Data Analytics in Smart Cities

3669 words (15 pages) Essay in Information Technology

23/09/19 Information Technology Reference this

Disclaimer: This work has been submitted by a student. This is not an example of the work produced by our Essay Writing Service. You can view samples of our professional work here.

Any opinions, findings, conclusions or recommendations expressed in this material are those of the authors and do not necessarily reflect the views of UK Essays.

Data Analytics in Smart Cities

                                                                    Abstract

The paper tells us about the Data Analytics being used in a specific industry that is smart cities. Smart Cities is an integration of information and communication technology and also the several physical devices that are connected to the network. Now with this rapidly growing population in the world, since most are moving from pre-urban to urban forms. There has been a great increase in the request for embedded devices, such as sensors, actuators, and smartphones that will lead to potential business for the new era of the Internet of Things (IoT).

Data Analytics pay a very important role in integrating and collecting this data. In this research paper, we focus on how distributed smart sensing systems and devices monitor the vast urban infrastructure, and why for this to react on time we need automated control and collected information for intelligent decision making. We discuss all of it in the form of how this “smart city” industry has adopted data analytics to improvise and develop. and how the adaption of data analytics impacted different activities within a city like controlling vehicle traffic, Managing Parking lot with ease, Smart homes referring to the proper management of water and energy consumption and its need. Reducing the risk of natural disasters such as Floods. We also focussed on major challenges faced by Data Analytics in its working with smart city and tried to put light on solutions as future research suggested by researchers introducing automated systems methods, developing mobile computing frameworks, data cleaning and data collection along with visualization. All these solutions have been suggested for issues such as Privacy of Data, Security and Variety. At last, we focus on the conclusion to improvise and maintain the current trend of development and work on its future research.

 I                                                           Introduction

The Proportion of this globe is increasing and with this increase what’s increasing is the movement of this population from one area to another, especially the movement of pre-urban to urban forms. With this comes the motivation of more developed infrastructure, motivated methodologies to maintain them and greater opportunities together attributed as what we call as a smart city. Smart city initiatives are mainly dependent on the collection and management of the right kind of data, analysis of pattern and optimization of system functioning. The additional fundamental elements here are the large volume of data and the process of examining it that is Data Analytics.

Now with Increasing population, their needs and giant economic infrastructure for same calls for handling every bit of it very wisely, effectively and efficiently which requires a probable smarter way for the smart city. We observe that the government and the companies are leveraging billions of dollars in public and private funds for smart cities. So, in the First part we are focussing on What are Smart Cities and why do we need data analytics for it. In the second part, we have focussed on the adoption and impact of data analytics. The things in focus that are automated Data analytics frameworks for various smart city attributes like Vehicle Traffic control, Flood analysis, Smart homes and their water and energy consumptions and Parking lot Management in cities by Data Analytics. At last, we will see some major challenges faced by Data Analytics in Smart Cities including Privacy Issues, Security Issues and Variety Issues.We will also focus on researchers solutions for these issues that could be implemented in the present and future research to diminish such issues .the interpretation of the huge amount of information is provided by emerging testing and the monitoring systems.

 Smart City and Its need for Data Analytics

Smart Cities as the name suggests is basically the city that is developed so smartly to handle its population and resources in a well-organised form. So, a smart city is designed as an urban area that uses different types of electronic data collection sensors to supply information which is used to manage assets and resources efficiently. Now coming to the data, the question that arises straight to our mind is from where this data is collected from and how does it collaboratively help to develop a strong foundation for the smart city. Well, an answer for same will be this data comes from citizens, devices, and assets that are processed and analysed to monitor and manage traffic and transportation systems, power plants, water supply networks, waste management, law enforcement, information systems, schools, libraries, hospitals, and other community services. The Smart City is basically an integration of information and communication technology and also the several physical devices that are connected to the network. So, we can say that a smart city technology allows the city officials to interact directly with the great city infrastructure and as well as the community to monitor the city activities and its evolution.

