홈으로ArticlesAll Issue
ArticlesDeepBlockScheme: A Deep Learning-Based Blockchain Driven Scheme for Secure Smart City
  • Sushil Kumar Singh1, Abir EL Azzaoui1, Tae Woo Kim1, Yi Pan2, and Jong Hyuk Park1,*

Human-centric Computing and Information Sciences volume 11, Article number: 12 (2021)
Cite this article 4 Accesses
https://doi.org/10.22967/HCIS.2021.11.012

Abstract

Today, the continuous deployment of sensors and the Internet of Things (IoT) has boosted the amount of manufacturing data in the smart city. Factories are rapidly becoming more interconnected in the world with sensing data. Big data are generally characterized by five V’s: high volume, high value, high veracity, high variety, and high velocity. Latency, scalability, centralization, reliability, security, and privacy are the major challenges for advanced smart city applications such as smart manufacturing, smart factory, and others. Meanwhile, blockchain is an emerging distributed technology that is deployed to minimize central authority control and provide a secure environment in the recent applications above. On the other hand, deep learning is one of the leading-edge technologies that offer modern analytic tools for the processing and analysis of data and provide scalable production in the smart factory application in a smart city. In this paper, we propose DeepBlockScheme: A Deep Learning-based Blockchain Driven Scheme for a Secure Smart City, where blockchain is used in a distributed manner at the fog layer to ensure the integrity, decentralization, and security of manufacturing data. Deep learning is utilized at the cloud layer to increase production, automate data analysis, and increase the communication bandwidth of the smart factory and smart manufacturing applications in smart cities. We present a case study of car manufacturing with the latest service scenarios for the proposed scheme and compare it to existing research studies using crucial parameters such as securityand privacy tools. Finally, open research challenges are also discussed based on the proposed scheme.


Keywords

Deep Learning, Blockchain, Smart Manufacturing, Scalability, Security and Privacy


Introduction

Along with the rapid development of digital sensor devices based on information and communication technology (ICT), the Internet of Things (IoT) has become the medium for exchange or communication of data, managing the smart city’s application services such as better recognition, tracking, monitoring, and control. These sensor devices, including RFID, humidity, temperature, accelerometer, GPS, and others, are connected to everything through the Internet. Exponential growth is seen every day in the connected sensing IoT devices, with an estimated 50 million expected to be connected to the Internet by 2022 [1, 2]. A smart city is an infrastructure for the accelerated growth of sensing devices with new-generation technology and a developing economy based on telecommunications, sensors networks and others. The development of the smart city needs a lot of major components and services, including smart management, smart control, smart communications used in various recent advanced applications such as smart manufacturing, smart vehicles, smart farming, and others. The composition of information and communication advanced technologies is the predominant need of the smart city environment, and it develops, deploys, and promotes sustainable development solutions to address the growing industry’s challenges such as scalability, centralization, security, and privacy [3]. A crucial part of this ICT is essentially the integrated network of connected IoT devices and industrial machines that transmit data with the help of a wireless medium.
In the digital revolution, smart manufacturing offers optimization capabilities to improve efficiency at low cost and less time, communication bandwidth, and interconnection to humans and machines. It is defined as the fully integrated, collaborative manufacturing systems that respond in real time to changing demands and conditions in smart factories for the supply network, customer needs, and supply chains [4]. It is a new manufacturing environment wherein all tools or machines are interconnected with wireless medium and controlled and monitored by sensors and advanced technologies, including machine learning, deep learning, blockchain, and others. Nowadays, the developed manufacturing factories are deploying smart and intelligent technologies with improved optimization of energy and machine uses and increased productivity by approximately 20% [5]. For Industry 4.0, digital manufacturing is a method of generating a bridge between the physical and software environments with the help of advanced technologies such as IoT, ICT, and others, providing better services such as decision-making, data analysis, and production. It optimizes people, processes, equipment, and resources in smart industries worldwide. According to McKinsey’s research, the smart city industry is forecast to be a 400-billion-dollar market by 2020 worldwide, accounting for approximately 60% of the world’s GDP by 2025 [6]. Manufacturing in an industrial smart city has various advantages, including improvement of data collection, quality management, low computer resources, low congestion, resiliency, and others. Still, it faces a lot of challenges in an industrial smart city with smart manufacturing such as latency, scalability, centralization, reliability, security, and privacy.
Blockchain is the latest distributed ledger technology for enhancing smart manufacturing in the smart city because it has a lot of success factors in the Blockchain adoption for a smart manufacturer. It represents capability platforms for potential support to industrial applications in the smart city. The use of blockchain technology in industries enables decentralization, automatic decision making, digital integrity, reliability, authentication, and secure communication environment in a distributed manner. Blockchain consists of blocks, with every block interconnecting to previous blocks. Every block has four fields: transaction information, timestamp, own hash value, and previous block hash value. Sharma et al. [7] used the miner node selection algorithm for the automotive industry in a distributed smart city and simulate a mined block dataset with a private Ethereum blockchain. With the use of consensus algorithm in consortium blockchain, point-to-point (P2P) communication platform with security and reliability is provided between clients and service providers in the ubiquitous manufacturing for the smart city [811].
On the other hand, deep learning is also being developed for industrial manufacturing in the smart city’s factory. It has outstanding potential and provides real-time functionality in terms of machine tools’ efficiency and production in industrial enterprises. To address issues of centralization, scalability, and communication latency, Singh et al. [12] proposed a deep learning-based cloud at the application layer of smart city platforms for smart industry manufacturing production. It cost-effectively offers high-performance computing devices or resources for manufacturing in a smart city environment. For the analysis and processing of manufacturing data, it provides advanced analytics software such as PyTorch, Konux, Falkonry, and others [1315]. This software is utilized for proving performance in manufacturing in the smart industry. Deep learning uses feature abstraction through multiple hidden layers for increasing production and automatically processing data in smart factories. It also identifies and predicts the number of products with end-to-end optimization in the manufacturing of smart cities [16]. It can extract and learn significant features or patterns from complex manufacturing data with hidden layers and provide scalable data for smart city applications. Deep learning is dependent on multiple layers of artificial neural networks [17, 18].
In this paper, we are proposing a deep learning-based blockchain-driven scheme for a secure smart city. Blockchain is used at the fog layer to address challenges, including decentralization, data integrity, reliability, security, and privacy. Deep learning is utilized at the cloud layer for increasing production, improving communication bandwidth, and enabling advanced decision making with the help of hidden layers for smart manufacturing in a smart city. We also examine its blockchain-based secure scheme and focus on a case study with service scenarios regarding the improvement of the manufacturing process in an industrial environment for the smart city.
The main contribution of this research with some key considerations are summarized as follows:

