects, for the ring road with the initial density less than the second critical density, the travel time can be simply predicted by using the equilibrium speed. However, this simpler approach is unavailable for scenarios over the second critical.展开更多
With enormous growth of the number of Internet users and appearance of new applications, characterization of Internet traffic has attracted more and more attention and has become one of the major challenging issues in...With enormous growth of the number of Internet users and appearance of new applications, characterization of Internet traffic has attracted more and more attention and has become one of the major challenging issues in telecommunication network over the past few years. In this paper, we study the network traffic pattern of the aggregate traffic and of specific application traffic, especially the popular applications such as P2P, VoIP that contribute most network traffic. Our study verified that majority Internet backbone traffic is contributed by a small portion of users and a power function can be used to approximate the contribution of each user to the overall traffic. We show that P2P applications are the dominant traffic contributor in current Internet Backbone of China. In addition, we selectively present the traffic pattern of different applications in detail.展开更多
Early detection and rapid resolution network congestion can considerably improve network capacity. Consequently, much research has been carried out on predicting traff ic patterns in 3G networks. This paper introduces...Early detection and rapid resolution network congestion can considerably improve network capacity. Consequently, much research has been carried out on predicting traff ic patterns in 3G networks. This paper introduces an access point centric approach that is implemented by two prediction models, the traffic abstraction model and the order-k Markov model. Traffi c predictions are carried out to support the congestion control in the semi-smart antenna systems. The simulation result shows that the cumulative error rate is below 25% even carrying out multi-step-ahead predictions.展开更多
基金The National Natural Science Foundation of China(No.41471371)
文摘In order to detect the traffic pattern of moving objects in the city more accurately and quickly, a parallel algorithm for detecting traffic patterns using stay points and moving features is proposed. First, the features of the stay points in different traffic patterns are extracted, that is, the stay points of various traffic patterns are identified, respectively, and the clustering algorithm is used to mine the unique features of the stop points to different traffic patterns. Then, the moving features in different traffic patterns are extracted from a trajectory of a moving object, including the maximum speed, the average speed, and the stopping rate. A classifier is constructed to predict the traffic pattern of the trajectory using the stay points and moving features. Finally, a parallel algorithm based on Spark is proposed to detect traffic patterns. Experimental results show that the stay points and moving features can reflect the difference between different traffic modes to a greater extent, and the detection accuracy is higher than those of other methods. In addition, the parallel algorithm can increase the speed of identifying traffic patterns.
基金supported by China MOST project (No.2012BAH46B04)
文摘Pattern matching is a fundamental approach to detect malicious behaviors and information over Internet, which has been gradually used in high-speed network traffic analysis. However, there is a performance bottleneck for multi-pattern matching on online compressed network traffic(CNT), this is because malicious and intrusion codes are often embedded into compressed network traffic. In this paper, we propose an online fast and multi-pattern matching algorithm on compressed network traffic(FMMCN). FMMCN employs two types of jumping, i.e. jumping during sliding window and a string jump scanning strategy to skip unnecessary compressed bytes. Moreover, FMMCN has the ability to efficiently process multiple large volume of networks such as HTTP traffic, vehicles traffic, and other Internet-based services. The experimental results show that FMMCN can ignore more than 89.5% of bytes, and its maximum speed reaches 176.470MB/s in a midrange switches device, which is faster than the current fastest algorithm ACCH by almost 73.15 MB/s.
文摘The paper covers analysis and investigation of lighting automation system in low-traffic long-roads. The main objective is to provide optimal solution between expensive safe design that utilizes continuous street lighting system at night for the entire road, or inexpensive design that sacrifices the safety, relying on using vehicles lighting, to eliminate the problem of high cost energy consumption during the night operation of the road. By taking into account both of these factors, smart lighting automation system is proposed using Pattern Recognition Technique applied on vehicle number-plates. In this proposal, the road is sectionalized into zones, and based on smart Pattern Recognition Technique, the control system of the road lighting illuminates only the zone that the vehicles pass through. Economic analysis is provided in this paper to support the value of using this design of lighting control system.