Data Analytics pay a most important key role in tackling this challenge. Data analytics applications involve collecting, integrating and preparing time and space dependent data produced by sensors, engineered systems and physical assets followed by developing and testing the analytical models for verifying the accuracy of results.And with this being in the picture there are several paradigms that are associated with it being pattern recognition, machine learning and statistics, Intelligent Databases and knowledge acquisition, visualizing data, performance computing and much more. Thus, this embraces the very new concept of Big Data Analytics for the interpretation of the smart cities and its massive amount of data.

Adoption of Data Analytics in Smart Cities and Its Impact

Data Analytics in smart cities is the need of an hour. As the rapid growth of population density in urban cities demands that the services and an infrastructure be provided to meet the needs of city inhabitants. The Adoption of Data Analytics in Smart cities has been great for revitalizing the methods and techniques related to city development and public welfare. With this, there has been a great increase in the request for embedded devices, such as sensors, actuators, and smartphones that will lead to potential business for the new era of the Internet of Things (IoT).In this paper now let’s see how the Data Analytics has been adopted by the smart city and at the same time its impacts that have made a big profit and easy wellbeing of its population as a whole leading to urban planning.

Smart cities initiatives are trying their best to explore advancements in the Internet of Things (IoT) domain to basically tackle common urban challenges such as reducing the energy consumption, reducing traffic congestion and also environmental pollution that is basically caused due to excessive pollutants within the city. So, some of the adoptions by smart cities in data analytics that has already been adopted and some that are still in process to improvise the system are as follows is explained in detail: –

•    Vehicle Traffic Analysis

In the detection of the analysis for traffic we see, the smart city analyses vehicular traffic data in real time and at the same time, it also facilitates in finding how much time it will take to reach a destination by taking alternative methods with the current intensity of traffic on that particular route.  The updated information provided by it helps in making the public reach comfortably to the appropriate destination. The government traffic authorities are at ease in controlling traffic and create an optimised plan in unwanted and uncertain circumstances like blocking of roads due to several reasons like accidents, strikes etc. The advantages of this method have impacted so vastly as it not only helped the government as well as citizens to save fuel but at the same time reduce pollution that is created due to excessive pollution. Thus, the diversion of traffic takes place to obtain equal usage of all alternative roads and ways. 

•    Parking Data Analysis

By analysing the current usage of parking lots, citizens can select the closest parking lot to their location. Let’s take an example here to understand data analysis used in this case Fig. 1 shows the number of free spaces in various parking garages in Aarhus, and Fig. 2 shows the current use of parking garages. As per this study, the users are updated about free parking in real time. It helps the public to save fuel without manually searching for the free parking space. It creates a great profit at the same time. Because what we see is that in general the people usually look for less congested areas to visit for shopping or recreation to be at ease for getting a free parking space. Thus, helping the vendors to be able to sell much more items in such areas of parking the parking analysis also provides direction to governmental authorities in urban planning to build more parking areas near places with a higher volume of consumers. The Figure below shows that the Brun’s has ample parking with a capacity of 931 cars, but still resulting in parking being unavailable. Thus, conveying the need for more parking lots at that location.

 

Figure1: . Free spaces at various parking lots at different times

Figure 2: Usage of various parking lots at different times.

•    Smart home data analysis

Here we explain the use of Data Analytics in creating a smart home and its consumption of water and electricity. In every city, we come across different homes located at different streets with different consumption of electricity and water usage. Now taking this into consideration, a smart technique of data analytics method has been developed to find out the current usage of each home’s consumption. So, this indeed helps the smart cities to manage their water resources with respect to their current data usage. And thus, next year’s water usage can also be well predicted based on it. and at the same time, the flow of the water for different areas with the actual need in that area can also be controlled.

This analysis can also be used for water resources in the city. That is for example if there are more reservoirs, the required amount of water can be stored by finding the overall water consumption parameters in a smart city. Similarly, if there is a scarcity of reservoirs, then the water needs can be predicted beforehand, and the consumption can be planned accordingly. Thus, by this type of water management of water, can similarly be performed to manage energy, such as electricity and gas

•    Flood data analysis

Flood, as we all know, happens due to rainwater m snow melting or storms etc, so in smart cities, different types of floods are examined, and as a result, the fact that is observed is rainwater creates higher chances of flood and followed by same is snow:-

Using data analytics to measure flood threat and its damage analysis we have: –

•    M representing the magnitude of the flood, which is calculated as the log (duration × severity × area affected).

