Editorial Trajectory Data Mining in Distributed Sensor...

EditorialTrajectory Data Mining in Distributed Sensor Networks

Shaojie Qiao,1 Huidong (Warren) Jin,2 Yunjun Gao,3 Lu-An Tang,4 and Huanlai Xing1

1School of Information Science and Technology, Southwest Jiaotong University, No. 111, Erhuanlu Beiyiduan, Chengdu 610031, China2Digital Productivity Flagship, CSIRO, GPO Box 664, Canberra, ACT 2601, Australia3College of Computer Science, Zhejiang University, No. 38, Zheda Road, Hangzhou 310058, China4NEC Labs America, 4 Independence Way, Princeton, NJ 08540, USA

Correspondence should be addressed to Shaojie Qiao; [email protected]

Received 29 April 2015; Accepted 29 April 2015

Copyright © 2015 Shaojie Qiao et al. This is an open access article distributed under the Creative Commons Attribution License,which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

The prevalence of distributed sensor networks on the Internethas allowed the field to become a relevant and active researcharea, attracting professionals and researchers from a varietyof fields and disciplines. By incorporating trajectory infor-mation, we can bring distributed sensor networks back to thephysical world, conveniently sharing our real-life experiencesin the virtual world. By mining trajectory patterns or pre-dicting locations from distributed sensor networks, peoplecannot only track and share location-based information witheach other via mobile devices, desktop computers, or sensors,but also benefit from the collective knowledge learned fromthis content [1].

Wireless sensor networks, global positioning systems,and mobile computing techniques are developing rapidly,such that it is now possible to systematically track andpredict the mobility of objects which accumulate a hugecollection of mobile data. Accordingly, there is an ever-increasing interest in performing data analysis over trajectorydata [2]. By processing and analyzing the historical trajectorydata using data mining or machine learning techniques, itis relatively easy to predict accurate information associatedwith the position ofmoving objects.This practice is known astrajectory datamining (TDMfor short) [3, 4], and as our dailylives become even more embedded with these technologies,the importance of TDM is evenmore important. For example,consider the case when a GPS enabled device is takenbeyond the working proximity of satellites and is renderedinoperable. A possible solution to this is to employ TDMsoftware which can provide an intelligent navigation service.

Arguably, a trajectory is one of the most fundamentalproperties in human life, and the research on TDM indistributed sensor networks works to bridge the gap betweenthe virtual and physical world. This research of trajectorydata mining in distributed sensor networks has the potentialto change the way we live, such as enabling applicationsfor better path planning [5, 6] and restaurant/business rec-ommendations. Research can also be conducted to advancehuman mobility modeling and user activity analyses [6–9], which can have broad impacts on social science andengineering.

This special issue covers a wide range of research workwhich can contribute to addressing and solving the chal-lenges faced in the location-based distributed sensor networkresearch domain, for example, spatial and spatiotemporaldata mining in distributed sensor networks, moving objecttracking, indexing, and retrieval in distributed sensor net-works, and activity recognition and sensing for distributedsensor networks.

The readers of TDM in distributed sensor networks canfind in this special issue not only state-of-the-art researchfindings and updated reviews on the common techniquesin TDM, but also important questions to be resolved, thatis, user behavior modeling using physical sensor data andmobile and ubiquitous computing for distributed sensornetworks.

Currently, the problem of security in distributed sensornetwork has attracted a lot of attention from researchers.And cloud data storage and retrieval have become popular

Hindawi Publishing CorporationInternational Journal of Distributed Sensor NetworksVolume 2015, Article ID 913165, 3 pageshttp://dx.doi.org/10.1155/2015/913165

2 International Journal of Distributed Sensor Networks

for efficient datamanagement in distributed sensor networks.In this special issue, X. Zhang et al. proposed an efficientpairing-free auditing scheme for data storage in distributedsensor networks. They employed a third party auditor (TPA)to verify the integrity of sensor data without retrieving theentire data information. In addition, they designed the homo-morphic message authentication codes to reduce the spacestorage of the verification information. They also employedthe random masking technique to guarantee that the TPAcannot recover the primitive data blocks in distributed sensornetworks. Finally, they adapted the proposed scheme forsupporting batch auditing so that the TPA can efficientlyperform multiple auditing tasks.

Multisensor information fusion has garnered wide sup-port in a variety of applications and is gradually becomingan active research area. Bad shunting of track circuit is oneof the major risks for railway traffic safety. The occupancyof track cannot be correctly detected due to bad shunting,which could severely degrade the efficiency of dispatchingtrain commands. In order to improve the efficiency of trackoccupation detection, Z. Hua et al. proposed a multisensortrack occupancy detection model based on chaotic neuralnetworks. This model used the detection results of trackoccupancy collected by multiple sensors as the fundamentaldata and then calculated the weights using the chaotic neuralnetworks and performs data fusion, in order to determinewhether the track is occupied. Extensive experimental resultsdemonstrate that the proposed model can detect the trackoccupancy in an effective and efficient fashion.

With the rapid development of space technology, asteroidexploration becomes an active research field in deep spaceexploration. How to find the global optimum flight programis a key problem in TDM of the deep space exploration.Aiming to handle this problem, M. Wang et al. proposedan approach to design the optimal trajectory by differentialevolution (DE) algorithm for asteroid exploration based onmixed coding, while the celestial sequence and the timesequence are coded together into the chromosomes of DEand optimized simultaneously. The proposed algorithm canutilize the characteristics of the high efficiency and globaloptimization ability of differential evolution, as well as avoidthe problem of high complexity in the branch-and-boundalgorithm and the problem of local optimal solutions in thegreedy algorithm. The proposed approach can be used tosolve the Fourth Contest of National Space Orbit Designin China, and the result shows that both the computationalefficiency and the performance of the algorithm are superior.

