sensors-logo

Journal Browser

Journal Browser

Artificial Intelligence and Blockchain in the Internet of Things: Opportunities, Challenges and Solutions

A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Internet of Things".

Deadline for manuscript submissions: closed (31 October 2021) | Viewed by 15253

Special Issue Editors


E-Mail Website
Guest Editor
Deakin Blockchain Innovation Lab, School of Information Technology, Deakin University, Geelong, Australia
Interests: blockchain; IoT; edge computing; data analysis and privacy

E-Mail Website
Guest Editor
Department of Human Informatics and Cognitive Sciences, Faculty of Human Sciences, Waseda University, Tokyo 169-8050, Japan
Interests: behavior and cognitive informatics; big data; intelligence computing; blockchain; cyber security
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
School of Informatics, University of Leicester, Leicester LE1 7RH, UK
Interests: data analytics; AI; cloud computing; service computing; IoT; blockchain
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
Faculty of Political Science and Sociopsychological Dynamics, Università degli Studi Internazionali di Roma, Via Cristoforo Colombo 200, 00147 Rome, Italy
Interests: UX; interaction design; learning experience design; mobile applications; smart community; smart city; robotics; IoT; AI; AR
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
Deakin Blockchain Innovation Lab, School of Information Technology, Deakin University, Australia
Interests: information security and privacy; signal and image processing; data analytics and machine intelligence; IoT; blockchain

Special Issue Information

Dear Colleagues,

In recent years, Internet of Things (IoT) has been experiencing exponential growth enabled by the fast-popularized sensors, diverse IoT systems, and massive volume of corresponding heterogeneous IoT data. These unique characteristics pose great challenges to coordinate the distributed IoT devices and handle the increasingly massive volume of data. Although cloud computing has superior performances conducting IoT data analytics and potentially solves some of the issues, to a certain extent, the centralized structure is subject to privacy leakage, single point failure, low-efficient communication, etc. Blockchain, as an emerging decentralized technology, brings several advantageous features like data immutability and non-tempering, which make the mitigation of existing limitations possible. However, integrating blockchain and IoT leads to additional issues, for example, maintaining reliable blockchain systems for IoT systems, anomaly detection, privacy leakage, and poor scalability. Motivated by this, it is essential to devise smart blockchain systems for IoT by leveraging artificial intelligence (AI). The current prosperity of AI in various real-world scenarios incentivizes the joint efforts of AI and blockchain to eliminate the existing issues of IoT.

In this Special Issue, we aim to gather state-of-art advances in AI and blockchain for IoT. Topics include, but are not limited to, the following:

  • New architectures and designs of smart blockchain for IoT
  • AI-enhanced edge computing in blockchain for IoT
  • Privacy and security countermeasures in smart blockchain for IoT
  • Scalable blockchain enabled by AI for IoT
  • Intelligent incentive mechanisms in blockchain for IoT
  • AI and blockchain empowered big data analytics for IoT
  • Anomaly detection and attack defense using AI and blockchain for IoT
  • Smart blockchain-driven IoT applications

Dr. Longxiang Gao
Prof. Dr. Qun Jin
Prof. Dr. Lu Liu
Prof. Dr. Marco Romano
Prof. Dr. Yong Xiang
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sensors is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • Internet of Things (IoT)
  • Artificial intelligence (AI)
  • Blockchain
  • Privacy and security
  • Reliability
  • Scalability
  • Big data analytics
  • Cloud computing/edge computing
  • Incentive mechanism
  • Anomaly detection

Published Papers (3 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

15 pages, 1489 KiB  
Article
Federated Transfer Learning for Authentication and Privacy Preservation Using Novel Supportive Twin Delayed DDPG (S-TD3) Algorithm for IIoT
by Arumugam K, Srimathi J, Sudhanshu Maurya, Senoj Joseph, Anju Asokan, Poongodi M, Abdullah A. Algethami, Mounir Hamdi and Hafiz Tayyab Rauf
Sensors 2021, 21(23), 7793; https://doi.org/10.3390/s21237793 - 23 Nov 2021
Cited by 43 | Viewed by 3649
Abstract
The Industrial Internet of Things (IIoT) has led to the growth and expansion of various new opportunities in the new Industrial Transformation. There have been notable challenges regarding the security of data and challenges related to privacy when collecting real-time and automatic data [...] Read more.
The Industrial Internet of Things (IIoT) has led to the growth and expansion of various new opportunities in the new Industrial Transformation. There have been notable challenges regarding the security of data and challenges related to privacy when collecting real-time and automatic data while observing applications in the industry. This paper proposes an Federated Transfer Learning for Authentication and Privacy Preservation Using Novel Supportive Twin Delayed DDPG (S-TD3) Algorithm for IIoT. In FT-Block (Federated transfer learning blockchain), several blockchains are applied to preserve privacy and security for all types of industrial applications. Additionally, by introducing the authentication mechanism based on transfer learning, blockchains can enhance the preservation and security standards for industrial applications. Specifically, Novel Supportive Twin Delayed DDPG trains the user model to authenticate specific regions. As it is considered one of the most open and scalable interacting platforms of information, it successfully helps in the positive transfer of different kinds of data between devices in more significant and local operations of the industry. It is mainly due to a single authentication factor, and the poor adaptation to regular increases in the number of users and different requirements that make the current authentication mechanism suffer a lot in IIoT. As a result, it has been very clearly observed that the given solutions are very useful. Full article
Show Figures