For example: Please refer to the table below that Table 2 for this. If M is greater than 4, it means the flood is of a higher intensity. Approximately 50,250 floods at a higher intensity have occurred at various locations in the world. In a similar sense, if the value of M is greater than 6, the intensity of the flood is dangerous. A total of 13,751 floods have been recorded at this intensity. The flood ratio in the case of both of these magnitudes is greater in the event of rain. We can see that 35% of the floods have occurred due to rain, followed by snow at 1.5%. If in an area rain crosses a predefined threshold, a warning signal or alert can be broadcasted to the public and the same goes for snow. For which flood intensity could be predicted by putting sensors on the hills.

Table 2: Table showing statistics for different kind of flood causes

Challenges Faced by Data Analytics in Smart Cities

 

•    Privacy Issues the suggestions of researchers for future work of same.

With increasing data all around the world the thing that is of concern is the data privacy and protection. We see that the data privacy and protection issues are increasing with each day. More and more data are being collected, harvested and generated. So, if any data that is improperly masked can cause harm to its privacy and get revealed to its users. Thus, the Big data comes into the picture by being ethically owned and used by its producers. Individual access to the data in today’s scenario is made impracticable, data are likely to be de-identified to such an extent that is sufficient to lower down its privacy concerns. Some of the major things of concern are online communication via several channels that particularly needed to be done by hardware and software channels. Suggestions by researchers to deal with such privacy issues is Legal provisioning that is on using the data, use of data for safely ensuring safe travel of data over the networks and development of a context-aware framework for managing the lack of predictability of wireless connectivity and data privacy.

•    Security Breach Issues, and the suggestions of researchers for future work of same

Security of data is something of prime importance whether it be the security of data processing and sharing, some intellectual property, the security of users, the personal privacy, commercial secrets and financial information are some of the concerns in smart cities. The vast diversified data by sensor networks and then the fraudulent users and financial losses due to malicious data and legitimate services are other potential issues in the smart cities. According to Kaisler et al. (2013), the unregulated accumulation of data by numerous social media organizations is the biggest threat to security, as large sets of data tempt cyber attackers. Therefore, the security of data needs to be implemented at the technological, government and business policy and public levels through strict legal terms and conditions (Kaisler et al. , 2013). For addressing such security breach, researchers have suggested methods like developing a mobile-Cloud framework to solve the data over-collection problem, which can be set as a benchmark for various web applications. Several Data pre-processing techniques such as data cleaning, data integration and data transformation and reduction has been used to reduce data noise and inconsistencies while securing data.

•    Variety Issues and the Solution for same

Variety is the result of the growth of virtually unlimited heterogeneous data. The data here can be in various forms like structured, unstructured, text, virtual and the data being collected from various sources like the output from the RFID tags, Barcode logs, Machine logs, documents, text messages, videos, still images, audios, graphs, 

The heterogeneity problem is actually created due to incompatibility in data, recognition problem arising due to the merger of the data for various sources. The Solution suggested for these kinds of issues by the researchers are possible techniques such as automatic recognition of data to form patterns and remove outliers (Cheng et al. , 2015), use of data analytics to convert heterogeneous multi-level geographical data into useful information to derive the knowledge (Li et al. , 2015b) and construction of data models for deeply looking into the data to form meaningful patterns. One of the nicest example that could be considered for this is Noordhuis applied PageRank Algorithm on Twitter user base to obtain user rankings. Computations in a large amount of data were conducted in a two-phase process. So, we observed in the first phase, i.e. crawling phase, the data was retrieved from Twitter, and in the second phase, i.e. processing phase, the PageRank algorithm was then applied for the computation of the data. Using this algorithm, Noordhuis reduced the variety of data arriving from 1.8 billion nodes and analysed the user rankings from heterogeneous data within a few seconds (Hashem et al. , 2015).