Nowadays, a large number of network thermal imagingcameras have worked over distributed sensor networks,offering the capability of online remote intelligent videosurveillance. Z. Li et al. proposed a new intrusion detec-tion and cooperative tracking approach applied for PTZ(Pan/Tilt/Zoom) network thermal imagers. First, the intru-sion detection module eliminates the offset between thecurrent frame and the prior frame via FOV (Field-of-View)matching and then handles intrusion detection by motiondetection in the preset surveillance zone. The cooperativetracking module shifts the priority of tracking by imagerpose estimation, which is based on FOV matching, and

can avoid transferring the local features from one imagerto another one. In addition, another work relevant to thisresearch is addressed. J. Yang et al. presented an originalparticle filter tracking algorithm named labeled particle filterwhich describes each image patch with a binary label. Theyused a one-bit binary label, that is, positive or negative, todescribe the attribute of image patch.Therefore, the candidatetarget template is established only if the label of the candidatetargets matches the label of the reference target, and thecomputational complexity can be reduced. Experimentalresults show that the proposed algorithm can handle the real-time object tracking with less time cost as well as maintaininghigh tracking accuracy.

We hope that this special issue will spark your interest inthe young yet fast-evolving field of trajectory data mining indistributed sensor networks. The techniques and algorithmspresented are of practical utility, rather than selecting algo-rithms that perform well on small “toy” sensor data sets. Theresearch works described in this special issue are geared forthe discovery of user behavior and mobility in real sensordata.

Acknowledgments

This special issue is partially supported in part by theNationalNatural Science Foundation of China under Grants 61100045and 61165013, by the Specialized Research Fund for theDoctoral ProgramofHigher Education of China underGrant20110184120008, by the Youth Foundation for Humanitiesand Social Sciences of Ministry of Education of China underGrant 14YJCZH046, and by the Fundamental Research Fundsfor the Central Universities under Grant 2682013BR023.

Shaojie QiaoHuidong (Warren) Jin

Yunjun GaoLu-An Tang

Huanlai Xing

References

[1] S. Qiao, D. Shen, X. Wang, N. Han, and W. Zhu, “A self-adaptive parameter selection trajectory prediction approachvia hidden Markov models,” IEEE Transactions on IntelligentTransportation Systems, vol. 16, no. 1, pp. 284–296, 2015.

[2] T.Hunter, P. Abbeel, andA.M. Bayen, “Thepath inference filter:model-based low-latency map matching of probe vehicle data,”IEEE Transactions on Intelligent Transportation Systems, vol. 15,no. 2, pp. 507–529, 2014.

[3] Y. Zheng, “Trajectory data mining: an overview,”ACMTransac-tions on Intelligent Systems and Technology, vol. 6, no. 3, article1, 2015.

[4] Y. Zheng and X. Zhou, Computing with Spatial Trajectories,Springer, New York, NY, USA, 2011.

[5] S. Qiao, C. Tang, H. Jin et al., “PutMode: prediction of uncertaintrajectories in moving objects databases,” Applied Intelligence,vol. 33, no. 3, pp. 370–386, 2010.

[6] C. Song, Z. Qu, N. Blumm, and A.-L. Barabsi, “Limits of pre-dictability in human mobility,” Science, vol. 327, no. 5968, pp.1018–1021, 2010.

International Journal of Distributed Sensor Networks 3

[7] S. Qiao, T. Li, H. Li, J. Peng, and H. Chen, “A new block-modeling based hierarchical clustering algorithm for web socialnetworks,” Engineering Applications of Artificial Intelligence, vol.25, no. 3, pp. 640–647, 2012.

[8] A. Campbell and T. Choudhury, “From smart to cognitivephones,” IEEE Pervasive Computing, vol. 11, no. 3, pp. 7–11, 2012.

[9] D. Centola, “The spread of behavior in an online social networkexperiment,” Science, vol. 329, no. 5996, pp. 1194–1197, 2010.

International Journal of

AerospaceEngineeringHindawi Publishing Corporationhttp://www.hindawi.com Volume 2014

RoboticsJournal of

Hindawi Publishing Corporationhttp://www.hindawi.com Volume 2014


Active and Passive Electronic Components

Control Scienceand Engineering

Journal of



RotatingMachinery


Hindawi Publishing Corporation http://www.hindawi.com

Journal ofEngineeringVolume 2014

Submit your manuscripts athttp://www.hindawi.com

VLSI Design



Shock and Vibration


Civil EngineeringAdvances in

Acoustics and VibrationAdvances in



Electrical and Computer Engineering

Journal of

Advances inOptoElectronics

Hindawi Publishing Corporation http://www.hindawi.com

Volume 2014

The Scientific World JournalHindawi Publishing Corporation http://www.hindawi.com Volume 2014

SensorsJournal of


Modelling & Simulation in EngineeringHindawi Publishing Corporation http://www.hindawi.com Volume 2014


Chemical EngineeringInternational Journal of Antennas and

Propagation




Navigation and Observation



DistributedSensor Networks


Editorial Trajectory Data Mining in Distributed Sensor...

Documents

Transcript of Editorial Trajectory Data Mining in Distributed Sensor...