文摘Introduction: In 21st century, road traffic accidents (RTA) are considered as increasing epidemic of non-communicable disease which is abandoned and needs special attention to prevent them. The aim of this study was to assess the factors and pattern of injuries associated with road traffic accidents. Methods: A cross sectional study was conducted among 112 RTA victims and 56 drivers in Palpa District of Nepal. The association of factors and pattern of injuries with exposure to accidents was assessed using Fisher’s exact test. Bivariate logistic regression examined the association between driving and socio-demographics factors and exposure to road accidents. Results: Of 112 RTA victims, 50% were in the age group of 21 to 40 years and 71.4% were male. Drivers who were in the age less than or equal to 30 years were more likely (OR: 3.6;95% CI: 1.0, 14.3) to expose to an accident than those who were above 30 years. Similarly, those having driving speed less than 40 km/hr were less likely to expose to an accident than those with speed 40 - 60 km/hr (OR: 6.0;95% CI: 0.8, 73.5) and those with speed more than 60 km/hr (OR 7.8;95% CI: 1.0, 100.1). Moreover, the driving experience was also found positively associated (OR: 5.6;95% CI: 1.1, 35.5) with the exposure to an accident. Conclusion: Being in younger age group, male gender, morning time, the driving speed, driving experiences, and driving hours on the road were positively associated with RTA. The efforts should be made to enforce laws in control of speed targeting experienced drivers and those with younger age groups.
基金This work is supported by the following projects： National Natural Science Foundation of China grant 60772136, 111 Development Program of China NO.B08038, National Science ＆ Technology Pillar Program of China NO.2008BAH22B03 and NO. 2007BAH08B01.
文摘In order to identify any traces of suspicious activities for the networks security, Network Traffic Analysis has been the basis of network security and network management. With the continued emergence of new applications and encrypted traffic, the currently available approaches can not perform well for all kinds of network data. In this paper, we propose a novel stream pattern matching technique which is not only easily deployed but also includes the advantages of different methods. The main idea is： first, defining a formal description specification, by which any series of data stream can be unambiguously descrbed by a special stream pattern; then a tree representation is constructed by parsing the stream pattern; at last, a stream pattern engine is constructed with the Non-t-mite automata （S-CG-NFA） and Bit-parallel searching algorithms. Our stream pattern analysis system has been fully prototyped on C programming language and Xilinx Vn-tex2 FPGA. The experimental results show the method could provides a high level of recognition efficiency and accuracy.
基金supported by Basic Science Research Program through the National Research Foundation of Korea(NRF)funded by the Ministry of Education(2014R1A1A2057796)and(2015R1D1A1A01059049)
文摘The phenomenon of data explosion represents a severe challenge for the upcoming big data era.However,the current Internet architecture is insufficient for dealing with a huge amount of traffic owing to an increase in redundant content transmission and the end-point-based communication model.Information-centric networking(ICN)is a paradigm for the future Internet that can be utilized to resolve the data explosion problem.In this paper,we focus on content-centric networking(CCN),one of the key candidate ICN architectures.CCN has been studied in various network environments with the aim of relieving network and server burden,especially in name-based forwarding and in-network caching functionalities.This paper studies the effect of several caching strategies in the CCN domain from the perspective of network and server overhead.Thus,we comprehensively analyze the in-network caching performance of CCN under several popular cache replication methods(i.e.,cache placement).We evaluate the performance with respect to wellknown Internet traffic patterns that follow certain probabilistic distributions,such as the Zipf/Mandelbrot–Zipf distributions,and flashcrowds.For the experiments,we developed an OPNET-based CCN simulator with a realistic Internet-like topology.
基金supported by the National Natural Science Foundation of China[grant number 52371359]the Dalian Science and Technology Innovation Fund[grant number 2022JJ12GX015].
文摘Recognition of ship traffic patterns can provide insights into the rules of navigation,maneuvering,and collision avoidance for ships at sea.This is essential for ensuring safe navigation at sea and improving navigational efficiency.With the popularization of the Automatic Identification System(AIS),numerous studies utilized ship trajectories to identify maritime traffic patterns.However,the current research focuses on the spatiotemporal behavioral feature clustering of ship trajectory points or segments while lacking consideration for multiple factors that influence ship behavior,such as ship static and maritime geospatial features,resulting in insufficient precision in ship traffic pattern recognition.This study proposes a ship traffic pattern recognition method that considers multi-attribute trajectory similarity(STPMTS),which considers ship static feature,dynamic feature,port geospatial feature,as well as semantic relationships between these features.First,A ship trajectory reconstruction method based on grid compression was introduced to eliminate redundant data and enhance the efficiency of trajectory similarity measurements.Subsequently,to quantify the degree of similarity of ship trajectories,a trajectory similarity measurement method is proposed that combines ship static and dynamic information with port geospatial features.Furthermore,trajectory clustering with hierarchical methods was applied based on the trajectory similarity matrix for dividing trajectories into different clusters.The quality of the similarity measurement results was evaluated by quality criterion to recognize the optimal number of ship traffic patterns.Finally,the effectiveness of the proposed method was verified using actual port ship trajectory data from the Tianjin Port of China,ranging from September to November 2016.Compared with other methods,the proposed method exhibits significant advantages in identifying traffic patterns of ships entering and leaving the port in terms of geometric features,dynamic features,and adherence to navigation rules.This study could serve as an inspiration for a comprehensive exploration of maritime transportation knowledge from multiple perspectives.