Conclusion and Future Research

After analysing and doing such in-depth research study on data analytics in smart cities. The main factors I have analysed during this research study are that Smart cities and urban planning can have a major impact on national development. The adaption of these specific data analytics techniques to develop and maintain the city infrastructure and its resources and human population is beyond any major accomplishments to develop a city real smart. At the same time, I have also realised that these efforts can increase the decision-making power of society by allowing them to make intelligent and also effective decisions at appropriate times. The proposed system within this paper has been smart cities and urban planning by using an IoT-generated Big Data analysis that has been something majorly focused. Furthermore, we have explained the challenges faced by the Data Analytics methodology within smart cities, in short discussing the adaption and impact of data analytics on smart cities. This calls for action for providing enhanced services to citizens while cities are growing due to urbanisation, and while resources are limited demands for a more intelligent use of the existing resources.

Future work will focus on the evaluation of the proposed methodology for (near-)real-time city data analytics in different domains. Much of the future work have been discussed above in form of suggestions and solution to issues faced and other include how can government authorities, researchers and the citizens can collaboratively try for other domains within the smart city that are yet to be developed and improvised by using data analytics methodology in future work and research.

                                                                   References

  • Rathore, M. M., Ahmad, A., Paul, A., & Rho, S. (2016). Urban planning and building smart cities based on the internet of things using big data analytics. Computer Networks101, 63-80
  • Chase, R. L. (1997). The knowledge-based organization: an international survey. Journal of Knowledge Management1(1), 38-49.
  • Alavi, A., & Buttlar, W. G. (Eds.). (2018). Data Analytics for Smart Cities. CRC Press.
  • Chauhan, S., Agarwal, N., & Kar, A. K. (2016). Addressing big data challenges in smart cities: A systematic literature review. Info : The Journal of Policy, Regulation and Strategy for Telecommunications, Information and Media, 18(4), 73-90
  • Al Nuaimi, E., Al Neyadi, H., Mohamed, N., & Al-Jaroodi, J. (2015). Applications of big data to smart cities. Journal of Internet Services and Applications6(1), 25.
  • Bélissent, J. (2010). Getting clever about smart cities: New opportunities require new business models. Cambridge, Massachusetts, USA.)
  • Hashem, I. A. T., Chang, V., Anuar, N. B., Adewole, K., Yaqoob, I., Gani, A., … & Chiroma, H. (2016). The role of big data in smart city. International Journal of Information Management36(5), 748-758
  • Dey, S., Chakraborty, A., Naskar, S., & Misra, P. (2012, October). Smart city surveillance: Leveraging benefits of cloud data stores. In Local Computer Networks Workshops (LCN Workshops), 2012 IEEE 37th Conference on (pp. 868-876). IEEE
  • Hashem, I.A.T., Yaqoob, I., Anuar, N.B., Mokhtar, S., Gani, A. and Khan, S.U. ( 2015 ), ” The rise of ‘big data’ on cloud computing: review and open research issues “, Information Systems, Vol. 47, pp. 98 – 115
  • Kaisler, S., Armour, F., Espinosa, J.A. and Money, W. ( 2013 ), ” Big data: issues and challenges moving forward “, Proceedings of the 46th Hawaii International Conference on System Sciences (HICSS), Wailea, Maui, HI, pp. 995 – 1004 .
  • Li, J., Tao, F., Cheng, Y. and Zhao, L. (2015c), “Big data in product lifecycle management”, The International Journal of Advanced Manufacturing Technology, Vol. 81 Nos 1/4, pp. 667-684.
  • Cheng, B., Longo, S., Cirillo, F., Bauer, M. and Kovacs, E. (2015), “Building a big data platform for smart cities: experience and lessons from Santander”, Proceedings of the International Congress on Big Data (BigData Congress), New York, NY , pp. 592-599

Cite This Work

To export a reference to this article please select a referencing stye below:

Reference Copied to Clipboard.
Reference Copied to Clipboard.
Reference Copied to Clipboard.
Reference Copied to Clipboard.
Reference Copied to Clipboard.
Reference Copied to Clipboard.
Reference Copied to Clipboard.

Related Services

View all

DMCA / Removal Request

If you are the original writer of this essay and no longer wish to have the essay published on the UK Essays website then please: