Data Analytics in Smart City

This paper discusses the impact of big data analytics in smart cities and proposes an integrated framework to optimize computing resources for better performance. The framework uses a big data deep reinforcement learning approach with Q network and virtual servers to manage smart city applications effectively. The paper also highlights the privacy issues associated with big data analytics and the importance of data redundancy and latency.

DATA ANALYTICS IN SMART CITY
Data Analytics in smart city
Name of the Student
Name of the University
Author Note:

1
DATA ANALYTICS IN SMART CITY
Table of Contents
Article Review...........................................................................................................................2
Introduction................................................................................................................................2
Critical analysis for quantitative studies....................................................................................2
Introduction to the problem....................................................................................................2
Research Procedure....................................................................................................................3
Discussion..................................................................................................................................3
Method Specific Criteria for Qualitative studies.......................................................................5
Conclusion..................................................................................................................................5
Reference....................................................................................................................................7

2
DATA ANALYTICS IN SMART CITY
Article Review
He, Ying, F. Richard Yu, Nan Zhao, Victor CM Leung, and Hongxi Yin. "Software-
defined networks with mobile edge computing and caching for smart cities: A big data
deep reinforcement learning approach." IEEE Communications Magazine 55, no. 12
(2017): 31-37.
Introduction
This resource has been chosen from the IEEE communications magazine published in
the year 2017. The IEEE magazines are very much reliable in nature. The prime
determination of this document is to focus on the consequences of the big data analytics in
smart cities1. The software defined networks with mobile edge computing and caching are
clearly presented in this paper. This resource provides in-depth knowledge about the current
and past problems of data analytics used in the smart cities. The information present in the
resource are mostly from the primary sources and is highly logical and unbiased.
Critical analysis for quantitative studies
Introduction to the problem
The desired outcomes of the enabling technologies are not obtained even after several
years of incorporation in the smart cities. This resource will propose an integrated framework
which will be helpful to optimize the computing resources so that better performances can be
achieved in the smart cities. This paper will be helpful to answer the following questions.
o How to improve the performance of big data analytics in smart cities?
o What is the effectiveness of the proposed framework?
1 He, Ying, F. Richard Yu, Nan Zhao, Victor CM Leung, and Hongxi Yin. "Software-defined networks with
mobile edge computing and caching for smart cities: A big data deep reinforcement learning approach." IEEE
Communications Magazine 55, no. 12 (2017): 31-37.

3
DATA ANALYTICS IN SMART CITY
The author of this resource wanted to optimize the performance of the big data
analytics used in smart cities, as new threats are constantly entering the market2. According to
the authors of this resource, there was a need for evaluating the approaches which are taken
while accessing big data in smart cities.
Research Procedure
The chosen research methodology procedure for this assignment is the qualitative
research analysis. Primary type of data collection technique is applied in this paper along
with the secondary type. The primary data is collected from a survey of 10 residents of smart
cities and the secondary data collection is done from peer reviewed journals. The issues
related to the big data analytics in smart cities are focused with the help of the data collected.
The residents of the smart cities were given unbiased information about this topic. Strict
guidelines were given to them to provide an integrated solution to the problems related to the
big data in smart cities. The chosen group of 10 residents is large enough to have a variety of
opinions about the selected topic.
Discussion
The data collected is helpful in understanding the issues related to the big data
analytics in smart cities. According to Mohammadi and Ala Al-Fuqaha3, the privacy issues
are a huge source of concern in the smart cities. These issues can have decreased the
performance of the high end advanced systems. The author of this resource helpful in
understanding the anonymity of the big data analytics in the smart cities. There are many
2 He, Jianhua, Jian Wei, Kai Chen, Zuoyin Tang, Yi Zhou, and Yan Zhang. "Multitier fog computing with large-
scale iot data analytics for smart cities." IEEE Internet of Things Journal 5, no. 2 (2018): 677-686.
3 Mohammadi, Mehdi, and Ala Al-Fuqaha. "Enabling cognitive smart cities using big data and machine
learning: Approaches and challenges." IEEE Communications Magazine 56, no. 2 (2018): 94-101.

4
DATA ANALYTICS IN SMART CITY
types of e-discovery problems associated with the big data which is mentioned in this paper4.
The data security is one of the prime aspect of big data in the smarter cities.
The author of this resource stated that a framework can help in optimize the issues
related to the big data. The smart city applications can be managed effectively with the
efficient management of the resources. Big data reinforcement learning approach with the Q
network. The Q valuation action function are used in artificially intelligent systems and the
data analytics in smart cities and its positive impact are also noticed5. The proposed schemes
are made to interfere in different privacy issues associated with big data analytics. The
problems related to the big data analytics are solved to a huge extent with the help of this
proposed framework.
The software defined network and the virtual network are secured with the help of this
framework. The flexibility and centralized principles which are followed in this framework
can be used in the mobile edge computing. Each of the virtual networks used in the big data
are used as virtual servers such as the RSU’s and MEC servers. Each severs functions on the
basis of the QoS requirement. The virtual resources are allocated to mobile network virtual
operators. Latency and redundancy of data is significant decreased after the application of
this framework. Networking capabilities of an organization can be improved significantly
with the help of the proposed framework6. The author of this resource also stated about the
advantage of this framework considering the computing capability and the caching capability.
4 Hashem, Ibrahim Abaker Targio, Victor Chang, Nor Badrul Anuar, Kayode Adewole, Ibrar Yaqoob,
Abdullah Gani, Ejaz Ahmed, and Haruna Chiroma. "The role of big data in smart city." International
Journal of Information Management 36, no. 5 (2016): 748-758.
5 Strohbach, Martin, Holger Ziekow, Vangelis Gazis, and Navot Akiva. "Towards a big data analytics
framework for IoT and smart city applications." In Modeling and processing for next-generation big-data
technologies, pp. 257-282. Springer, Cham, 2015.
6 Mahdavinejad, Mohammad Saeid, Mohammadreza Rezvan, Mohammadamin Barekatain, Peyman Adibi,
Payam Barnaghi, and Amit P. Sheth. "Machine learning for Internet of Things data analysis: A survey." Digital
Communications and Networks (2017)