Design and propose DeepBlockScheme: A deep learning-based blockchain-driven schemeis proposed for a secure smart city.

Provide a case study of car manufacturing with service scenarios for the proposed scheme in a smart city.

Compare and summarize the proposed scheme and showthat it is better than traditional architecture or methods.

Finally, open research challenges are also discussed based on the proposed scheme.


The rest of this paper is structured as follows. Section 2 summarizes related work with challenges and issues related to smart manufacturing in a smart city in a comparison table together with traditional research studies and discusses key considerations.A deep learning-based blockchain-driven scheme is proposed in Section 3 together with the methodological flow. Section 4 discusses a case study of car manufacturing with service scenarios in the smart city following the protocols of the proposed driven scheme. Open research challenges discussed in Section 5.Finally, Section 6 presents the conclusion.


Related Work

In this section, we discuss existing related research studies for secure smart cities with research issues and challenges. Then, we show the key considerations for the proposed driven scheme of smart city applications and address the challenges of existing studies. The basic and major needs of the proposed driven scheme are cited, and a reliable, tamper-proof environment is provided for smart city applications.

Seminal Contribution
Numerous researches have studied the integration of deep learning and blockchain for the security and scalability of smart cities (Table 1). Li et al. [19] proposed a distributed cloud manufacturing system for peer-to-peer transactions with high security and scalability in distributed networks. Ferragand Maglaras[20] proposed a novel deep learning and blockchain-based energy framework for smart grids. This framework is based on two schemes: a blockchain-based scheme to prevent smart grid attacks and a deep learning-based schemeas an intrusion detection system (IDS)deployed to detect network attacks. The proposal was tested on the CICIDS2017 dataset, a power system dataset, and a web robot (BoT)-IoT dataset. Note, however, that this framework did not consider edge computing-enabled blockchain to achieve optimal energy management policy in the smart grid environment. On the other hand, Liu et al. [21] developed a blockchain-enabled data collection and secure scheme using Ethereum and deep reinforcement learning to create a safe environment for industrial IoT (IIoT). This joint framework can provide higher security, reliability, and stronger resistance to attacks such as DoS and DDoS for data sharing. Nonetheless, this method does not cover all the nodes of the blockchain ledger, and the proposed model cannot execute multiple tasks simultaneously. As another approach, Zhang et al. [22] solved the problem of trust tax for small and medium-sized enterprises using blockchain-based security and trust mechanism. The data generated in smart manufacturing can be securely stored, organized, integrated, and communicated among different stakeholders. Still, this method does not cover the possibility of data manipulation at the hardware/software level; moreover, the type of data to input in the blockchain to reduce the trust tax is not analyzed.
Zhang et al. [23] proposed a blockchain-based lightweight data consensus algorithm for IIoT to secure data transmission in the IIoT for smart city applications. The presented algorithm uses a distributed ledger on multiple-edge gateways and assures the data safety of smart factories in smart city applications. Nonetheless, the secret-sharing technology exhibits lower accuracy than other methods. Wu et al. [24] established a hybrid offloading model using mobile cloud computing and mobile edge computing. The authors proposed an algorithm based on distributed deep learning-driven task offloading (DDTO) to decide whether a given task should be offloaded to the cloud and determined if offloading should be done in the central cloud or edge cloud. This proposition was designed for IoT-enabled smart city environment. Security issues were not addressed in the study, however. Single points of failure, data privacy, and security dilemma are critical in centralized IoT systems.

