Please wait a minute...

Current Issue

    30 September 2020, Volume 4 Issue 3
    Topic:IoT in Intelligent Transportation
    Space-air-ground integrated networks:review and prospect
    Xuemin(Sherman) SHEN,Nan CHENG,Haibo ZHOU,Feng LYU,Wei QUAN,Weisen SHI,Huaqing WU,Conghao ZHOU
    2020, 4(3):  3-19.  doi:10.11959/j.issn.2096-3750.2020.00142
    Asbtract ( 3941 )   HTML ( 581)   PDF (4834KB) ( 3634 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    With the advance of the information technologies,the scale of the information services gradually expands,from ground services,to aerial,maritime,and spatial services,with the soaring requirements on multi-dimensional comprehensive information resources.The space-air-ground integrated networks (SAGINs) are envisioned to provide seamless network services to spatial,aerial,maritime,and ground users,satisfying the future network requirements on all-time,all-domain,and all-space communications and interconnected networking.Firstly,we reviewed the current research development of SAGINs,discussing the research trends on the low-earth orbiting (LEO) satellite constellation and space-ground network integration.Then,the reinforcement learning (RL) framework was proposed in SAGINs to address the problems of complex architecture,high dynamics,and resource constraints in SAGINs,which facilitated efficient and fast network design,analysis,optimization,and management.As a case study,the method of applying deep RL (DRL) was showed for the intelligent access network selection in SAGINs.To improve the RL training efficiency,a comprehensive SAGINs simulation platform was established,through which the agent-environments interaction was accelerated and training samples could be obtained more cost-effectively.Finally,some open research directions were presented.

    Smart tags based on the batteryless backscatter technology:applications and challenges
    Ying GUO,Gongpu WANG,Zonghui LI,Ruisi HE,Zhangdui ZHONG
    2020, 4(3):  20-29.  doi:10.11959/j.issn.2096-3750.2020.00183
    Asbtract ( 452 )   HTML ( 68)   PDF (2059KB) ( 842 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    Since the radio frequency identification (RFID) technology was put forward,it has been widely used in the transportation,logistics,industry and business due to its convenience and high efficiency.As a carrier for storing recognizable data,the RFID tags play a crucial role in the Internet of things (IoT).More and more functions and modules are embedded in the RFID tags and developed into smart tags in different application fields.Recently,wireless batteryless smart tags have arisen and grown rapidly with the development of the IoT and various emerging backscatter technologies.Wireless batteryless smart tags use the passive backscatter technology to harvest the energy and transmit information through radio frequency signals.Starting from the RFID technology,the history of the RFID and smart tags was introduced briefly,the differences between traditional smart tags and emerging wireless smart tags were compared,the advantages of wireless batteryless smart tags were concluded,several specific applications of it in different fields were listed,and the open challenges were analyzed.

    SDN enabled space-terrestrial integrated network architecture of railway system
    Yinglei TENG,Xin LI,Jian WANG,Bogen CAI,Mei SONG
    2020, 4(3):  30-41.  doi:10.11959/j.issn.2096-3750.2020.00184
    Asbtract ( 280 )   HTML ( 41)   PDF (2709KB) ( 672 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    In view of the current situation that it is difficult to guarantee the safe and reliable transmission of data with the poor geographical environment in the single standard train communication network,the communication needs of each business of the railway system were investigated and a space-terrestrial integrated network architecture based on software defined network (SDN) and network functions virtualization (NFV) was proposed.By focusing on the controller to manage the physical facilities,the architecture realized decoupling application and physical infrastructure.The design of the architectural details and the requirements of the agreement for the architecture in the functional requirements and the information flow were discussed.In the end,the performance comparison between the space-terrestrial integrated network and other single-system network coverage was given,problems remaining to be solved and some feasible solutions faced by the space-terrestrial integrated network were briefly discussed.