5
DATA ANALYTICS IN SMART CITY
Method Specific Criteria for Qualitative studies
The validity of the primary data and the secondary data is analyzed with the help of
the mean, median and standard deviation. The quantitative data are placed in a graphical
representation with the help of the quantitative data analysis technique7. The other kind of
data analysis technique used for evaluation the data from the research methodology is the
orthogonal coding. This research will help the readers of this document to develop a skill
about how to deal with the issues of the big data analytics8. The participant who had their role
in evaluating this topic was very much co-operative throughout the data collection process.
The method of analyzing the response was stated to the participants and any violations of the
policies may result in the strict legal actions against them9. Younger generations of the
society were mainly selected for this assignment.
Conclusion
This paper is written in a precise manner, and it helps in concluding about the impact
of the negative effects of big data analytics in the smart cities. The paper focuses on all the
privacy issues associated with the application of big data. How these issues will impact the
effectiveness of the cities are also stated in this paper. The paper helps in realizing the
importance of data redundancy and latency. From the above paper, it can be concluded that
the proposed framework can be effectively used in the big data analytics in the smart cities as
we are all aware of the positive consequences of using this framework across many new
advanced systems.
7 Mohammadi, Mehdi, and Ala Al-Fuqaha. "Enabling cognitive smart cities using big data and machine
learning: Approaches and challenges." IEEE Communications Magazine 56, no. 2 (2018): 94-101.
8 Habibzadeh, Hadi, Andrew Boggio-Dandry, Zhou Qin, Tolga Soyata, Burak Kantarci, and Hussein T.
Mouftah. "Soft Sensing in Smart Cities: Handling 3Vs Using Recommender Systems, Machine Intelligence, and
Data Analytics." IEEE Communications Magazine 56, no. 2 (2018): 78-86.
9 Thomas, Robert W., and José M. Vidal. "Toward detecting accidents with already available passive traffic
information." In Computing and Communication Workshop and Conference (CCWC), 2017 IEEE 7th Annual,
pp. 1-4. IEEE, 2017

6
DATA ANALYTICS IN SMART CITY

7
DATA ANALYTICS IN SMART CITY
Reference
Habibzadeh, Hadi, Andrew Boggio-Dandry, Zhou Qin, Tolga Soyata, Burak Kantarci, and
Hussein T. Mouftah. "Soft Sensing in Smart Cities: Handling 3Vs Using Recommender
Systems, Machine Intelligence, and Data Analytics." IEEE Communications Magazine 56,
no. 2 (2018): 78-86.
Hashem, Ibrahim Abaker Targio, Victor Chang, Nor Badrul Anuar, Kayode Adewole, Ibrar
Yaqoob, Abdullah Gani, Ejaz Ahmed, and Haruna Chiroma. "The role of big data in smart
city." International Journal of Information Management 36, no. 5 (2016): 748-758.
He, Jianhua, Jian Wei, Kai Chen, Zuoyin Tang, Yi Zhou, and Yan Zhang. "Multitier fog
computing with large-scale iot data analytics for smart cities." IEEE Internet of Things
Journal 5, no. 2 (2018): 677-686.
He, Ying, F. Richard Yu, Nan Zhao, Victor CM Leung, and Hongxi Yin. "Software-defined
networks with mobile edge computing and caching for smart cities: A big data deep
reinforcement learning approach." IEEE Communications Magazine 55, no. 12 (2017): 31-
37.
Mahdavinejad, Mohammad Saeid, Mohammadreza Rezvan, Mohammadamin Barekatain,
Peyman Adibi, Payam Barnaghi, and Amit P. Sheth. "Machine learning for Internet of Things
data analysis: A survey." Digital Communications and Networks (2017).
Mohammadi, Mehdi, and Ala Al-Fuqaha. "Enabling cognitive smart cities using big data and
machine learning: Approaches and challenges." IEEE Communications Magazine 56, no. 2
(2018): 94-101.

8
DATA ANALYTICS IN SMART CITY
Strohbach, Martin, Holger Ziekow, Vangelis Gazis, and Navot Akiva. "Towards a big data
analytics framework for IoT and smart city applications." In Modeling and processing for
next-generation big-data technologies, pp. 257-282. Springer, Cham, 2015.
Thomas, Robert W., and José M. Vidal. "Toward detecting accidents with already available
passive traffic information." In Computing and Communication Workshop and Conference
(CCWC), 2017 IEEE 7th Annual, pp. 1-4. IEEE, 2017.