Abstract By combining blockchain technology (BT) and reinforcement learning (RL), the proposed work addresses the difficulties associated with vaccine recommendations. The need for individualized recommendations is obvious as vaccine schedules become more complicated and there are more vaccines available. The proposed work presents a novel approach that combines the adaptability of RL with the security, privacy, and transparency of BT. Layers for data processing, application, consensus, and smart contracts are included in the system architecture. It provides user‐managed secure access, individualized vaccine recommendations, and decentralized data storage. The system aims to improve public health outcomes by using smart contracts to automate procedures and RL to improve recommendations. Using 10‐fold cross‐validation on the Vaccine Adverse Event Reporting System (VAERS) dataset, the experimental study verifies the performance of the system. The study focuses on metrics like accuracy, sensitivity, specificity, and F‐measure when contrasting the proposed model with current solutions. The ability of proposed model to offer precise and well‐informed vaccine recommendations is demonstrated by its consistent outperformance of competitors in accuracy and sensitivity.

Industrial Internet of Things (IoT) and Industry 4.0 enable interconnection among various devices. An opportunistic IoT network is an ad hoc network that is formed by the nodes (e.g., smart vehicles and mobile phones) by utilizing various short radio range techniques. In this kind of network, information forwarding and dissemination among other smart devices is based upon the opportunistic contact nature mainly due to network dynamics and user mobility. Routing plays an important part in these kinds of networks since there does not exist a pre-established route (Tyagi and Kumar, 2013). Nodes are often selected dynamically based upon many parameters such that messages can be delivered successfully to the destination devices or sinks. However, these intermediate nodes are often selfish because routing these packets costs energy. In the case of incomplete cooperation and asymmetric information, message delivery can be severely degraded, which increases the network delay affecting the overall network performance. Therefore, this work proposes an incentive design mechanism based on the contract theory to reward intermediate nodes appropriately to forward the messages. The contract theory is used to model the forwarding-forwarder node interaction as a labor market with private information. First, the users are classified into a finite number of types according to their ability of forwarding the message, and the service trading between the forwarding and forwarder nodes is properly modeled. Furthermore, the necessary and sufficient conditions are derived to provide the incentives to the nodes involved in the message forwarding. Extensive simulations show that the proposed mechanism is effective in providing incentives and outperforms other benchmark schemes in terms of delivery probability, average latency, and overhead ratio.

With a subtle rise in the vehicular traffic, it has become necessary for the users to be more aware of their surroundings. Vehicular AdHoc Network (VANET) provides a solution to connect these vehicles with the data centers to leverage this information for the benefit of the users. It renders end-to-end details for traffic flow monitoring and dynamic route scheduling of vehicles to prevent unforeseen incidents. Current researches suggest that numerous IoV architectures authenticate the vehicles enabling inter-vehicular communication. To improve the quality of service, this work leverage vehicle-to-roadside communication, and priority based batch-verification system. Further, to ensure safer computations of time-critical information and faster processing of event-driven messages, vehicular edge computing based hierarchical framework is proposed. The security analysis proves that this framework can substantially improve power consumption and mitigate security issues such as traceability, identity privacy-preserving, replay attacks, denial of service attacks, and impersonate attacks.

There has been an asymmetric shift toward harnessing cloud-based technologies as the world focuses on shifting operations remotely. Data security for remote operations is crucial for the protection and preservation of critical infrastructure. Furthermore, there has been an emerging trend to integrate IoT-based devices with the expanding cloud infrastructure. In this work, mobile cloud-based infrastructure is considered where contact opportunities are developed in an opportunistic manner so as to facilitate efficient data forwarding and secure process handling. A probabilistic framework is proposed that facilitates data routing between the nodes and local cloud in an IoT network coupled with a multitier trust and encryption scheme for secure data delivery in the cloud-based IoT network. The proposed scheme is evaluated with simulations over two data sets against attack resilience and routing efficiency-based performance metrics, comparing to standard protocols, such as PRoPHET, MaxProp, ProWait, and TCAFE, which displays the enhancement in operations of Sec-CIoT.

Analysis of human posture has many applications in the field of sports and medical science including patient monitoring, lifestyle analysis, elderly care etc. It is important to understand if a person is healthy (in terms of his everyday posture) or is suffering from a joint/bone disease as reflected by his incorrect posture. Many of the works in this area have been based on computer vision techniques. These are limited in providing real-time solution. The aim of the proposed work is to classify the human posture during three different activities (standing, sitting and sleeping/lying) as a healthy or an unhealthy one. This is done by applying machine learning techniques on a large posture dataset which is collected with the help of MPU-6050 sensors mounted on multiple positions on the body. The performance evaluation of the proposed work reveals that the proposed work is efficient enough to classify the postures accurately.

The ongoing pandemic of COVID-19 has shown the limitations of our current medical institutions. There is a need for research in automated diagnosis for speeding up the process while maintaining accuracy and reducing computational requirements. In this work, an IoT and edge computing based framework is proposed to automatically diagnose COVID-19 from CT scans of the patients using Deep Learning techniques. The proposed method requires less computational power and uses ensemble learning to increase the models’ overall predictive performance. In the simulation, it was found that each model performs better in some areas than the other. The proposed scheme uses ensemble learning to take advantage of such an occurrence and achieved an accuracy of 86.2% and an AUC score of 89.8% on the COVIDCT-Dataset. This accuracy is achieved keeping the hardware accessibility in mind by training the models using a labeled dataset of CT-scans of the patients. Unlike other works, we were able to train models on a single enterprise-level GPU. It can easily be provided on the edge of the network, which reduces communication overhead and latency. This work aims to demonstrate a less hardware-intensive approach for COVID19 detection with excellent performance combined with medical equipment and help ease the examination procedure.

Handoff in a cognitive radio networks (CRNs) is a situation that arises whenever a secondary user (SU) has to switch from its current channel to a new target channel in case the primary user (PU) reclaims the current channel or the channel conditions get worst. Before starting the SU transmission, a proactive decision to select the prospective vacant target channel after the PU interruption to resume the unfinished transmission can save substantial sensing time. In addition, the sequence of backup target channels can help reducing the service time of a SU considerably. This paper proposes a proactive decision based handoff scheme for CRNs, in which a non- iterative greedy approach is implemented to proactively determine the optimal target channel sequence without requiring the usual brute force strategy. Simulation results show that the proposed approach outperforms the reactive approach as well as a chosen benchmark scheme in terms of service time and number of handoffs. A comparative performance is also obtained in terms of throughput achieved by the SU under varying PU traffic.

Handoff in cognitive radio networks (CRNs) is a situation that arises whenever a secondary user (SU) has to switch from its current channel to a new target channel in case the primary user (PU) reclaims the current channel. Often when a SU switches to a target channel, it finds that it has to share the target channel with the coexistent users. These coexistent users can either be the interrupted or non-interrupted SUs who also wish to share the same channel. Long waiting in a queue or simultaneous access to the channel may decrease the SU's and network's throughput considerably. The SUs may even behave selfishly to maximize their own throughput. This paper analyzes the interactions and behavior of the SUs during the target channel sharing through non-cooperative, mixed strategic, and cooperative games. The benefits of the SUs and the overall network is analyzed by finding the Nash equilibrium and the Nash bargaining solution (NBS) for the non-cooperative, mixed strategy, and cooperative game respectively.