The term "lockdown" was introduced due to the COVID-19, and it drastically transformed the lifestyle of the human being. Before COVID-19 hit our society, we used to go to hospitals or clinics even for the same health issues, where doctors used to do clinical tests by physical examination. But this has drastically changed for COVID-19 norms; the physical examination is only applicable in critical care scenarios. Still in human life there are some diseases such as diabetes and blood pressure that are not critical but need regular consultation. Therefore, digitalization and communication revolution provide an effective solution, where basic consultation and patient monitoring can be performed easily through digital communication channels such as mobile phones, apps, or video-conferencing calls.

In this pandemic situation, it is necessary to maintain social distancing, and restriction has been imposed on traveling, which brings a greater restriction on how to do real-time monitoring of a patient from any location at any instant of time. This problem can easily be solved with the introduction of m-health technology in healthcare sector. It uses digital applications for remote monitoring, remote data collection, diagnosis, and treatment support. This revolutionary development has made diagnosis and prediction of diseases much convenient at early stages. Because of this, the human health problem is minimized.

This chapter will discuss how the m-health technology helps patients as well as healthcare workers. Due to this real-time monitoring, a patient can easily be diagnosed from his/her place. The chapter comprises what is m-health, working of m-health technology, impact of m-health technology on society. Also, this provides insight on all the aspects in m-health technology.

Today, the effect of COVID-19 has become a worldwide problem. The transmission of this virus from one human being to another is a serious concern. This virus can spread from one person to another due to contact of a contaminated surface. The virus can survive on the surface of metal, wood, plastic, glass, disposal goods, etc. The survival time of the virus depends upon the nature of surface. To destroy the virus from the contaminated surface, some specific concentrations of alcoholic chemicals such as ethanol, propanol and sodium hypochlorite are required. The uses of exposure time of these chemicals depend upon the percentage of concentration. One successful method to control the transmission of virus is to make people stay at their home as virus needs human body for transmission from one place to another. The spreading rate of virus through human being is very high. However, this virus has spread across the whole world and the survival of human beings is very difficult in the present scenario, but also there are some positive aspects that have been observed. Due to low movements of vehicles, air pollution, and due to industrial lockdown, air and water pollution have decreased.

Quality medical care and remote monitoring will significantly mitigate the mortality rate of rural people during the COVID outbreak. Individual care and diagnosing are challenging in a short period during the pandemic situation in the hospital. An exhaustive survey on the technologies and wearable devices used on the Internet of Medical Things (IoMT) to combat COVID-19 is done in this chapter. The security threats at different levels of IoMT are also discussed. This chapter also proposes a low-cost secured IoMT device to monitor the quarantined COVID patients in rural areas. The essential medical parameters like body temperature, oxygen level, heart rate, and glucose level have been measured and securely transmitted to the cloud. Any abnormal condition will be identified and informed to the medical data center with high priority using a priority-based preemptive real-time operating system scheduling algorithm. The medical information collected from the IoMT device is securely transmitted and stored in a cloud using Advanced Encryption Standard. Further, the device will also track an unauthorized movement of the quarantined patient and intimate the local administrative officer to prevent the COVID-19 spread.

With a projected increase in world population to about 2.3 billion by the year 2050 and the corresponding challenges this increase would have on the provision of healthcare for the populace, there arises a need for a drastic improvement in the current state of the healthcare industry in order to overcome the challenges. A shift from the usual reactive approach to healthcare, in which health conditions would have deteriorated before treatment begins, to a more proactive methodology, which focuses on early diagnosis, identification and prevention of health conditions and wellness management is needed. This can be achieved by making health condition monitoring and well-being management a huge priority. Thus, considerations must be given to Internet of Things (IoT) technologies, as they can impact positively in designing, building and maintaining intelligent, interconnected and individually tailored healthcare services and products. With the aid of IoT technologies, individual physical conditions can be monitored continuously and remotely and actions are taken as necessary. Also, a proper record can be kept for individual health conditions and their progress levels monitored, thus, enabling healthcare providers to better evaluate and detect early symptoms of health problems. Although with the adoption of the IoT in healthcare, a lot of benefits are obtainable, there are still some concerns, including security, standards, scalability and privacy. These concerns seem to overwhelm the seemingly broad opportunities available in IoT and must be tackled to facilitate the application of IoT. This chapter aims to open up the techniques and advantages of IoT in personalized healthcare. It also opens up the challenges and possible solutions that can be adopted in tracking and monitoring health status.

The healthcare sector has a large deployment of critical assets, which must be available at the right place at the right time. This necessitates not only the location of the assets being monitored in real time but also the serviceability being ensured through predictive maintenance. The Internet of Things (IoT) has transformed real-time data acquisition, which can be aggregated and analysed for meaningful inferences about the monitored process and assets. The information can be collected and exchanged through radio, Bluetooth or other communications technologies but raises privacy and security concerns as the critical asset information is susceptible to interception and tampering both in transit and at rest.

The asset information is critical both for privacy preservation and tamper proofing. Combining the use of blockchain technology with IoT can provide a high degree of trust and security. The data can thereby be securely shared within the private blockchain only with the authorised parties.

This chapter discusses the application of combining IoT and blockchain technologies into a solution to address challenges in the healthcare sector. In particular, we present an architecture for integrating IoT, edge artificial intelligence and blockchain technologies for asset management in the healthcare sector.

The rampaging effects of the coronavirus disease in 2019 (COVID-19), which was pronounced a pandemic on 11 March 2020 by the World Health Organization (WHO), have become one of the biggest challenges of the twenty-first century in terms of general wellbeing and safety. The effects of COVID-19, with over 100 million positive cases and more than 3 million deaths, have caused great damage to the social, economic and family well-being of people around the world. Clinical studies of COVID-19 have shown that patients are mostly infected from the lungs as a result of the SARS-COV-2 virus (severe acute respiratory syndrome coronavirus 2), for which the data collected from various patients are huge for medical practitioners to analyse and capture the trends. To solve this problem, the concept of deep data analysis comes into play. Deep data analysis is a process used in deriving useful information, trends and analysing large-scale data. Making use of deep analytics processes will ensure that needed results are gotten from millions of COVID-19 data. This chapter discusses the various deep analytics applications and how they can be used specifically for COVID-19 data. One very useful deep analytics technique is the convolutional neural network (CNN) model. CNN has shown to be useful in analysing image data and this technique can be applied in COVID-19-related situations. A method of diagnosing positive COVID-19 patients involves chest X-ray, radiography. The captured X-rays can be fed to a trained CNN model that checks for differences between that of the positive patients and a healthy one. Thus, deep analytics through CNN can be useful in diagnosing COVID-19 patients. To carry out the deep analytics, the COVID-19 radiography database on Kaggle was used. This chest X-ray database consists of 3,615 COVID-19 positive images, 10,192 normal images, 1,345 viral pneumonia images and 6,012 lung opacity images. After cleaning the data, they were split into training, testing and validation sets. The trained CNN model was trained to distinguish between the four different groups of images. Eventually, the proposed system was synchronized with Internet of Things - based health monitoring tools and provides results to doctors and health workers, in general, to adequately diagnose and assist in the treatment of COVID-19.

Bioengineering sign is responsible for processing biosignal acquisition preprocessing and evaluation. It is used so that physicians can decide on valuable information. New methods of image processing helped us to expose data, which was initially used to treat various diseases completely modified by this approach. Healthcare professionals use several types of face detection and machine learning (ML) techniques to examine physiological data. Using intelligent biomedical analytical techniques, software-based signals may be examined to allow physicians to make much better judgments in clinical trials. ML techniques in healthcare, biology and bioinformatics are becoming very effective. Biomedical signals processing and analysis progresses have been unbelievable in many fields, comprising biometrics, medical data management, etc. Biosignal monitoring and database technology that are applications- and data based not only get profit from learning machines but also promote the implementation of intelligent procedures. In this chapter, we will discuss new development and techniques in the interpretation of signals and ML for biological brain signals. In this, we will focus on the intelligent algorithms, covering novel theories, electrocardiography signals preparation and knowledge discovery analysis categorization, etc.

