Developing an intelligent virtual medical assistant device would be a better solution for people who can't spend their time and/or who have movement and transportation issues for physical diagnosis and checkup, especially the old-age people and those who have other movement related diseases. Such virtual medical assistants will be a boon to both patients and their relatives. A simple IoT-enabled virtual medical assistant can be an IoT device with sensors to monitor the health status on some basic parameters such as temperature, blood pressure, oxygen level, etc. However, for providing smart healthcare, intelligence needs to be embedded in these kinds of virtual assistants. This article discusses the application of machine intelligence (ML) algorithms in an intelligent virtual medical assistant to provide improved solutions by tracking the patients' historical data along with the current data, which can then provide suggestions, notifications, and medical prescriptions for self-improvement.

In this digital era, at most 80-90% of business transactions are digitized using different mechanisms. In the case of businesses and financial institutions, such digitization poses both merits as well as challenges. Nowadays, the IT industries are focusing on providing a trustworthy solution, namely blockchain-based applications, to provide secured online transactions. This blockchain technology provides a comprehensive solution to B2B applications by providing support to process information across organizations in a highly secured manner. In blockchain, these kinds of secured online transactions are achieved using hyperledgers. In particular, the hyperledger is decentralized as it is replicated across the entire network for all the participants to collaborate in a secured manner. In this chapter, an analysis of the application of hyperledgers in B2B blockchain apps to and their implications in this digital era is provided.

As there are several data sets available, this chapter gives insight on which regions of India have been heavily impacted during the first wave of COVID-19 and the classification of patient status using an ML-based data analytics algorithm. The chapter provides a greater insight on the background work and the reports generated based on the analytical results gathered from the data set. In this pandemic situation, such reports will be a great benefit to assess the history of occurrence and the current status of the COVID-19 situation in India.

Edge analytics are tools and algorithms that are deployed in the internal storage of IoT devices or IoT gateways that collect, process, and analyze the data locally rather than transmitting it to the cloud for analysis. Edge analytics is applied in a wide range of applications in which immediate decision making is required. In the case of general IoT data analytics on the cloud, the data need to be collected from the IoT devices and to be sent to the cloud for further processing and decision making. In life-critical applications such as healthcare, the time taken to send the data to the cloud and then getting back the processed data to take decisions will not be acceptable. Hence, in these kinds of MIoT applications, it is essential to have analytics to be done on the edge in order to avoid such delays. Hence, this chapter is providing an abstract view on the application of machine learning in MIoT so that the data analytics provides fruitful results to the stakeholders.

The research work focuses on the highly important and sensitive research area of detection and prevention of vulnerabilities associated with data processing in MIoT devices when accessed through the network. This work analyzes the application of AI and ML techniques in MIoT applications along with security and privacy threats in medical IoT (MIoT) environment for real-time systems and proposes a framework to address them. It proceeds to the development of an innovative real-time research work by devising mechanisms to prevent the attacks in IoT devices.