文摘Although the number of road traffic accidents,fatalities,injuries has been slightly reduced in recent years,HCMC(Ho Chi Minh City)would still face challenges in reducing and restraining road traffic accidents in the future.This paper presents the results of road traffic accident data analysis over the past 3 years that we collected from the Road-Railway Police Bureau in HCMC.Based on the results,we could be able to deeply understand trends,characteristics,and causes of road traffic accidents.Such a deep understanding is a scientific basis to study and formulate synchronous strategy along with specific solutions to solve road traffic accident problems more effectively in the future.
基金supported by the Ministry of Environment(Environmental Protection Administration),Taiwan(Projects EPA-106-L103-02-A022,EPA-106-L102-02-A142)the"National"Science and Technology Council(Ministry of Science and Technology),Taiwan(Nos.108-2625-M-008-002,108-2119-M-008-003,108-2636-E-008-004,109-2636-E-008-008,110-2636-E-008-006,111-2636-E-008-014,and 112-2636-E-008-005(Young Scholar Fellowship Program),112-2119-M-008-010,and 108-2638-E-008-001-MY2(Shackleton Program Grant)).
文摘Traffic emissions have become the major air pollution source in urban areas.Therefore,understanding the highly non-stational and complex impact of traffic factors on air quality is very important for building air quality prediction models.Using real-world air pollutant data from Taipei City,this study integrates diverse factors,including traffic flow,speed,rainfall patterns,andmeteorological factors.We constructed a Bayesian network probabilitymodel based on rainfall events as a big data analysis framework to investigate understand traffic factor causality relationships and condition probabilities for meteorological factors and air pollutant concentrations.Generalized Additive Model(GAM)verified non-linear relationships between traffic factors and air pollutants.Consequently,we propose a long short term memory(LSTM)model to predict airborne pollutant concentrations.This study propose a new approach of air pollutants and meteorological variable analysis procedure by considering both rainfall amount and patterns.Results indicate improved air quality when controlling vehicle speed above 40 km/h and maintaining an average vehicle flow<1200 vehicles per hour.This study also classified rainfall events into four types depending on its characteristic.Wet deposition from varied rainfall types significantly affects air quality,with TypeⅠrainfall events(long-duration heavy rain)having the most pronounced impact.An LSTM model incorporating GAM and Bayesian network outcomes yields excellent performance,achieving correlation R^(2)>0.9 and 0.8 for first and second order air pollutants,i.e.,CO,NO,NO_(2),and NO_(x);and O_(3),PM_(10),and PM_(2.5),respectively.
基金The US National Science Foundation (No. CMMI-0408390,CMMI-0644552)the American Chemical Society Petroleum Research Foundation (No.PRF-44468-G9)+3 种基金the Research Fellowship for International Young Scientists (No.51050110143)the Fok Ying-Tong Education Foundation (No.114024)the Natural Science Foundation of Jiangsu Province (No.BK2009015)the Postdoctoral Science Foundation of Jiangsu Province (No.0901005C)
文摘Based on Gaussian mixture models（GMM）, speed, flow and occupancy are used together in the cluster analysis of traffic flow data. Compared with other clustering and sorting techniques, as a structural model, the GMM is suitable for various kinds of traffic flow parameters. Gap statistics and domain knowledge of traffic flow are used to determine a proper number of clusters. The expectation-maximization （E-M） algorithm is used to estimate parameters of the GMM model. The clustered traffic flow pattems are then analyzed statistically and utilized for designing maximum likelihood classifiers for grouping real-time traffic flow data when new observations become available. Clustering analysis and pattern recognition can also be used to cluster and classify dynamic traffic flow patterns for freeway on-ramp and off-ramp weaving sections as well as for other facilities or things involving the concept of level of service, such as airports, parking lots, intersections, interrupted-flow pedestrian facilities, etc.
基金The Program for New Century Excellent Talents in University(No.NCET-11-0565)the Fundamental Research Funds for the Central Universities(No.K13JB00160,2012JBZ010,2011JBM217)+2 种基金the Ph.D.Programs Foundation of Ministry of Education of China(No.20120009120010)the Program for Innovative Research Team in University of Ministry of Education of China(No.IRT201206)the Natural Science Foundation of Shandong Province(No.ZR2012FM010,ZR2011FZ001)
文摘In order to classify the Intemet traffic of different Internet applications more quickly, two open Internet traffic traces, Auckland I1 and UNIBS traffic traces, are employed as study objects. Eight earliest packets with non-zero flow payload sizes are selected and their payload sizes are used as the early-stage flow features. Such features can be easily and rapidly extracted at the early flow stage, which makes them outstanding. The behavior patterns of different Intemet applications are analyzed by visualizing the early-stage packet size values. Analysis results show that most Internet applications can reflect their own early packet size behavior patterns. Early packet sizes are assumed to carry enough information for effective traffic identification. Three classical machine learning classifiers, classifier, naive Bayesian trees, i. e., the naive Bayesian and the radial basis function neural networks, are used to validate the effectiveness of the proposed assumption. The experimental results show that the early stage packet sizes can be used as features for traffic identification.
文摘加密技术的广泛应用给恶意活动提供了藏匿的机会,对网络安全监测体系带来了巨大挑战.现有的加密流量检测方法主要是在单个数据包级别提取统计流量特征,因此可能会由于潜在的IP分片而破坏原始连续通信行为中隐含的特征.此外,大多数方法对于网络流的交互模式建模粒度较粗,未能深入挖掘对等实体间的通信意图,难以适应新型恶意软件通信行为和通信量的变化.本文以交互为分析粒度,提出了方法 ISG-Net(interaction state graphnet).该方法基于状态转换构建流量交互状态图,并引入了融合流量时序信息的自注意力编码模型.特别地,本文通过交互状态图获取蕴含全局信息的交互状态表示,然后对每次交互进行细粒度的特征提取,以融合得到会话(双向流)的表示.在3个数据集上的实验结果表明,在加密恶意流量检测任务中,本文方法在准确性、鲁棒性和容错性均优于现有算法.
基金Project supported by the Russian Foundation for Basic Research(No.18-07-00518)the National Natural Science Foundation of China(No.10972212)
文摘Travel time through a ring road with a total length of 80 km has been predicted by a viscoelastic traffic model(VEM), which is developed in analogous to the non-Newtonian fluid flow. The VEM expresses a traffic pressure for the unfree flow case by space headway, ensuring that the pressure can be determined by the assumption that the relevant second critical sound speed is exactly equal to the disturbance propagation speed determined by the free flow speed and the braking distance measured by the average vehicular length. The VEM assumes that the sound speed for the free flow case depends on the traffic density in some specific aspects, which ensures that it is exactly identical to the free flow speed on an empty road. To make a comparison, the open Navier-Stokes type model developed by Zhang(ZHANG, H. M. Driver memory, traffic viscosity and a viscous vehicular traffic flow model. Transp. Res. Part B, 37, 27–41(2003)) is adopted to predict the travel time through the ring road for providing the counterpart results.When the traffic free flow speed is 80 km/h, the braking distance is supposed to be 45 m,with the jam density uniquely determined by the average length of vehicles l ≈ 5.8 m. To avoid possible singular points in travel time prediction, a distinguishing period for time averaging is pre-assigned to be 7.5 minutes. It is found that the travel time increases monotonically with the initial traffic density on the ring road. Without ramp effects, for the ring road with the initial density less than the second critical density, the travel time can be simply predicted by using the equilibrium speed. However, this simpler approach is unavailable for scenarios over the second critical.
文摘With enormous growth of the number of Internet users and appearance of new applications, characterization of Internet traffic has attracted more and more attention and has become one of the major challenging issues in telecommunication network over the past few years. In this paper, we study the network traffic pattern of the aggregate traffic and of specific application traffic, especially the popular applications such as P2P, VoIP that contribute most network traffic. Our study verified that majority Internet backbone traffic is contributed by a small portion of users and a power function can be used to approximate the contribution of each user to the overall traffic. We show that P2P applications are the dominant traffic contributor in current Internet Backbone of China. In addition, we selectively present the traffic pattern of different applications in detail.
文摘Early detection and rapid resolution network congestion can considerably improve network capacity. Consequently, much research has been carried out on predicting traff ic patterns in 3G networks. This paper introduces an access point centric approach that is implemented by two prediction models, the traffic abstraction model and the order-k Markov model. Traffi c predictions are carried out to support the congestion control in the semi-smart antenna systems. The simulation result shows that the cumulative error rate is below 25% even carrying out multi-step-ahead predictions.