Table1. Comparison of related work
Research work Year Deep learning Blockchain Security issues Solutions Security architecture Hidden pattern requirement
Li et al. [19] 2018 No Yes No Partially Distributed No
Ferrag andMaglaras[20] 2019 Yes Yes Yes Yes Centralized Yes
Liu et al. [21] 2019 Yes Yes Yes Yes Distributed Yes
Zhang et al. [22] 2019 No Yes Yes Partially Distributed No
Zhang et al. [23] 2020 No Yes Yes Partially Distributed No
Wu et al. [24] 2020 Yes No No No Centralized Yes
Our contribution 2020 Yes Yes No Yes Distributed Yes
The above-mentioned state-of-the-art examined the development of smart manufacturing using different methods and technologies. Still, these methods face various limitations including security and privacy. Moreover, some of them are not considered fully automated solutions. Therefore, we propose a secure, automated smart manufacturing framework using consortium blockchain for security, privacy, and scalability and deep learning for a fully automated, self-developed smart manufactory.

Key Considerations for the Proposed Driven Scheme
There are five key considerations in establishing an effective proposed driven scheme for the applications of a secure smart city: decentralization, scalability, security, privacy, and automation. The industry and manufacturing have been driving the innovation and growth of countries since the early industrial revolution in 1840, accounting for approximately 15.6% of global GDP as of 2018 [25]. With the rapid development of Industry 4.0 and emergence of IoT technology, however, the industry evolution has become known as smart manufacturing. Smart manufactories and factories are the main pillars of a smart city. Thus, we present a deep learning-based blockchain-driven scheme for a secure smart city that follows the five key considerations and discuss the importance of each.

Decentralization: It is the process of distributing data in the network without the use of central authority. Blockchain technology provides a distributed way as a ledger for transferring or storing the data in the networks.

Scalability: It is a requirement of advanced applications such as smart manufacturing and smart factories for efficient, scalable production. Thus, we consider and utilize deep learning technology at the cloud or data processing layer for scalability production in smart city applications.

Security: Using blockchain, the data gathered from the device layer can be securely stored and communicated to the data analysis layer to process it according to the protocols of the proposed scheme.

Privacy:It is another essential consideration for a smart city. Using blockchain technology, it shares a database that stores all transactions between smart manufacturers in a distributed or immutable ledger [26]. Thus, we consider a consortium Blockchain to maintain the privacy of the collected data while reducing the time taken for verification and validation processes.

Automation:It is also a very crucial and essential key consideration for smart city applications. In this paper, we consider using deep learning to improve the production process in smart manufacturing and, as a result, develop smart cities.


Proposed Deep Learning-based Blockchain Driven Scheme

The existing research studies have some issues, including centralization, scalability, and communication bandwidth for smart cities applications such as smart manufacturing, smart factory, and smart transportations. In this section, we present a deep learning-based blockchain-driven scheme for a secure smart city and address the challenges of existing research.

Overview of the Proposed Scheme
The design overview of the deep learning-based blockchain-driven scheme for a secure smart city is shown in Fig. 1. It consists of five layers: device layer, edge layer, cyber layer, data analytics layer, and application layer. Three functions are mainly used in the proposed driven scheme: (1) data gathering, (2) data communication, and (3) data processing and analysis.

The first layer has various physical IoT devicescategorized into three parts: industrial devices (flowmeter, power meter, speedometer, and others), sensor devices (RFID, light, proximity, pressure, and ultrasonic sensors), and IoT devices (smart vehicle, watch, camera, monitor, and speakers). These devices are utilized to collect IoT raw data related to various smart cities (SC1, SC2, SC3).

The second layer contains various industrial gateways at the edge layer of smart cities,which serve as the data communication medium between the device layer and the blockchain layer.

In the third layer, a blockchain-based distributed information hub-based edge node is utilized at the edge layer of the smart city. This consortium blockchain is controlled by trusted entities (designed by the government and/or smart manufacturing), and its main role is to verify and validate the data before adding it to the blockchain.

The fourth layer is the data processing and analysis layer where all the data gathered in the device layer and validated by the cyber layer is being analyzed using deep learning-based methods to extract knowledge.

The fifth and last layer is the application layer, where all the knowledge and results extracted from the data analytics layer are applied directly in the application layer to realize self-management, self-distribution, self-automation, scalable production, and rapid development in smart manufacturing.

Blockchain distributed networks have various government miners used for verification and validation of data and stored information in the network. With this network, we can provide security and privacy in a decentralized manner. A deep learning-based intelligent cloud is available in the cloud layer. The data analysis and processing function is completed in this layer, providing more production in smart manufacturing with self-management, distribution, management, rapid development, and other applications. These applications are part of the application layer.
Fig. 1. Design overview of a deep learning-based blockchain driven scheme for secure smart city.


Structural Design with Methodological Flow
This subsection illustrates the methodological flow of the proposed driven scheme for a secure smart city. In this scheme, functionality is divided into three modules: data gathering, data communication, and data processing a analysis. Blockchain technology is offered at the fog layer for securing communication and storing data on an immutable or tamper-proof ledger, and deep learning is used at the cloud layer for data processing and analysis. With deep learning, the production of smart manufacturing is increased according to the smart city’s requirements. The methodological flow of the proposed scheme for a secure smart city is shown in Fig. 2, and the categorized modules are discussed below:
Data gathering:Data gathering is the first module for the proposed scheme as part of the device layer. This layer has various types of devices, including industrial, sensors, and IoT devices (flowmeter, power meter, ultrasonic, proximity sensors, smartwatch, and smart monitor). All these devices generate raw data—such as temperature, rotational speed, electricity, and current flow—which is transferred to smart city applications including smart manufacturing, smart grid, and others. These applications draw useful information from the raw data.
Data communication:As the second module of the proposed scheme for a smart city, it is available on the edge layer. With the help of industrial gateways, useful information or data is transferred to the Blockchain networks. The entire smart manufacturing is centralized, so it has disadvantages like security and privacy. To mitigate this issue, we communicate data or information to the blockchain networks.
Fig. 2. Methodological flow of the proposed scheme for secure smart city.
Blockchain-based distributed information hub: The fog layer consists of a blockchain-based distributed information hub module, which has some blockchain networks. This network has various government miners and local nodes. The verification and validation function are completed by miners as proof of the work consensus algorithm. First, smart manufacturing transfers the information in the blockchain networks, then all miners initiate the verification process. The verification process is done by one miner first as if solving a computational puzzle. Verification information is then transferred in the blockchain networks and validated by all other miner nodes. When more than 51% of miner nodes validate the information, the validation process will then be completed, and one block adds to the blockchain; otherwise, do not add the block to the blockchain. With the help of a blockchain distributed network, we provide security and privacy with the tamper-proof and immutable ledger.
Data analysis and processing:This is the last module of the proposed driven scheme for smart city applications, referred to as data analysis and processing. This is used at the data analytics or cloud layer, offering deep learning. Thus, in this layer, we are using a deep learning-based intelligent cloud functionality. In this process, it has three parts: input layer, many hidden layers, and output layer. Current production and analysis data are used as input in the input layer. Data is then transferred to the various hidden layers. With the hidden layers, we can predict future outputs and increase the production or scalability of data. This data is then transferred to the output layer of deep learning. Hidden layers A1, A2, A3 are shown in Fig. 2. This output is subsequently communicated to the last layer, called the application layer. It provides various advantages for smart city applications such as rapid development of data, scalable production of data, self-automation, self-management, self-distribution, and self-contribution of data in smart city applications such as smart manufacturing, smart grid, and others.


A Case Study with Service Scenarios

In this section, we present a case study with service scenarios for the proposed driven scheme in smart city applications. We are taking a case study example of smart vehicle manufacturing in Seoul, South Korea. We categorized the country into three parts: Busan, Daegu, and Jeju Island. All cities have a smart car manufacturing center, but the headquarters are in Seoul. A case study with the service scenario of the proposed Scheme is shown in Fig. 3.
This proposal studies the role of Blockchain and deep learning in improving the smart factory in a smart city environment. Blockchain can securely collect data and information from different sensors and IoT devices. The collected data is validated by a group of trusted government nodes in the blockchain ledger to guarantee its accuracy. As a final step, the data is communicated to the cloud layer where it can be processed using deep learning methods and classes. The results are used to improve the production and quality of rapid development, scalable production, automated production, self-management, and self-distribution and prevent future errors.

