Towards Disaster Resilient Smart Cities: Can Internet of Things and Big Data Analytics Be the Game Changers?

被引:99
作者
Shah, Syed Attique [1 ,7 ]
Seker, Dursun Zafer [2 ]
Rathore, M. Mazhar [3 ]
Hameed, Sufian [4 ]
Ben Yahia, Sadok [5 ]
Draheim, Dirk [6 ]
机构
[1] Istanbul Tech Univ, Inst Informat, TR-34469 Istanbul, Turkey
[2] Istanbul Tech Univ, Civil Engn Fac, Dept Geomat Engn, TR-34469 Istanbul, Turkey
[3] Hamad Bin Khalifa Univ, Coll Sci & Engn, Div Informat & Comp Technol, Doha, Qatar
[4] NUCES, IT Secur Labs, Karachi 75160, Pakistan
[5] Tallinn Univ Technol, Dept Software Sci, EE-12618 Tallinn, Estonia
[6] Tallinn Univ Technol, Informat Syst Grp, EE-12618 Tallinn, Estonia
[7] Balochistan Univ Informat Technol Engn & Manageme, Dept Informat Technol, Quetta 87300, Pakistan
关键词
Big data analytics; Internet of Things; smart city; disaster management; Hadoop; spark; smart data analytics; geo-social media analytics; disaster resilient smart city; SOCIAL MEDIA; INFORMATION; MANAGEMENT; IOT; SYSTEM; EMERGENCIES; EXPERIENCE; FRAMEWORK;
D O I
10.1109/ACCESS.2019.2928233
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Disasters (natural or man-made) can be lethal to human life, the environment, and infrastructure. The recent advancements in the Internet of Things (IoT) and the evolution in big data analytics (BDA) technologies have provided an open opportunity to develop highly needed disaster resilient smart city environments. In this paper, we propose and discuss the novel reference architecture and philosophy of a disaster resilient smart city (DRSC) through the integration of the IoT and BDA technologies. The proposed architecture offers a generic solution for disaster management activities in smart city incentives. A combination of the Hadoop Ecosystem and Spark are reviewed to develop an efficient DRSC environment that supports both real-time and offline analysis. The implementation model of the environment consists of data harvesting, data aggregation, data pre-processing, and big data analytics and service platform. A variety of datasets (i.e., smart buildings, city pollution, traffic simulator, and twitter) are utilized for the validation and evaluation of the system to detect and generate alerts for a fire in a building, pollution level in the city, emergency evacuation path, and the collection of information about natural disasters (i.e., earthquakes and tsunamis). The evaluation of the system efficiency is measured in terms of processing time and throughput that demonstrates the performance superiority of the proposed architecture. Moreover, the key challenges faced are identified and briefly discussed.
引用
收藏
页码:91885 / 91903
页数:19
相关论文
共 64 条
[1]  
AHA Center, 2018, 5 AHA CTR
[2]  
Akter S., 2017, Annals of Operations Research, P1, DOI DOI 10.1007/S10479-017-2584-2
[3]   Towards multi-agency sensor information integration for disaster management [J].
Alamdar, Farzad ;
Kalantari, Mohsen ;
Rajabifard, Abbas .
COMPUTERS ENVIRONMENT AND URBAN SYSTEMS, 2016, 56 :68-85
[4]  
[Anonymous], 2014, W3C WORKSHOP WEB THI
[5]  
[Anonymous], 2016, The Journal of Machine Learning Research, DOI DOI 10.1145/2882903.2912565
[6]  
[Anonymous], 2012, 223132012 ISO
[7]  
[Anonymous], 2019, WORLD URB PROSP 2018
[8]  
[Anonymous], 2018, SIGMA
[9]  
Apache Software Foundation, AP FLUM
[10]   Spark SQL: Relational Data Processing in Spark [J].
Armbrust, Michael ;
Xin, Reynold S. ;
Lian, Cheng ;
Huai, Yin ;
Liu, Davies ;
Bradley, Joseph K. ;
Meng, Xiangrui ;
Kaftan, Tomer ;
Franklint, Michael J. ;
Ghodsi, Ali ;
Zaharia, Matei .
SIGMOD'15: PROCEEDINGS OF THE 2015 ACM SIGMOD INTERNATIONAL CONFERENCE ON MANAGEMENT OF DATA, 2015, :1383-1394