In machine learning (ML), many prediction strategies are being popularly made to handle prediction and forecasting issues. Our study demonstrates the potential of ML models to forecast the quantity of forthcoming patients plagued by COVID-19 that is presently thought of as a possible threat to human kind. Four commonly used prediction models such as linear regression, random forest, support vector machine (SVM), and decision-tree classifier are employed in this study to predict the COVID-19 cases under different scenarios. Three styles of predictions were created by every model such as quantity of fresh infected cases, quantity of deaths, and also the range of recoveries within the next 10 days. The results created by the study prove it as efficient mechanism to use these strategies for the present situation of the COVID-19. In this work, we have collected the dataset from the Indian Council of Medical Research website and have applied train test split method to train the model and test the model. We have taken 80% data to train our model and 20% to test our model. In this work, we have applied four ML models for predicting the active cases, recovered cases, confirmed cases, and deceased cases. The four models that we have applied were linear regression, SVM, random forest classifier, and decision tree. After applying these models, we found that linear regression model gives the highest accuracy. In this work, we have also made an android app where we stored all the data of our prediction in firebase cloud storage. When the user opens the app it shows two buttons where one button is for ML prediction and the other for knowing the numerical value of the COVID cases. Thus when a user clicks for the numerical value, it asks for the day and month, and after mentioning the day and month, all the numeric details of active cases, recovered/deceased cases, and confirmed cases are displayed. If a user clicks for ML prediction, then it gives a pop-up for all the types of ML models and thus it displays the graph of that model that the user has clicked.

Internet of Medical Things (IoMT) manages a large number of medical devices and these devices generate, collect, analyze, and transmit a huge amount of data over the network. The collection of medical devices, software applications, services, and healthcare system forms the IoMT healthcare system. The connectivity of sensors and devices has enabled healthcare services to modernize their clinical operations within the boundary of hospitals and from remote locations. The modernization of healthcare system has also posed new threats to security and privacy of sensitive healthcare data, and digitization, automation, new regulations, data analytics, and the development of value-based healthcare system represent some of numerous challenges and opportunities for the IoMT-based healthcare system. Thus, this chapter offers a brief introduction to the IoMT, and its impact on improving the quality of healthcare system. This chapter also provides insights into the emerging issues, i.e., security, privacy, trust, and risk due to the deployment of IoMT at large scale.

Blockchain in the Internet of Things (IoT) is a novel development that exhibits with decentralized, scattered, public, dispersed, and continuous record to exchange with IoT centers and hubs. Blockchain is a movement of blocks; each and every block is connected with its previous block. Each block is having the cryptographic hash-code, its data and previous block hash. The transactions in blockchain are the basic units that are being used to propagate data between IoT centers and hubs. The IoT nodes or hub are unambiguous kind of physical yet intelligent devices with implanted sensors, actuators, projects and developed to transact with other IoT nodes or hubs. The key job of blockchain in IoT is to give a method to process ensured about records of data through IoT node points. Blockchain is ensured about advancement that can be used unreservedly, publically and straightforwardly. IoT requires such an advancement to allow secure correspondence among IoT nodes and hubs in heterogeneous condition. The transactions in blockchain could be finished and examined any person who is affirmed to bestow inside the IoT. The blockchain in IoT may help with improving the correspondence security.

It is ordinary that blockchain will change the IoT. The determination of rules is fundamental to the joining of blockchain and the IoT as a segment of government establishments and in healthcare systems. Healthcare system is described as that is prepared for enabling the correspondence between healthcare substances such as specialists, doctors, chaperons, patients, nurse, meds, labs, suppliers and healthcare specialists. Healthcare suppliers can realize unmistakable security endeavors to ensure about the correspondence between different substances. Either their front-end systems that liable for speaking with specialist, doctor or nurse or their back-end structures that has the health-related data can get blockchain-based IoT security.

Despite pandemics, for instance, the one we are seeing, at this moment, these affiliations necessity to get right and definite information to condemn the best technique: as it has been found throughout ongoing months, solid logical information, quickly, trustworthy sensible data, sharing and declaring or revealing of this data, is the best approach to comprehension, along these lines diminishing overall pandemic. Furthermore, how the sullied cases can be consequently perceived and how the probability of the malady hazard can be assessed or evaluated and foreseen or anticipated by individuals or specialists ceaselessly. In this COVID-19 pandemic, it is critical to consider answers for present blockchain as one of the rising headways as it guarantees health information security, assurance and give legitimate instruments to open minded patient testing, screening, treatment and exchange of defilement anticipation and control information with patients and everyone; fluctuating, appropriate security endeavors for singular security are given.

Blockchain-based IoT application to healthcare business can improve information security; medicinal administrations data can be examined and transmitted while keeping up data security, privacy and protection. This chapter proposes a blockchain-based IoT system that might be applied to healthcare systems to fight against COVID-19 pandemic through consequently recognizing dark tainted cases similarly as predicting and evaluating the risk of COVID-19 pandemic in the networks. Identification, monitoring, reconnaissance, contact tracing and mitigation can bolster and fortify the proposed system with significant highlights if there should arise an occurrence of disease recognition, virus chance expectation and estimation of COVID-19.