We consider smart vehicle manufacture in this proposal as a case study to explain in detail the steps needed to realize secure smart manufacturing in a smart city. Smart vehicle manufacturer SV is located in South Korea. SV’s headquarters are in Seoul, South Korea, with different branches in Busan, Daegu, and Jeju Island. SV produces 1,300 smart cars every year. The cars are connected with a consortium blockchain, continuously uploading data regarding the car status including motor condition, temperature, oil level, tire condition, and other technical information. The car also records all the errors that occur and uploads all the collected data once a week to the blockchain ledger. The legal trusted nodes designed by the company verify whether or not the record is legally sent from the car itself. Once the verification is done, the node decides to add a block to the blockchain with the data communicated or signal the car for fraud and falsified data.
The cars are not the only participants in the blockchain ledger. The infrastructure in a smart city also provides CCTV records and road conditions to the blockchain ledger. These data have to be validated by miners chosen by the government. SV company has three other branches in three different cities as important participants in the manufacturing. The headquarters need to know the process and problems regarding the production of cars. The branches also upload in the blockchain ledger all the data regarding the production process and any other data regarding production errors.
All the data uploaded through industrial gateways into a consortium blockchain are communicated to the data processing and analysis layer. In this layer, deep learning-based intelligent clouds process the provided data to analyze it and extract knowledge based on it. The knowledge and results will help the headquarters make critical decisions regarding the production process in the other branches and keep track of the produced smart cars to understand the technical problems better, find a solution to them, and avoid the recurrence of such errors in the future production line.


Open Research Challenges

This study proposed a deep learning-based blockchain-driven scheme for secure smart city applications like smart manufacturing, which mitigates various issues such as centralization, scalability, automation, communication bandwidth, security, and privacy. For this purpose, blockchain technology provides a secure environment for smart manufacturing and automation as scalable production in smart factories offered by deep learning technology. With hidden layers in deep learning, futuristic prediction for intelligent manufacturing is smartly analyzed. Nonetheless, there are still some open challenges in smart city applications, such as generation of massive amount of data, complexity of managing data quality, supply chain scenario, quality service issue, computation, and others. All of the open research challenges are discussed one by one below:
Big data as management:It is essential to deal with issues in smart city applications such as smart manufacturing, smart healthcare, etc. Every application uses different IoT devices because billions of IoT devices are connected to the Internet worldwide. These devices are cautiously increased, generating IoT data for smart applications [27, 28]. This issue is related to the insufficient understanding and acceptance of big data in smart city applications because data have different formats and varieties. Various methods are used to overcome this type of challenge, such as top-down ladder and autonomous scenario. This method was first accepted by top management data, top-down smart factory ladder, and any other smart city application. Another technique or methodology is an autonomous scenario as a digital platform where all devices are connected to each other in a digitally distributed manner, providing effective big data solution for smart city applications such as smart factories, smart manufacturing, and others. Nonetheless, this challenge was not resolved completely. Thus, we can say that it is an open research challenge. Complexity of managing data quality:Different types of data are available in smart city applications. Thus, it is a critical issue in managing data qualitatively and quantitatively. The diverse information sources carry many information types and complex data arrangements and increase the data integration complexity. Traditionally, organizations utilized only their departments’ data, such as production, supply chain, and others. Nowadays, organizations are using some outer data to improve product quality, such as Hero-Honda, Maruti-Suzuki, and many more. Data storage space is also a problem given the complexity of managing the data in the current manufacturing and production. Thus, the complexity of managing data quality issues exists because resources, technologies, tools, and methodologies are insufficient for addressing this type of problem.
Supply chain scenario: Smart supply chains will enable data handled by distinct digital policies related to internal data methods such as those of a manufacturing factory’s financial governance, outside constructions of suppliers, distributors, retailers, logistics, and operation such as IoT-based products generation systems. The IT-enabled hybrid model has been used in traditional supply chain scenarios for the smart factory. This model’s main problem is information or data stored in slice form such as country-wise or region-wise and city-wise. Thus, inconsistency and redundancy problems arise in this supply chain methodology. To address these challenges, different types of sensors, IoT devices, and advanced technologies, including RFID, GPS, WiBro, and many more, are employed, with more flexible, collaborative digital methodology open for the supply chain management scenario provided. Still, this issue is not resolved fully.
Data visualization: Virtual reality solution is a tool employed for data visualization in various smart city applications. The distribution of processes to many separate supply chain nodes often offers an intricate orchestration of various production aspects such as quality assurance, process agreement, and preservation activities. Virtual reality technology can significantly support an overwhelming number of these activities as data visualization. Still, it is an open research challenge for various advanced smart applications because virtual reality and other tools are not sufficient for mitigating the data visualization issue in smart advanced applications.
Optimizing inefficient processes: This is another open research challenge. Theoretical index levels and inconsistent quality assurance rules and regulations affect overall operational efficiency in the smart manufacturing factory. Still, there are other factors that cause the wasted staff time, which inevitably decreases manufacturing output in the factory. The typical production workforce still consumes far too much time executing old-fashioned machinery controls and keeping paper documents. The IT staff are forced to spend time managing hardware and software instead of finding new fields of discovery. At either end of the product generation process, the procurement and transportation departments rely too much on expensive shipping services.
Quality service issue: This is also an open research issue because deep learning is used to increase scalable production in the smart factory or smart manufacturing with the futuristic prediction of hidden layer output. This is addressed by the proposed scheme. Still, the quality service issue exists in the smart city application. We can improve and increase the manufacturing product quantity with this research, but quality issues are continuously generated. The management culture of all departments, resistance to technological innovation, upper management's unwillingness to provide additional resources and time, and increasing complexity of the supply chain are the measure of quality service challenge in smart city applications like a smart factory, smart manufacturing, and others.
Design computation: Design computation is another open research challenge because various methods and frameworks are easily designed in smart city applications with sensors and IoT devices. Still, these did not resolve design computation issues because advanced applications need some extra resources and computation speeds in smart application environments [29, 30]. A key area of challenge for intelligent manufacturing or smart industries is the lack of sufficient concurrency models in computing, which affects the 5G network’s ability to provide real-time performance.


