The Internet of things (IoT) is a heterogeneous network of different types of wireless networks such as wireless sensor networks (WSNs), ZigBee, Wi-Fi, mobile ad hoc networks (MANETs), and RFID. To make IoT a reality for smart environment, more attractive to end users, and economically successful, it must be compatible with WSNs and MANETs. In light of this, the present paper discusses a novel quantitative trust model for an IoT-MANET. The proposed trust model combines both direct and indirect trust opinion in order to calculate the final trust value for a node. A Beta probabilistic distribution is used to combine different trust evidences and direct trust has been calculated. The theory of ARMA/GARCH has been used to combine the recommendation trust evidences and predict the resultant trust value of each node in multi-step ahead. Further, a routing protocol has been designed to ensure the secure and reliable end-to-end delivery of packets by only considering trustworthy nodes in the path. Simulation results show that our proposed trust model outperforms similar existing trust models.
Internet of Things (IoT) has revolutionized the digital world by connecting billions of electronic devices over the internet. IoT devices play an essential role in the modern era when conventional devices become more autonomous and smart. On the one hand, high‐speed data transfer is a major issue where the 5G‐enabled environment plays an important role. On the other hand, these IoT devices transfer the data by using protocols based on centralized architecture and may cause several security issues for the data. Merging artificial intelligence to 5G wireless systems solves several issues such as autonomous robots, self‐driving vehicles, virtual reality, and engender security problems. Building trust among the network users without trusting third party authorities is the system's primary concern. Blockchain emerged as a key technology based on a distributed ledger to maintain the network's event logs. Blockchain provides a secure, decentralized, and trustless environment for IoT devices. However, integrating IoT and blockchain also has several challenges; for example, major challenge is low throughput. Currently, the ethereum blockchain network can process approximately 12 to 15 transactions per second, while IoT devices require relatively higher throughput. Therefore, blockchains are incapable of providing functionality for a 5G‐enabled IoT based network. The limiting factor of throughput in the blockchain is their network. The slow propagation of transactions and blocks in the P2P network does not allow miners and verifiers to fastly mine and verify new blocks, respectively. Therefore, network scalability is the major issue of IoT based blockchains. In this work, we solved the network scalability issue using blockchain distributed network while to increase the throughput of blockchain, this article uses the Raft consensus algorithm. Another most important issue with IoT networks is privacy. Unfortunately, the blockchain distributed ledgers are public and sensitive information is available on the network for everyone are private, but in such cases, third party editing is not possible without revealing the original contents. To solve privacy issues, we used zkLedger as a solution that is based on zero knowledge‐based cryptography.
The global demand for electricity has visualized high growth with the rapid growth in population and economy. It thus becomes necessary to efficiently distribute electricity to households and industries in order to reduce power loss. Smart Grids (SG) have the potential to reduce such power losses during power distribution. Machine learning and artificial intelligence techniques have been successfully implemented on SGs to achieve enhanced accuracy in customer demand prediction. There exists a dire need to analyze and evaluate the various machine learning algorithms, thereby identify the most suitable one to be applied to SGs. In the present work, several state-of-the-art machine learning algorithms, namely Support Vector Machines (SVM), K-Nearest Neighbor (KNN), Logistic Regression, Naive Bayes, Neural Networks, and Decision Tree classifier, have been deployed for predicting the stability of the SG. The SG dataset used in the study is publicly available collected from UC Irvine (UCI) machine learning repository. The experimentation results highlighted the superiority of the Decision Tree classification algorithm, which outperformed the other state of the art algorithms yielding 100% precision, 99.9% recall, 100% F1 score, and 99.96% accuracy.
Ensuring soil strength, as well as preliminary construction cost and duration prediction, is a very crucial and preliminary aspect of any construction project. Similarly, building strong structures is very important in geotechnical engineering to ensure the bearing capability of structures against external forces. Hence, in this first-of-its-kind state-of-the-art review, the capability of various artificial intelligence (AI)-based models toward accurate prediction and estimation of preliminary construction cost, duration, and shear strength is explored. Initially, background regarding the revolutionary AI technology along with its different models suited for geotechnical and construction engineering is presented. Various existing works in the literature on the usage of AI-based models for the abovementioned applications of construction and maintenance are presented along with their advantages, limitations, and future work. Through analysis, various crucial input parameters with great impact on the estimation of preliminary construction cost, duration, and soil shear strength are enumerated and presented. Lastly, various challenges in using AI-based models for accurate predictions in these applications, as well as factors contributing to the cost-overrun issues, are presented. This study can, thus, greatly assist civil engineers in efficiently using the capabilities of AI for solving complex and risk-sensitive tasks, and it can also be used in Internet of things (IoT) environments for automated applications such as smart structural health-monitoring systems.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.