    Research on the UAV-aided data collection and trajectory design based on the deep reinforcement learning
    Zhiyu MOU,Yu ZHANG,Dian FAN,Jun LIU,Feifei GAO
    2020, 4(3):  42-51.  doi:10.11959/j.issn.2096-3750.2020.00177
    Asbtract ( 1355 )   HTML ( 167)   PDF (5066KB) ( 1075 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    The Internet of things (IoT) era needs to realize the wide coverage and connections for the IoT nodes.However,the IoT communication technology cannot collect data timely in the remote area.UAV has been widely used in the IoT wireless sensor network for the data collection due to its flexibility and mobility.The trajectory design of the UAV assisted sensor network data acquisition was discussed in the proposed scheme,as well as the UAV charging demand in the data collection process was met.Specifically,based on the hierarchical reinforcement learning with the temporal abstraction,a novel option-DQN (option-deep Q-learning) algorithm targeted for the discrete action was proposed to improve the performance of the data collection and trajectory design,and control the UAV to recharge in time to ensure its normal flight.The simulation results show that the training rewards and speed of the proposed method are much better than the conventional DQN (deep Q-learning) algorithm.Besides,the proposed algorithm can guarantee the sufficient power supply of UAV by controlling it to recharge timely.

    Outage performance analysis of wireless powered railway Internet of things
    Jiaxing MA,Ke XIONG,Yu ZHANG,Zhangdui ZHONG,Qiang NI
    2020, 4(3):  52-59.  doi:10.11959/j.issn.2096-3750.2020.00182
    Asbtract ( 175 )   HTML ( 27)   PDF (3548KB) ( 643 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    Based on the scenario of railway Internet of things,the system outage performance of the relay network was analyzed,which was assisted with the power beacon (PB),using the half-duplex decode-and-forward relay mode over the Rician fading channel.In view of the equipment supply problems in railway scenes,such as difficult battery replacing,high management overhead,difficult wiring,etc.,the wireless energy collection was applied to railway scenes,providing sufficient and stable energy for the energy-constrained wireless equipment,thus solving the equipment supply problems in traditional railways.Considering that the source node and the relay node in the network were energy limited nodes,and the energy of the information transmission came from the radio frequency signal transmitted from the PB deployed on the train.The source node and the relay node collected energy from the PB,and the source node sent information to the relay node by using the collected energy,and then the relay node forwarded the information received to the destination node.The closed-form expressions of the network end-to-end outage probability and the throughput were derived.The analytical results were demonstrated by Monte Carlo simulation.And based on this analysis,the impact of the ratio of transmitting power of the PB to noise,the Rician K-factor,the time switching factor,transmission rate and relative position on the end-to-end outage probability and throughput were studied.When the train is in the middle of the source node and the relay node,the system can obtain better outage and throughput performance.

    Research on real-time fusion method of multi-source heterogeneous flight trajectory data stream
    Zhuxi ZHANG,Wang TIAN,Shaochuan ZHU,Hongyan LIU,Xi ZHU
    2020, 4(3):  60-68.  doi:10.11959/j.issn.2096-3750.2020.00181
    Asbtract ( 385 )   HTML ( 34)   PDF (2262KB) ( 667 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    Secondary surveillance radar (SSR) and automatic dependent surveillance-broadcast (ADS-B) are the two main surveillance methods coexisting in the airspace surveillance system.In order to improve the accuracy and stability of surveillance,real-time fusion of SSR and ADS-B trajectory is crucial.In view of the fact that the existing methods are difficult to meet the real-time fusion requirements of large-scale trajectories,a real-time fusion method of SSR and ADS-B data streams was designed with big data technology.This method was based on the big data processing framework of micro-batch processing and followed the MapReduce programming model.While obtaining a fusion trajectory of high quality,it ensured high concurrency and real-time data processing capability of the system.Finally,a real-time flight simulation experiment based on real flight data was carried out to verify the feasibility of the method.

    Multi-agent driven collaborative decision mechanism of information fusion for autonomous driving vehicles
    Jiayu CAO,Supeng LENG,Ke ZHANG
    2020, 4(3):  69-77.  doi:10.11959/j.issn.2096-3750.2020.00179
    Asbtract ( 639 )   HTML ( 79)   PDF (1223KB) ( 1011 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    Autonomous vehicles play an important part in intelligent transportation systems.In these vehicles,driving control decision is obtained based on the collection of massive traffic states and intensive information processing.However,the spatial-temporal characteristics of the traffic states and the constrained environmental perception range of an individual vehicle seriously undermine the effectiveness of the state collection.Multi-agent driven collaborative decision provides a potential approach to address the problem.A multi-dimensional information fusion mechanism was proposed,which improved the gain of vehicular information fusion for autonomous driving tasks.Moreover,an intelligent distributed decision algorithm was designed for autonomous driving applications,which maximized the road traffic flow while maximizing the gain of information fusion on the autonomous driving mission under vehicular cost and resource constraints.Numerical results demonstrate the convergence and practicability of the proposed algorithm.

    Prediction of the waterborne navigation density based on the multi-feature spatio-temporal graph convolution network
    Wei DONG,Leilei ZHANG,Ziheng JIN,Wei SUN,Junbo GAO
    2020, 4(3):  78-85.  doi:10.11959/j.issn.2096-3750.2020.00176
    Asbtract ( 244 )   HTML ( 38)   PDF (4338KB) ( 481 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    In the face of the development of the information technology in the port and waterway,the Internet of things (IoT) technology can help to build China’s water transport perception network.The big data analysis of the waterborne transport has become a hot topic for researchers and practitioners in the field of transportation.The navigation density of each port in the water transportation is nonlinear and spatio-temporal correlation,so it is a great challenge to accurately predict it.A multi-feature spatiotemporal graph convolution network (MFSTGCN) was proposed to solve the problem of the traffic density prediction.MFSTGCN effectively captured the spatial-temporal correlation of the ship navigation density data by using the spatial convolution and temporal convolution through three features,which were navigation volume,average ship speed and ship density.The experiment was carried out on the automatic identification system (AIS) data set collected from a shipping platform.The results show that the prediction effect of the MFSTGCN model is better than the spatio-temporal graph convolution network (STGCN) model.

    Research on the optimization method of emergency material post transportation model based on bi-level programming
    Haixia ZHOU,Yurong MEI,Furu LYU,Zhixin SUN
    2020, 4(3):  86-95.  doi:10.11959/j.issn.2096-3750.2020.00180
    Asbtract ( 201 )   HTML ( 23)   PDF (1748KB) ( 498 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    Emergency logistics is a special logistics activity that protects the need of personnel,materials and funds in the event of a major emergency.In the post transportation model of emergency supplies,how to quickly and accurately deliver a large amount of rescue materials to the place of need is a huge challenge to emergency logistics.The logistics cost and the logistics time in the entire logistics process could be minimized by the bi-level planning method while meeting the demand for emergency supplies at the demand point.The bi-level programming model was constructed with the minimum logistics cost of the upper layer and the shortest logistics time of the bottom layer as the goal,and a hybrid tabu search genetic algorithm (HTSGA) was designed to solve the model,which solved the problem of emergency logistics transportation route optimization after the disaster.Finally,the experimental result comparison verified the effectiveness of the model and algorithm.

    Research on the spectrum sensing and sharing technology in the dynamic spatiotemporal data driven cognitive Internet of vehicles
    Caili GUO,Jiujiu CHEN,Yidi XUAN,He ZHANG
    2020, 4(3):  96-105.  doi:10.11959/j.issn.2096-3750.2020.00178
    Asbtract ( 297 )   HTML ( 29)   PDF (2141KB) ( 921 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    With the explosive development of the intellectualization and network connection of the global automobile industry,the communication technology as a crucial support of the Internet of vehicles (IoV) is facing the problem of spectrum shortage.In addition to providing security services,the diverse service demands of the IoV make the introduction of the cognitive radio technology an effective solution,which can share heterogeneous spectrum resources integrating the sub-6 GHz and millimeter-wave spectrum resources with primary users.But the performance is limited due to the influence of the complex dynamic environment of the IoV.To address this issue,a novelty method was proposed which aimed to make full use of the potential multi-source dynamic spatiotemporal data,mine and learn the changing rules of the vehicle trajectory and traffic flow,and the rules were used to guide the sensing and sharing of the spectrum resource.The system-level simulation platform was built for simulation analysis,the results showed that the performance of the proposed scheme was effectively improved.