Conclusion

A fully developed smart city cannot be achieved without the assistance of the smart manufactory as it is the main pillar and driver for the advancement of smart cities. Thus, securing and automating smart manufactories are a crucial requirement. To this end, we proposed DeepBlockScheme, a deep learning-based blockchain scheme for a secure smart city where blockchain is used in a distributed manner at the fog layer for ensuring the integrity, decentralization, and security of manufacturing data. Deep learning is utilized in the cloud layer for production increase, automatic data analysis, and higher communication bandwidth of smart factory applications in smart cities. We presented a case study of smart vehicle manufacturing in a smart city to study and examine blockchain and deep learning approaches to secure, automate, and develop smart manufacturing.


Authors’ Contributions

Everyone in the author list has participated in the writing of this article, reviewed, and revised the article reasonably. All authors read and approved the final manuscript.


Funding

This study was supported by the Advanced Research Project funded by the SeoulTech (Seoul National University of Science and Technology).


Competing Interests

The authors declare that they have no competing interests.


Keywords

Array


Author Biography

author

Name : Sushil Kumar Singh
Affiliation : Dept. of Computer Science and Engineering, Seoul National University of Science & Technology (SeoulTech), Seoul, Korea
Biography : He received his M.Tech. Degree in Computer Science and Engineering from Uttarakhand Technical University, Dehradun, India. Currently, he is pursuing his Ph.D. degree under the supervision of Prof. Jong Hyuk Park at the Ubiquitous Computing Security (UCS) Laboratory, Seoul National University of Science and Technology, Seoul, South Korea. His current research interests include Blockchain, Artificial Intelligence, Big Data, and the Internet of Things. Contact him atsushil.sngh001007@seoultech.ac.kr

author

Name : Abir EL Azzaoui
Affiliation : Dept. of Computer Science and Engineering, Seoul National University of Science & Technology (SeoulTech), Seoul, Korea
Biography : She received B.S Degree in Computer Science from University of Picardie Jules-Verne, Amiens, France. Currently,she is pursuing her Mater degree in Computer Science and Engineering under the supervision of Professor. Jong Hyuk Park.Her current research interests include Blockchain, Internet of Things (IoT) security and Post-Quantum Cryptography. Contact her at abir.el@seoultech.ac.kr

author

Name : Tae Woo Kim
Affiliation : Dept. of Computer Science and Engineering, Seoul National University of Science & Technology (SeoulTech), Seoul, Korea
Biography : Hereceived the B.S. degree in computer science from Kumoh National Institute of Technology, Gumi, South Korea. He is currently pursuing the master’s degree in computer science and engineering with the Ubiquitous Computing Security (UCS) Laboratory, Seoul National University of Science and Technology, Seoul, South Korea, under the supervision of Prof. Jong Hyuk Park. His current research interests include Cloud security, Software Defined Network, and Internet-of-Things (IoT) security. Contact him at tang_kim@seoultech.ac.kr