Figure 1

16 pages, 1287 KiB  
Article
Blockchain-Enabled Asynchronous Federated Learning in Edge Computing
by Yinghui Liu, Youyang Qu, Chenhao Xu, Zhicheng Hao and Bruce Gu
Sensors 2021, 21(10), 3335; https://doi.org/10.3390/s21103335 - 11 May 2021
Cited by 42 | Viewed by 4999
Abstract
The fast proliferation of edge computing devices brings an increasing growth of data, which directly promotes machine learning (ML) technology development. However, privacy issues during data collection for ML tasks raise extensive concerns. To solve this issue, synchronous federated learning (FL) is proposed, [...] Read more.
The fast proliferation of edge computing devices brings an increasing growth of data, which directly promotes machine learning (ML) technology development. However, privacy issues during data collection for ML tasks raise extensive concerns. To solve this issue, synchronous federated learning (FL) is proposed, which enables the central servers and end devices to maintain the same ML models by only exchanging model parameters. However, the diversity of computing power and data sizes leads to a significant difference in local training data consumption, and thereby causes the inefficiency of FL. Besides, the centralized processing of FL is vulnerable to single-point failure and poisoning attacks. Motivated by this, we propose an innovative method, federated learning with asynchronous convergence (FedAC) considering a staleness coefficient, while using a blockchain network instead of the classic central server to aggregate the global model. It avoids real-world issues such as interruption by abnormal local device training failure, dedicated attacks, etc. By comparing with the baseline models, we implement the proposed method on a real-world dataset, MNIST, and achieve accuracy rates of 98.96% and 95.84% in both horizontal and vertical FL modes, respectively. Extensive evaluation results show that FedAC outperforms most existing models. Full article
Show Figures

Figure 1

31 pages, 1202 KiB  
Article
Towards Secure Fitness Framework Based on IoT-Enabled Blockchain Network Integrated with Machine Learning Algorithms
by Faisal Jamil, Hyun Kook Kahng, Suyeon Kim and Do-Hyeun Kim
Sensors 2021, 21(5), 1640; https://doi.org/10.3390/s21051640 - 26 Feb 2021
Cited by 52 | Viewed by 5144
Abstract
Blockchain technology has recently inspired remarkable attention due to its unique features, such as privacy, accountability, immutability, and anonymity, to name of the few. In contrast, core functionalities of most Internet of Things (IoT) resources make them vulnerable to security threats. The IoT [...] Read more.
Blockchain technology has recently inspired remarkable attention due to its unique features, such as privacy, accountability, immutability, and anonymity, to name of the few. In contrast, core functionalities of most Internet of Things (IoT) resources make them vulnerable to security threats. The IoT devices, such as smartphones and tablets, have limited capacity in terms of network, computing, and storage, which make them easier for vulnerable threats. Furthermore, a massive amount of data produced by the IoT devices, which is still an open challenge for the existing platforms to process, analyze, and unearth underlying patterns to provide convenience environment. Therefore, a new solution is required to ensure data accountability, improve data privacy and accessibility, and extract hidden patterns and useful knowledge to provide adequate services. In this paper, we present a secure fitness framework that is based on an IoT-enabled blockchain network integrated with machine learning approaches. The proposed framework consists of two modules: a blockchain-based IoT network to provide security and integrity to sensing data as well as an enhanced smart contract enabled relationship and inference engine to discover hidden insights and useful knowledge from IoT and user device network data. The enhanced smart contract aims to support users with a practical application that provides real-time monitoring, control, easy access, and immutable logs of multiple devices that are deployed in several domains. The inference engine module aims to unearth underlying patterns and useful knowledge from IoT environment data, which helps in effective decision making to provide convenient services. For experimental analysis, we implement an intelligent fitness service that is based on an enhanced smart contract enabled relationship and inference engine as a case study where several IoT fitness devices are used to securely acquire user personalized fitness data. Furthermore, a real-time inference engine investigates user personalized data to discover useful knowledge and hidden insights. Based on inference engine knowledge, a recommendation model is developed to recommend a daily and monthly diet, as well as a workout plan for better and improved body shape. The recommendation model aims to facilitate a trainer formulating effective future decisions of trainee’s health in terms of a diet and workout plan. Lastly, for performance analysis, we have used Hyperledger Caliper to access the system performance in terms of latency, throughput, resource utilization, and varying orderer and peers nodes. The analysis results imply that the design architecture is applicable for resource-constrained IoT blockchain platform and it is extensible for different IoT scenarios. Full article
Show Figures

Figure 1

Back to TopTop