A review on deep learning for future smart cities

Bhattacharya, Sweta; Somayaji, Siva Rama Krishnan; Gadekallu, Thippa Reddy; Alazab, Mamoun; Maddikunta, Praveen Kumar Reddy

doi:10.1002/itl2.187

Cited by 97 publications

(54 citation statements)

References 35 publications

(48 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Looking on "hot" future directions which may be followed in conjunction with smart cities, one can be referred to the definition and implementation of AI-oriented (e.g., Deep Learning, DL) methods for several aspects discussed in Sections 2 and 3. To this end, transfer learning regarding various aspects of a smart city, from one platform to another, as well as moving its related processing tasks, is a future direction, together with the integration of semantic technologies in high-layer applications, in order to enable better interaction of smart devices with the users living the city itself (e.g., workers, tourists, and citizens) [157]. Moreover, the use of virtual objects with AI algorithms would help in creating virtual representations of physical objects (i.e., digital twins) so that the objects can be modeled to be proactive and work automatically and autonomously [158].…”

Section: Future Research Directionsmentioning

confidence: 99%

IoT-Enabled Smart Sustainable Cities: Challenges and Approaches

et al. 2020

View full text Add to dashboard Cite

The ongoing diffusion of Internet of Things (IoT) technologies is opening new possibilities, and one of the most remarkable applications is associated with the smart city paradigm, which is continuously evolving. In general, it can be defined as the integration of IoT and Information Communication Technologies (ICT) into city management, with the aim of addressing the exponential growth of urbanization and population, thus significantly increasing people’s quality of life. The smart city paradigm is also strictly connected to sustainability aspects, taking into account, for example, the reduction of environmental impact of urban activities, the optimized management of energy resources, and the design of innovative services and solution for citizens. Abiding by this new paradigm, several cities started a process of strong innovation in different fields (such as mobility and transportation, industry, health, tourism, and education), thanks to significant investments provided by stakeholders and the European Commission (EC). In this paper, we analyze key aspects of an IoT infrastructure for smart cities, outlining the innovations implemented in the city of Parma (Emilia Romagna region, Italy) as a successful example. Special attention is dedicated to the theme of smart urban mobility.

show abstract

Section: Future Research Directionsmentioning

confidence: 99%

IoT-Enabled Smart Sustainable Cities: Challenges and Approaches

et al. 2020

View full text Add to dashboard Cite

show abstract

“…У роботі [10] проводиться аналіз використання "Інтернету речей" (Internet of Things -IoT) в сучасних розумних містах і в розумних містах найближчого майбутнього -в тому числі в десяти напрямках перерахованих в [5]. Робиться висновок про те, що зібрані дані вимагають максимально ефективного аналізу і обробці (в статті велика частина присвячена використанню алгоритмів глибинного навчання).…”

Section: аналіз останніх досліджень та публікаційunclassified

«smart City» in the Context of Intelegent System and Big Data: Strategies, Risks

Boyko

Vasilenko

2021

MEC

View full text Add to dashboard Cite

According to UN forecasts, by 2050 more than two-thirds of the world’s population will live in cities. Urban and rural areas are evolving and their evolution are based on wide use of broadband Internet systems, cloud computing platforms, geoinformation and geo-positioning systems, high-load computing clusters, wireless telecommunications, “Internet of Things” systems and other technological and information innovations. With the increasing complexity and cohesion of urban systems, the cost of management decisions - and the associated cost of decision errors - has increased significantly. The time for deciding has on the contrary decreased. Incoming data may be deliberately inaccurate, unreliable, clogged with random and intentional interference. And in many cases, it is the management decision that is a critical factor for development and proper functioning of the urban system especially in the context of the formation of a smart city infrastructure. The paper studies use cases of artificial intelligence systems (AI) for processing big data and decision support as a solution to the problems listed above. Use of AI systems allow collecting and cleaning data to obtain a reliable information landscape of the urban systems. Further, on the basis of the obtained picture, AI systems can be used for operational analysis and response to emerging crisis situations, for analyzing the medium-term perspective and balancing the optimal use of urban resources, for long-term planning of the urban environment development. Currently, according to experts, there are two main strategies for the development of information systems - vertical and horizontal. The article analyzes the possibility of applying these two strategies to the use of AI in an urban environment. Using the example of the implementation experience (ET City Brain), on the one hand, conclusions can be drawn about the long-term benefits of such an implementation, on the other, about the risks associated with "vendor lock-in" and the associated problems. One of the biggest risks is the subsequent monopolization of the management system, which transfers part of the power from city structures to the owners of the information system, who, in such conditions, gain the right to vote and leverage on municipalities. It is shown that maximal use of open data and open source software solutions are the most beneficial from the point of view from the point of view of the city and urban systems as stakeholders in the formation of a smart city.

show abstract

“…The optimization algorithms have undergone various improvements in terms of many factors. One among them is by introducing adaptive operators or adaptive functions (Rajakumar, 2013a) (Rajakumar, 2013b) (Swamy et al, 2013) (George & Rajakumar, 2013) (Rajakumar & George, 2012).The abnormal nodes or abnormal co-authoring detection in the semantic graphs is accomplished with the proposed BO-FBU model (He et al, 2016) (Bhattacharya, Somayaji, Gadekallu et al, 2020). Mathematical model of proposed BBO: Initially, the population of the habitats is generated in a random manner.…”

Section: Proposed Bo-fbumentioning

confidence: 99%

Design and Development of Ternary-Based Anomaly Detection in Semantic Graphs Using Metaheuristic Algorithm

Reddy

Rajput

2021

International Journal of Digital Crime and Forensics

View full text Add to dashboard Cite

At present, the field of homeland security faces many obstacles while determining abnormal or suspicious entities within the huge set of data. Several approaches have been adopted from social network analysis and data mining; however, it is challenging to identify the objective of abnormal instances within the huge complicated semantic graphs. The abnormal node is the one that takes an individual or abnormal semantic in the network. Hence, for defining this notion, a graph structure is implemented for generating the semantic profile of each node by numerous kinds of nodes and links that are associated to the node in a specific distance via edges. Once the graph structure is framed, the ternary list is formed on the basis of its adjacent nodes. The abnormalities in the nodes are detected by introducing a new optimization concept referred to as biogeography optimization with fitness sorted update (BO-FBU), which is the extended version of the standard biogeography optimization algorithm (BBO). The abnormal behavior in the network is identified by the similarities among the derived rule features. Further, the performance of the proposed model is compared to the other classical models in terms of certain performance measures. These techniques will be useful to detect digital crime and forensics.

show abstract

A review on deep learning for future smart cities

Cited by 97 publications

References 35 publications

IoT-Enabled Smart Sustainable Cities: Challenges and Approaches

IoT-Enabled Smart Sustainable Cities: Challenges and Approaches

«smart City» in the Context of Intelegent System and Big Data: Strategies, Risks

Design and Development of Ternary-Based Anomaly Detection in Semantic Graphs Using Metaheuristic Algorithm

Contact Info

Product

Resources

About