author

Name : Dr. Yi Pan
Affiliation : Dept. of Computer Science, Georgia State University, Atlanta, Georgia, USA
Biography : Hereceived PhD degree in computer science from the University of Pittsburgh, Pennsylvania.He is now a full professor in the Department of Computer Science at Georgia State University Atlanta, Georgia, USA. He has published more than 100 journal papers with 38 papers published in various IEEE journals. In addition, he has published more than 100 papers in refereed conferences. He has served as the editor-in-chief or an editorial board member for 15 journals. Contact him at yipan@gsu.edu

author

Name : DR. JAMES J. (JONG HYUK) PARK
Affiliation : Dept. of Computer Science and Engineering, Seoul National University of Science & Technology (SeoulTech), Seoul, Korea
Biography : Hereceived Ph.D. degrees from Korea University, Korea, and Waseda University, Japan. He is now a professor at the Department of Computer Science and Engineering, Seoul National University of Science and Technology, Korea. Dr. Park has published about 300 research papers in international journals and conferences. He is editor-in-chief of Human-centric Computing and Information Sciences (HCIS) by Springer, The Journal of Information Processing Systems (JIPS) by KIPS. His research interests include IoT, Information Security, Smart City, Blockchain, etc. Contact him at jhpark1@seoultech.ac.kr


References

[1] S. Mishra, S. Jain, C. Rai, and N. Gandhi, “Security challenges in semantic web of things,” in Innovations in Bio-Inspired Computing and Applications. Cham, Switzerland: Springer, pp. 162-169.
[2] L. Megouache, A. Zitouni, and M. Djoudi, “Ensuring user authentication and data integrity in multi-cloud environment,” Human-centric Computing and Information Sciences, vol. 10, article no. 15, 2020. https://doi.org/10.1186/s13673-020-00224-y
[3] J. Kang and J. H. Park, “Integration of cloud and big data analytics for future smart cities,” Journal of Information Processing Systems, vol. 15, no. 6, pp. 1259-1264, 2019.
[4] S. Tanwar, S. Tyagi, and S. Kumar, “The role of internet of things and smart grid for the development of a smart city,” in Intelligent Communication and Computational Technologies. Singapore: Springer, 2018, pp. 23-33.
[5] N. Tuptuk and S. Hailes, “Security of smart manufacturing systems,” Journal of Manufacturing Systems, vol. 47, pp. 93-106, 2018.
[6] E. Cakmak, “Smart city and industrial IoT applications,” 2017 [Online]. Available: https://iiot-world.com/smart-cities-buildings-infrastructure/smart-cities/smart-city-and-industrial-iot-applications.
[7] P. K. Sharma, N. Kumar, and J. H. Park, “Blockchain-based distributed framework for automotive industry in a smart city,” IEEE Transactions on Industrial Informatics, vol. 15, no. 7, pp. 4197-4205, 2018.
[8] A. VatankhahBarenji, Z. Li, W. M. Wang, G. Q. Huang, and D. A. Guerra-Zubiaga, “Blockchain-based ubiquitous manufacturing: a secure and reliable cyber-physical system,” International Journal of Production Research, vol. 58, no. 7, pp. 2200-2221, 2020.
[9] A. El Azzaoui, S. K. Singh, Y. Pan, and J. H. Park, “Block5gintell: blockchain for AI-enabled 5G networks,” IEEE Access, vol. 8, pp. 145918-145935, 2020.
[10] Y. S. Jeong and J. H. Park, “Security, privacy, and efficiency of sustainable computing for future smart cities,” Journal of Information Processing Systems, vol. 16, no. 1, 1-5, 2020.
[11] A. Dixit and R. Kumar, “Enhancement of big data privacy preserved of Map Reduce by using data anonymization technique,” The International Journal of Analytical and Experimental Modal Analysis, vol. 11, no. 11, pp. 2407-2411, 2019.
[12] S. K. Singh, Y. S. Jeong, and J. H. Park, “A deep learning-based IoT-oriented infrastructure for secure smart city,” Sustainable Cities and Society, vol. 60, article no. 102252, 2020.
[13] AIMultiple, “Manufacturing Analytics Software,” 2020 [Online]. Available: https://aimultiple.com/manufacturing-analytics-software.
[14] I. Mistry, S. Tanwar, S. Tyagi, and N. Kumar, “Blockchain for 5G-enabled IoT for industrial automation: a systematic review, solutions, and challenges,” Mechanical Systems and Signal Processing, vol. 135, article no. 106382, 2020.
[15] J. Cha, S. K. Singh, Y. Pan, and J. H. Park, “Blockchain-based cyber threat intelligence system architecture for sustainable computing,” Sustainability, vol. 12, no. 16, article no. 6401, 2020.
[16] J. Wang, Y. Ma, L. Zhang, R. X. Gao, and D. Wu, “Deep learning for smart manufacturing: methods and applications,” Journal of Manufacturing Systems, vol. 48, pp. 144-156, 2018
[17] S. K. Singh, M. M. Salim, J. Cha, Y. Pan, and J. H. Park, “Machine learning-based network sub-slicing framework in a sustainable 5G environment,” Sustainability, vol. 12, no. 15, article no. 6250, 2020.
[18] Y. Kim and J. Park, “Hybrid decentralized PBFT blockchain framework for OpenStack message queue,” Human-centric Computing and Information Sciences, vol. 10, article no. 31, 2020. https://doi.org/10.1186/s13673-020-00238-6
[19] Z. Li, A. V. Barenji, and G. Q. Huang, “Toward a blockchain cloud manufacturing system as a peer to peer distributed network platform,” Robotics and Computer-Integrated Manufacturing, vol. 54, pp. 133-144, 2018.
[20] M. A. Ferrag and L. Maglaras, “DeepCoin: a novel deep learning and blockchain-based energy exchange framework for smart grids,” IEEE Transactions on Engineering Management, vol. 67, no. 4, pp. 1285-1297, 2020.
[21] C. H. Liu, Q. Lin, and S. Wen, “Blockchain-enabled data collection and sharing for industrial IoT with deep reinforcement learning,” IEEE Transactions on Industrial Informatics, vol. 15, no. 6, pp. 3516-3526, 2018.
[22] Y. Zhang, X. Xu, A. Liu, Q. Lu, L. Xu, and F. Tao, “Blockchain-based trust mechanism for IoT-based smart manufacturing system,” IEEE Transactions on Computational Social Systems, vol. 6, no. 6, pp. 1386-1394, 2019.
[23] W. Zhang, Z. Wu, G. Han, Y. Feng, and L. Shu, “LDC: a lightweight dada consensus algorithm based on the blockchain for the industrial Internet of Things for smart city applications,” Future Generation Computer Systems, vol. 108, pp. 574-582, 2020.
[24] H. Wu, Z. Zhang, C. Guan, K. Wolter, and M. Xu, “Collaborate edge and cloud computing with distributed deep learning for smart city Internet of Things. IEEE Internet of Things Journal, vol. 7, no. 9, pp. 8099-8110, 2020.
[25] World Bank, “Manufacturing, value added (% of GDP) data,” 2021 [Online]. Available: https://data.worldbank.org/indicator.
[26] J. C. S. Sicato, S. K. Singh, S. Rathore, and J. H. Park, “A comprehensive analyses of intrusion detection system for IoT environment,” Journal of Information Processing Systems, vol. 16, no. 4, pp. 975-990, 2020.
[27] J. S. Sheu, I. S. Chen, and Y. S. Liao, “Realization of internet of things smart appliances,” Intelligent Automation and Soft Computing, vol. 25, no. 2, pp. 395-404, 2019.
[28] Z. Xu, Q. Zhou, and Z. Yan, “Special section on recent advances in artificial intelligence for smart manufacturing, Part I,” Intelligent Automation & Soft Computing, vol. 25, no. 4, pp. 693-694, 2019.
[29] M. H. Kabir, K. Thapa, J. Y. Yang, and S. H. Yang, “State-space based linear modeling for human activity recognition in smart space,” Intelligent Automation and Soft Computing, vol. 25, no. 4, pp. 673-681, 2019.
[30] W. Liu, J. He, M. Li, R. Jin, and Z. Zhang, “An efficient supervised energy disaggregation scheme for power service in smart grid,” Intelligent Automation and Soft Computing, vol. 25, no. 3, pp. 585-593, 2019.

About this article
Cite this article

Sushil Kumar Singh1, Abir EL Azzaoui1, Tae Woo Kim1, Yi Pan2, and Jong Hyuk Park1,*, DeepBlockScheme: A Deep Learning-Based Blockchain Driven Scheme for Secure Smart City, Article number: 11:12 (2021) Cite this article 4 Accesses

Download citation
  • Recived15 September 2020
  • Accepted5 January 2021
  • Published15 March 2021
Share this article

Anyone you share the following link with will be able to read this content:

Provided by the Springer Nature SharedIt content-sharing initiative

Keywords