search
Only on Eduzaurus

Artificial Intelligence And Machine Learning In Smart City Development

Download essay Need help with essay?
Need help with writing assignment?
75
writers online
to help you with essay
Download PDF

The idea of providing better living standards by incorporating technology into day-to-day activities of people is the sole purpose of the emergence of smart cites. This paper highlights some major technologies and solutions to various problems faced by the citizens due to lack of digitization. It emphasises on the application of Internet of Things(IoT), neural networks, machine learning, pattern recognition, Big Data Analytics and Cloud Infrastructures in developing a fully functional smart city.

Keywords— Artificial intelligence, machine learning, cloud, big data analytics, pattern recognition, neural networks, sensors, smart city

Essay due? We'll write it for you!

Any subject

Min. 3-hour delivery

Pay if satisfied

Get your price

Introduction

The idea behind smart city is profoundly based on optimization of costs, better living standards, preservation of resources, integration of technology and faster transactions in all fields. It incorporates all aspects of technology in transforming a complicated infrastructure into a digital, sophisticated and a simpler lifestyle. Here, the term ‘technology’ refers to the most popular and emerging fields like AI and IoT. They are the future and so are smart cities. Both these fields are spread across a huge radius and it is almost impossible to reach their ends. While AI is concerned with unifying technology with the simplest of things, IoT forms the foundation for connecting all these related technologies to create a grid. Many people have different perceptions with respect to the term ‘smart city’. This is well explained in [12]. It includes smart economy perception, smart governance, smart living, smart mobility, smart environment, knowledge sharing, planning and implementation, more efficient, easier and increased qualifications of jobs [12]. [image: Image result for deep learning smart city]Figure 1: Smart city components Smart city is the next big thing and the government has taken various initiatives to promote the need for a technical infrastructure in a city. One of the prominent initiatives is the ‘Smart Cities Mission’ by the Ministry of Housing and Urban Affairs [1]. This is a platform for the states to nominate some of their cities for transforming them into smart cities. This is conducted as a competition in which the cities will be selected and ranked based on their merit.

The different stages in the selection of Smart Cities is shown in Figure 2. Merit refers to the number of projects undertaken in that city, total cost of projects, total area-based development cost, total pan city solution and total urban population impacted. Due to such an initiative, many cities today provide core infrastructure, a decent quality of life to its citizens, a clean and sustainable environment, inclusive development, the idea to look at compact areas and create a replicable model which will act like a light house to other aspiring cities. It encourages the use of ‘smart’ solutions for complicated problems and to derive all the smart city components as shown in figure 1. The aim of the Smart Cities Mission is to drive economic growth and raise the quality of living by harnessing technology. Area based development has a vision to retrofit and redevelop areas including slums, into better planned ones thereby improving the lifestyle of the entire city. This comprehensive development will aid in enhancing liveability and incomes for all, create employment opportunities especially to the poor and the disadvantaged leading to inclusive cities. Figure 2: Smart City Project Stages

SMART CITY AND ARTIFICIAL INTELLIGENCE

Artificial intelligence(AI) is the science of simulating intelligence in machines and program them to mimic human actions. Learning, reasoning and perception are the major goals of AI. This concept is already used in medical diagnosis, robot control, electronic training, finance, remote sensing, optical character recognition, computer vision, virtual reality, image processing, game theory, semantic web, and more. It can be made comprehensive in the development of Smart cities. AI learns how people use the city: AI pattern recognition technology is used significantly to manage huge sources of raw data, such as ticket sales on mass transit, police reports, sensors on the roads and weather stations [2]. About 1 billion cameras are expected to be deployed in government property and infrastructure by 2020 to increase the source of this raw data. While only a fraction of cameras can be actively monitored by humans, this is where deep learning comes in. It can count vehicles and pedestrians, read licence plates and recognize faces, track the speed of vehicles to establish patterns. It can even collect and process the data from satellites to count the number of vehicles in a parking lot or track the amount of traffic in any given area at any given time. VIMOC Technologies’ LPR system can check if the vehicles parked in a parking lot have the right permits [3]. AI can be used for electricity supply and management, where a system can be built such the it can intelligently and effectively communicate to the human controllers in case of emergency [8]. AI optimizing infrastructure for cities: People face a lot of inconvenience when it comes to traffic and finding a place to park their vehicle. It is analysed that drivers spend about 107 hours per year in search of a parking lot. This problem can be tackled by collecting and sharing real time information among individuals, companies and government agencies. The drivers can provide real time data about traffic and accidents to help individuals save time and optimize their routes. Passengers feel more convenient to travel by buses which are trackable, than those for which they have to wait for a long time. They can thereby schedule their activities accordingly and save time. This is called Connected Public Transit Technology. This technology allows general public to communicate with buses and trains, thereby letting individuals know when they are arriving and inform them before hand in case of a delay. Waste management is an important sector in the development of a smart city.

A Self-thinking robot called SITA Finland, developed by ZEN Robotics is an intelligent system which uses AI for taking decisions on its own and solve problems related to construction and demolition debris [8]. In large parking lots, the amount of available parking is displayed on an LED and this information is shared to app developers through which the citizens can know where the parking is available. In a long term, this can be used to alter the planning and pricing decisions of the city. IOT can also be used in implementing smart parking system. This approach consists of two parts – hardware part for sending condition of parking slots to the internet and a software part for determining the nearest free parking space. The complete flowchart for this system is shown in figure 3 [10]. Adaptive signal control technology allows traffic lights to change based on real time data collected from various cameras and other companies which update their apps with the latest information about the traffic conditions at various locations across the city. This can improve the travel time by more than 10 percent in major cities and by 50 percent in areas with outdated signal timings. This technology is being deployed in many countries for a simple reason that it can reduce traffic congestion costs due to wasted fuel and productivity. The benefits of this technology have been deployed, measured and proven effective in cities like San Diego, San Antonio, Bellevue and in Los Angeles. [image: ]Figure 3: flow chart of smart parking modulePublic Safety: Smart cities are not just about saving fuel or reducing congestions, but they are also responsible for saving lives and fighting crime. Finding stolen cars and tracking criminals is one way of establishing safety in the city.

The same LPR technology is used here. Ambulances and fire engines use intelligent traffic lights to reach the scene of emergency quickly and safely. Huge amount of data collected by the city helps to locate places prone to frequent accidents, identify the reasons and prevent them in future. Further, automated response management systems can take over and communicate to relevant authorities in case of accidents. In such situations, big data plays a vital role in eradicating traffic fatalities and prioritize infrastructure projects. Some of the techniques that can be implemented to ensure security for the citizens in a smart city would be Gunshot detection sensors, video surveillance and analytics, drones and cybersecurity [7]. The two path breaking innovations in the field of cybersecurity are – SparkCognition which unveils Deep Armour, an AI empowered antivirus and DarkTrace which is working on identifying new cyber treats and predict better information for ensuring safety and security. AI based surveillance system can track the spread of germs causing various infections. For efficient treatment decisions and healthcare recommendations, cloud based smart electronic health reports can be used [8]. Smart cities can be made smarter by taking perspectives and participation from the citizens for building a cohesive environment.

OTHER TECHNOLOGIES

Different branches of Artificial Intelligence and Machine Learning can contribute to the evolution of Smart Cities. Pattern Recognition: Citizen-city synergy is perhaps the most important aspect of AI in smart cities. It helps in studying and analysing information that is already present, to make better decisions in the future while dealing with some significant changes in their operations. Due to the complexity of cities, many challenges may arise during the application of a clear model. Determining the right model for each city plays an important role in reducing the financial risk of huge upfront capital costs. Machine learning classification algorithms like Bayes Network (BN), Naïve Bayesian (NB), J48, and Nearest Neighbour (NN) can be used to predict weather data especially temperature and rain [9]. Image Recognition: This can be an interesting way to fight traffic and is already persistent in the busy streets of New York City. IntelliScape. io has partnered with the NYC Department of Transportation to understand and curb major traffic events in the city [5]. This when applied in all the traffic ridden cities in the world, will have a positive effect towards reducing traffic and hence will save a lot of time. The wondrous combination of machine learning and image recognition enables the system to detect traffic jams, parking violations, weather reports and send real-time alerts to city officials. The cameras fixed at the intersections capture and process activity, stream back findings and actionable data in real-time, like sending traffic warnings for vehicles violating the rules. This technology can be blended with weather, demographic and location specific data for real-time analytics. IoT: The three essential features of a smart city are being instrumented, interconnected and intelligent. This is achieved through IoT. It helps to remotely monitor, control and manage devices, access real-time data and analyse it by installing sensors (RFID, IR, GPS, laser scanners, etc), connect them to the internet and achieve intelligent recognition, tracking, monitoring, location and management. Some major applications of IoT are shown in Figure 4. IoT can be implemented for efficient supply and utilization of water, innovative solution for traffic congestion, more reliable public transport, transforming buildings to be energy efficient and for public safety. ICT has applications in the field of medicine, transport, tourism, governance, crime prevention, disaster management and the list go on. On of the applications is ambient assisted living for senior citizens. This technology enables them to stay at home and get their body parameters detected time to time by wearing body sensors.

A new technique of generating power from garbage collected in a city is being developed by CISCO. This will assist in eliminating garbage trucks from the city. Data can make life more secured – children playing in the parks can wear sensor-embedded bracelets, which tracks them in case they go missing. Smart Energy Grids are another innovation in this field. They can be used to detect the presence of people in a particular area and adjust the street lights accordingly, which allows scantly populated areas to switch off their lights and save energy. Big data collected from various hospitals across the country can determine common symptoms about a new disease and work together in spreading awareness and finding the right cure for the disease, thereby saving the lives of millions of people. This concept can be taken to a global level where doctors from different hospitals from all over the world come together to completely eradicate such deadly diseases. Deep Learning: This technique has been widely and effectively used for the analysis of different kinds of data including images, videos, speech, text and so on [6]. In smart cities, there is a lot of time series data which are uploaded from the sensors. Fortunately, deep learning has made a lot of progress in the field of artificial intelligence in the recent years and lends itself very well to sequential data analysis. Deep learning platform facilitates quick building of various applications using sequence learning models to solve problems of varied complexity including water distribution and leakage detection, energy conservation, waste disposal and many more. When the engines have been trained using deep learning techniques, the actuators that take actions automatically can also be controlled.

Conclusion

The paper documents all the major fields of AI and Machine Leaning. It explains in detail about different ways of approaching smart city problems and all the possible solutions. With the implementation of technologies like pattern recognition, image recognition, big data analytics, deep learning and neural networks, several problems pertaining to traffic management, parking, water and waste management, education and industrial sectors can be resolved efficiently.

Disclaimer

This essay has been submitted by a student. This is not an example of the work written by our professional essay writers. You can order our professional work here.

We use cookies to offer you the best experience. By continuing to use this website, you consent to our Cookies policy.

background

Want to get a custom essay from scratch?

Do not miss your deadline waiting for inspiration!

Our writers will handle essay of any difficulty in no time.