Length matters:Scalable fast encrypted internet traffic service classification based on multiple protocol data unit length sequence with composite deep learning

As an essential function of encrypted Internet traffic analysis,encrypted traffic service classification can support both coarse-grained network service traffic management and security supervision.However,the traditional plaintext-based Deep Packet Inspection(DPI)method cannot be applied to such a classification.Moreover,machine learning-based existing methods encounter two problems during feature selection:complex feature overcost processing and Transport Layer Security(TLS)version discrepancy.In this paper,we consider differences between encryption network protocol stacks and propose a composite deep learning-based method in multiprotocol environments using a sliding multiple Protocol Data Unit(multiPDU)length sequence as features by fully utilizing the Markov property in a multiPDU length sequence and maintaining suitability with a TLS-1.3 environment.Control experiments show that both Length-Sensitive(LS)composite deep learning model using a capsule neural network and LS-long short time memory achieve satisfactory effectiveness in F1-score and performance.Owing to faster feature extraction,our method is suitable for actual network environments and superior to state-of-the-art methods.

Application of Risk Index to Risk-Based Decision-Making in Vessel Traffic Service System

The applications of risk index to risk estimation, risk acceptability, and cost-benefit analysis for planning vessel traffic service （VTS） system were analyzed. An example of Wuhan Port shows that its application is easily implemented and can be helpful in a comprcbensive and scientific decision-making. Especially aiming to the difficult problems with respect to risk prediction, risk acceptability and cost-benefit assessment, this article put forward some new solutions based on risk-index, such as the trendline estimation, ALARP （as low as reasonably practicable） matrix and weighted cost-benefit analysis, with a fairly good operability and comparability.

Traffic services for vehicles: the process from receiving raw probe data to space-time diagrams and the resulting traffic service

Today, large quantities of vehicle data(FCD:floating car data) are widely used by traffic service providers to create and broadcast traffic states in road networks. As a first processing step, all raw position data received from Global Positioning Systems(GPS) have to be map matched in a digital road map. The technical aspects of such a matching process for GPS data are described in this report. After the matching process, spacetime-diagrams are created of the probe data showing traffic situation details over space and time. Various examples illustrate how traffic service quality depends on the number of matched GPS raw data; it will be stated that when 2% of connected vehicles in the total traffic flow are sending their GPS data in shorter time intervals, a high quality and precise reconstruction of the current traffic phases is achieved. Traffic reconstruction is followed by a translation into traffic information messages, which can be sent and used in vehicle navigation systems for driver information and dynamic route guidance.

Review on artificial intelligence techniques for improving representative air traffic management capability

The use of artificial intelligence(AI)has increased since the middle of the 20th century,as evidenced by its applications to a wide range of engineering and science problems.Air traffic management(ATM)is becoming increasingly automated and autonomous,making it lucrative for AI applications.This paper presents a systematic review of studies that employ AI techniques for improving ATM capability.A brief account of the history,structure,and advantages of these methods is provided,followed by the description of their applications to several representative ATM tasks,such as air traffic services(ATS),airspace management(AM),air traffic flow management(ATFM),and flight operations(FO).The major contribution of the current review is the professional survey of the AI application to ATM alongside with the description of their specific advantages:(i)these methods provide alternative approaches to conventional physical modeling techniques,(ii)these methods do not require knowing relevant internal system parameters,(iii)these methods are computationally more efficient,and(iv)these methods offer compact solutions to multivariable problems.In addition,this review offers a fresh outlook on future research.One is providing a clear rationale for the model type and structure selection for a given ATM mission.Another is to understand what makes a specific architecture or algorithm effective for a given ATM mission.These are among the most important issues that will continue to attract the attention of the AI research community and ATM work teams in the future.

Internet Multimedia Traffic Classification from QoS Perspective Using Semi-Supervised Dictionary Learning Models

To address the issue of finegrained classification of Internet multimedia traffic from a Quality of Service(QoS) perspective with a suitable granularity, this paper defines a new set of QoS classes and presents a modified K-Singular Value Decomposition(K-SVD) method for multimedia identification. After analyzing several instances of typical Internet multimedia traffic captured in a campus network, this paper defines a new set of QoS classes according to the difference in downstream/upstream rates and proposes a modified K-SVD method that can automatically search for underlying structural patterns in the QoS characteristic space. We define bagQoS-words as the set of specific QoS local patterns, which can be expressed by core QoS characteristics. After the dictionary is constructed with an excess quantity of bag-QoSwords, Locality Constrained Feature Coding(LCFC) features of QoS classes are extracted. By associating a set of characteristics with a percentage of error, an objective function is formulated. In accordance with the modified K-SVD, Internet multimedia traffic can be classified into a corresponding QoS class with a linear Support Vector Machines(SVM) clas-sifier. Our experimental results demonstrate the feasibility of the proposed classification method.

Urban Traffic Information Service Application Grid

Traffic information processing is very complicated because of dynamic, cooperative and distributed features. This paper describes the prototype system version 2.0 of Urban Traffic Information Service Application Grid (UTISAG), which is based on the previous version. In this version, a new architecture and more enhanced services are introduced, The. remarkable characteristic of the new system is providing dynamic information services for travelers by grid technology. Therefore, the key research includes integrating large multi-source traffic data, forecasting route status, simulating regional traffic flow parallelly, and implementing optimum dynamic travel scheme based on massive GPS data.

Anchor Vertex Selection for Enhanced Reliability of Traffic Offloading Service in Edge-Enabled Mobile P2P Social Networks

As the rapid growth of mobile social networks,mobile peer-to-peer(P2P)communications and mobile edge computing(MEC)have been developed to reduce the traffic load and improve the computation capacity of cellular networks.However,the stability of social network is largely ignored in the advances of P2P and MEC,which is related to the social relations between users.It plays a vital role in improving the efficiency and reliability of traffic offloading service.In this paper,we integrate an edge node and the nearby P2P users as a mobile P2P social network and introduce the problem of adaptive anchored(k,r)-core to maintain the stability of multiple mobile P2P networks.It aims to adaptively select and retain a set of critical users for each network,whose participation is critical to overall stability of the network,and allocate certain resource for them so that the maximum number of users of all networks will remain engaged and the traffic of cellular network can be minimized.We called the retained users as anchor vertices.To address it,we devise a peer-edge-cloud framework to achieve the adaptive allocation of resources.We also develop a similarity based onion layers anchored(k,r)-core(S-OLAK)algorithm to explore the anchor vertices.Experimental results based on a real large-scale mobile P2P data set demonstrate the effectiveness of our method.

Civil unmanned aircraft system operation in national airspace: A survey from Air Navigation Service Provider perspective

Unmanned Aircraft Systems(UASs) have advanced technologically and surged exponentially over recent years. Currently, due to safety concerns, most civil operations of UAS are conducted in low-level uncontrolled area or in segregated controlled airspace. As the industry progresses, both operational and technological capabilities have matured to the point where UASs are expected to gain greater freedom of access to both controlled and uncontrolled airspace. Extensive technical and regulatory surveys have been conducted to enable the expanded operations. However, most surveys are derived from the perspective of UAS own operating mechanism and barely consider interactions of their non-segregated activities with the Air Traffic Management(ATM) system. Hence, to fill the gap, this paper presents a survey conducted from the perspective of Air Navigation Service Provider(ANSP), which serves to accommodate these new entrants to the overall national airspace while continuing flight safety and efficiency. The primary objectives of this paper are to:(A) describe what typical ANSP-supplied UAS Traffic Management(UTM) architecture is required to facilitate all types of civil UAS operations;(B) identify three major ANSP considerations on how UAS can be accommodated safely in civil airspace;(C) outline future directions and challenges related with UAS operations for the ANSP.

Traffic Source Characterization：Considering Real Demands of Communication Attempts

in order to project a reliable telecommunication network ,we have to measure the call lossrate of present traffic and to predzct the traffic of hajective network. In this paper we point out that afactor of real communication needs for subscrihas should be added in studying the traffic source char-acterization. Generally, the predicted traffic does not equal to the real demends, Considered asubscriber's psychological facter for attempts in busy-hour, a mathematical medel of probable dertva-tive calls from each real communication demand is given,with which the calling-up probabity, andthe repeating attempt probability of original subscribers on line occupation are calculated and the rela-tionship between the traffic and the real cammunication need is predicted.

Research on the measurement of the price change of telecom services in China

It is difficult to measure the total change of the telecom service price （TSP） in China due to the complexity of TSP and the diversity of telecom service. This article analyzes the relation between telecom service revenue and traffic volumes of telecom service and deduces the method of measuring the total change in tendency of telecom price, which is based on the consumer＇s actual payment for telecom services. After describing the changing trend of TSP with the time series data from 1949 to 2000, the TSP showed a continuous declining tendency during 1949～1975. In contrast, the TSP showed a rising tendency from 1976 to 1991 and a sharp declining trend after 1992. Empirical tests and actual background of telecom reform support the results.