    Railway safety monitoring algorithm based on distributed optical fiber vibration sensor
    Fuyang CHEN,Bin JIANG,Yu SHA
    2020, 4(3):  106-111.  doi:10.11959/j.issn.2096-3750.2020.00173
    Asbtract ( 179 )   HTML ( 18)   PDF (923KB) ( 625 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    Aiming at the monitoring problem of the human climbing behaviour existing along the railway,a railway safety detection algorithm based on distributed optical fiber vibration sensors was proposed by combining the distributed optical fiber sensing technology and signal analysis technology.The surrounding vibration was sensed and transmitted through the optical cables laid along the fence network of the railway,and then the Internet of things (IoT) connection between the railway and monitoring algorithm was built to realize the intelligent monitoring of the climbing behavior.In view of the complicated surrounding environment of the railway and more interference,the Hamming window and wavelet threshold denoising method were used to filter the signal of each frame to improve the signal-to-noise ratio of the vibration signal.In the selection of features,the power spectrum and short-time over-level rate of the signal were extracted from the time domain and frequency domain respectively as a joint feature to determine whether there was climbing or creeping behavior.Since that the climbing behavior was spatially continuous,the minimum alarm range was set to filter out alarms with a too small range,which improved the accuracy of the monitoring system.

    Big data mining and application of long-distance oil and gas pipeline
    Tao YU,Lijun LIU,Hongjun CHEN,Yao YU
    2020, 4(3):  112-119.  doi:10.11959/j.issn.2096-3750.2020.00174
    Asbtract ( 258 )   HTML ( 27)   PDF (5212KB) ( 367 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    In response to the need of the intelligent construction of the long-distance oil and gas pipeline in the future,combining with the supervisory control and data acquisition (SCADA) system and operating parameters of the oil and gas pipeline,comparing with the characteristics of traditional theoretical methods and big data mining methods,the direction of big data to promote intelligent pipeline and three steps of digital informatization,theorization,and intelligence of the pipeline intelligence research were proposed.The pipeline intelligent architecture was established,which included a physical layer,a data layer,a data mining layer,an application layer,and a user layer.The data mining layer was the core of the architecture.The statistical analysis,time series prediction and working condition identification and other application cases showed that the use of the big data mining could effectively solve the actual production business needs and guide the future pipeline intelligent research and construction.

    Vehicle detection based on SqueezeNet convolutional neural network
    Zefa WEI,Hua CUI
    2020, 4(3):  120-125.  doi:10.11959/j.issn.2096-3750.2020.00175
    Asbtract ( 285 )   HTML ( 42)   PDF (1394KB) ( 567 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    In the intelligent transportation system,aiming at the problem of low portability and speed of detection in vehicle target detection algorithm,a vehicle detection method based on SqueezeNet convolutional neural network was proposed.In order to realize the rapid detection of vehicle targets,improve the portability and shorten the detection time of the single frame,the model was trained on the UA-DETRAC dataset by fusing the SqueezeNet with the single shot multibox detector (SSD) algorithm.The experimental results showed that the time of the single frame detection could reach 22.3 ms and the model size was 16.8 MB.Compared with the original SSD algorithm,the model size was reduced by about 8/9.At the same time,the accuracy of the proposed model was guaranteed.


Copyright Information
Quarterly,started in 2017
Cpmpetent Unit:Ministry of Industry and Information Technology of the People's Republic of China
Sponsor:Posts & Telecom Press Co.,Ltd.
Publisher: China InfoCom Media Group
Editor:Editor Board of Chinese Journal on Internet of Things
Editor-in-Chief:YIN Hao
Executive Editor-in-Chief:ZHU Hongbo
Director:LI Caishan
Address:F2, Beiyang Chenguang Building, Shunbatiao No.1 Courtyard, Fengtai District, Beijing, China
Tel:010-53878076、53879096、53879098
E-mail:wlwxb@bjxintong.com.cn
ISSN 2096-3750
CN 10-1491/TP
Visit
Total visitors:
Visitors of today:
Now online: