The applications and challenges of machine learning and artificial intelligence in the internet of things for healthcare applications are comprehensively covered in this book. Rapid developments in hardware, software and communication technologies have facilitated the emergence of internet-connected sensory devices that provide observations and data measurements from the physical world. The technology of internet-connected devices, referred to as the internet of things (IoT), continues to extend the current internet by providing connectivity and interactions between the physical and cyber worlds. The IoT is undoubtedly transforming the healthcare industry by redefining the space of devices and interaction of people in delivering healthcare solutions, resulting in applications that benefit patients, families, physicians, hospitals and insurance companies. The use of remote monitoring in the healthcare sector possible with IoT-enabled devices has the potential to keep patients safe and healthy, and empowers doctors to provide superlative care, thereby increasing patients’ engagement and satisfaction as a result of their interactions with doctors becoming easier and more efficient. Furthermore, remote monitoring of patients’ health helps reduce the length of hospital stays and prevents readmissions, in addition to having a major impact on reducing healthcare costs significantly and improving treatment outcomes.

In addition to increasing volume, the IoT generates big data characterized by its velocity in terms of time and location dependency, with a variety of multiple modalities and varying data quality. Intelligent processing and analysis of this big data are the keys to developing smart IoT applications, thereby making space for machine learning (ML) applications. Due to its computational tools that can substitute for human intelligence in the performance of certain tasks, artificial intelligence (AI) makes it possible for machines to learn from experience, adjust to new inputs and perform human-like tasks. Since IoT platforms provide an interface to gather the data from various devices, they can easily be deployed into AI/ML systems. The value of AI in this context is its ability to quickly mesh insights from data and automatically identify patterns and detect anomalies in the data that smart sensors and devices generate — information such as temperature, pressure, humidity, air quality, vibration and sound — that can be really helpful.

Our intent in publishing this book was to comprehensively discuss all of the applications and challenges of using ML and AI in the IoT for healthcare applications that will benefit research scholars working in this domain. Therefore, the 17 chapters of the book briefly discussed below present IoT concepts, frameworks and ideas on biomedical data analytics and information retrieval from the different biomedical domains. The editorial advisory board and expert reviewers have ensured the high caliber of the chapters through careful refereeing of the submitted papers. For the purpose of coherence, we have organized the chapters with respect to similarity of topics addressed, ranging from issues pertaining to the IoT for biomedical engineering and health informatics to computational intelligence for medical image processing and biomedical natural language processing.

• • In Chapter 1, “Internet of Medical Things – State of the Art,” Dr. Kishor Joshi and Dr. Ruchi Mehrotra present the latest technological advancements in the on-body segment of consumer health wearables. Since the traditional approach in healthcare is a more personalized touch-based system, it is not replaceable for diagnosis. Older, chronically ill patients need remote monitoring and medial management services that ensure that nurses or local healthcare assistants connect to doctors in urban or super-specialty fields for better services. This chapter indicates there is already a steep rise in internet of medical things (IoMT) products, but there is still huge potential for growth in the IoMT industry.
• • In Chapter 2, “Issues and Challenges Related to Privacy and Security in Healthcare Using IoT, Fog and Cloud Computing” Hritu Raj, Mohit Kumar, Prashant Kumar, Amritpal Singh and Om Prakash Verma describe the complete architecture along with various challenges and security risks of the next generation healthcare industry with healthcare IoT sensor and fog computing. Furthermore, some methodologies used in various research papers are presented that address security and privacy-related issues in the IoT, Fog and Cloud computing environment.
• • In Chapter 3, “Study of Thyroid Disease Diagnosis Using Machine Learning Technique,” Shanu Verma, Dr. Rashmi Popli and Dr. Harish Kumar discuss Graves’ disease, the most common cause of hypothyroidism that is associated with eye disease. Thyroid cancer, which infects the gland at the base of the neck, has been increasing over the past few years. Endocrinologists believe that this is because the use of new technology, i.e., machine learning, has allowed the detection of thyroid cancer that may not have been detected in the past. According to the Cancer Registry, thyroid cancer is the second more common cancer among women, occurring 3 times more often in women than in men. This chapter studies thyroid disease using a machine learning algorithm.
• • In Chapter 4, “A Review of Various Security and Privacy Innovations for IoT Applications in Healthcare,” Mr. Abhishek Raghuvanshi, Dr. Umesh Kumar Singh and Mr. Chirag Joshi focus on the analysis of numerous security and privacy technologies in healthcare, intelligent communities and smart homes available for IoT applications. According to the findings of an industrial internet survey by the World Economic Forum, roughly two-thirds of respondents said the main issue was interoperability and protection. Most IoT apps are web applications and all of them still have denial-of-service and man-in-the-middle attacks as major threats to the security of their healthcare, smart city, smart home and other IoT applications.
• • In Chapter 5, “Methods of Lung Segmentation Based on CT Images,” Amit Verma and Thipendra P. Singh focus on the use of CT scan images for analysis of lung airways, lung parenchyma, and breathing mechanisms. For better diagnosis of any lung problems, the automatic, nearly accurate analysis of CT images is better than the manual method of doctors analyzing CT scans. In this chapter, automatic and semi-automatic methods of segmentation of lung CT images are discussed.
• • In Chapter 6, “Handling Unbalanced Data in Clinical Images,” Amit Verma focuses on various data-level and algorithm-level-based approaches developed to balance imbalanced data for improving the accuracy of the trained model. In this chapter, the concept and problem of imbalanced data is discussed and various approaches for balancing the data are also highlighted, in which one of the state-of-the-art methods called bagging is discussed in detail.
• • In Chapter 7, “IoT-Based Health Monitoring System for Speech Impaired People Using Assistive Wearable Accelerometer,” Dr. Madhumathy P., Ishita Banerjee and Digvijay Pandey describe IoT-based wireless communication systems with network devices connected to each other that communicate through open source internet access and establish connection between apps and devices for communication between the person being supervised and the medical supervisor. This system can also keep track of real-time records and emergency alerts. To handle the storage and analysis of data-related issues, IoT analytics is implemented.
• • In Chapter 8, “Smart IoT Devices for the Elderly and People with Disabilities,” K. N. D. Saile and Kolisetti Navatha focus on the huge changes brought about by the IoT-powered revolution in health management devices for the elderly and disabled like sensors, wearable devices, audio and video assistance, etc. All these are possible with the help of the IoT. In this chapter, we discuss the technology trends in devices made during the IoT era.
• • In Chapter 9, “IoT-Based Health Monitoring and Tracking System for Soldiers,” Dr. Madhumathy P., Kavitha N and Digvijay Pandey discuss smart sensors used in the medical treatment of soldiers. By tracking a soldier’s location on the battlefield with a smart sensor attached to their body, more accurate body status information can be provided to medical units in order to offer more immediate care. These systems are designed to be implemented for complete mobility with a personal server, which in turn would give a message to the server base station through wireless mode. Soldiers are able to be identified at the earliest based on their unique IP address.
• • In Chapter 10, “Cloud-IoT Secured Prediction System for Processing and Analysis of Healthcare Data Using Machine Learning Techniques,” Dr. G. K. Kamalam, and Ms. S. Anitha discuss a cloud-IoT secured prediction system designed to improve healthcare performance by reducing the execution time of a patient’s request, optimizing the desired selection of the massive amount of patient’s facts and imparting a records retrieval process for those applications. Analysis of the experimental results show that the presented method performs better than existing benchmark systems for considering parameters like disease prediction accuracy, sensitivity, specificity, F-measure, and computational time.
• • In Chapter 11, “Cloud-IoT-Driven Healthcare: Review, Architecture, Security Implications and Open Research Issues,” Junaid Latief Shah, Heena Farooq Bhat and Asif Iqbal Khan discuss security loopholes inherent in IoT architecture and the Cloud platform. The chapter also elaborates on various security countermeasures that have been proposed in the literature, highlighting their strengths and limitations. Also, a discussion on possible defense measures has been provided. The chapter culminates in underlining some burning research problems and security issues that need to be addressed for seamless healthcare services.
• • In Chapter 12, “A Novel Usage of Artificial Intelligence and Internet of Things in Remote-Based Healthcare Applications,” Dr. V. Arulkumar, D. Mansoor Hussain, S. Sridhar, and Dr. P. Vivekananda present the information necessary to reap the benefits of research capacity solutions through AI techniques. Healthcare services are among the applications enabled by the IoT. Advanced sensors may be used to monitor the health of permanent patients or may be inserted into the bodies of patients that can analyze, combine and prioritize the information gathered. Working with algorithms helps doctors change treatments and, at the same time, helps to economize on healthcare.
• • In Chapter 13, “Use of Machine Learning in Healthcare,” V. Lakshman Narayana, R. S. M. Lakshmi Patibandla, B. Tarakeswara Rao and Arepalli Peda Gopi focus on AI-assisted healthcare. Quotient Health has developed a program designed to reduce the cost of EMR structures by strengthening and standardizing the structuring of these frames. This chapter discusses healthcare AI, various implementations of AI, certifiable healthcare benefits, the morality of AI computations and opportunities to improve quality of healthcare skills.
• • In Chapter 14, “Methods of MRI Brain Tumor Segmentation,” Amit Verma discusses the requirements for and importance of using MRI imaging in brain tumor segmentation and the basic methods of doing it. Furthermore, a region-based generative model with weighted aggregation methods for performing brain tumor segmentation using MRI images is also discussed.
• • In Chapter 15, “Early Detection of Type 2 Diabetes Mellitus Using a Deep Neural Network-Based Model,” Varun Sapra and Luxmi Sapra focus on implementing a deep neural network for early identification of diabetes mellitus. For this purpose, benchmark dataset available on the UCI Machine Learning Repository and Kaggle are explored. This chapter suggests a deep neural network-based framework for early detection of disease that can be used as an adjunct tool in clinical practices.
• • In Chapter 16, “A Comparative Analysis of Implementation Framework for Masked Face Detection,” Pranjali Singh, Amitesh Garg and Amritpal Singh discuss quick and accurate approaches for the difficult task of face recognition resulting from certain facial features being hidden by the masks used during the current pandemic. This study uses deep learning-related techniques to resolve the issues of detecting facial features hidden by a mask. Another method of face mask detection is through TensorFlow, YOLOv5, SSDMNV2, SVMs, OpenCV, and Keras. The first step is to discard the masked face region. Next, a pre-trained deep convolutional neural network (CNN) is applied to extract the best features from the obtained regions. Labeled image data is used to train the CNN model. With 98.7% accuracy, a face mask is identified by the proposed system. By using the SVM classifier, the dataset of RMFD had a testing accuracy of 99.64%, SMFD achieved a 99.49% testing accuracy, and LFW achieved 100% testing accuracy. The SSDMNV2 approach used in the study in this chapter yields a 92.64% accuracy score and a 93% F1 score.
• • In Chapter 17, “IoT-Based Automated Healthcare System,” Dr. Darpan Anand and Mr. Ashish Kumar give an overview of the SDN and NFV types of sensors used in IoT devices. Apart from that, the views of various researchers are also given. The challenges of an SDN-based IoT device for healthcare architecture are also discussed.

The seventeen chapters of this book were written by eminent professors, researchers, and those in the industry from different countries. The chapters were initially peer reviewed by the editorial board members, reviewers, and those in the industry who also span many countries. All chapters have been designed to include basic introductory topics and advancements as well as future research directions, which will enable budding researchers and engineers to pursue their work in this area.

The topic of intelligent IoT for advanced healthcare system(s) is so diversified that it cannot be covered in a single book. However, with the encouraging research contributed by the researchers in this book, we (contributors), editorial board members, and reviewers tried to sum up the latest research domains, developments in the data analytics field, and other applicable areas. First and foremost, we express our heartfelt appreciation to all the authors. We thank them all for considering and trusting this edited book as the platform for publishing their valuable work, and for for the kind co-operation extended by them during the various stages of processing this manuscript. We hope this book will serve as a motivating factor for those researchers who have spent years working as crime analysts, data analysts, statisticians, and budding researchers.

Dr. Rohit Tanwar

School of Computer Science,
University of Petroleum and Energy Studies, Dehradun, India

Dr. S. Balamurugan

Director of Research and Development,
Intelligent Research Consultancy Service (iRCS), Coimbatore, India

Dr. Rakesh Kumai Saini

School of Computing, DIT University, Dehradun, India

Dr. Vishal Bharti

School of Computing, DIT University, Dehradun, India

Dr. Premkumar Chithaluru

School of Computer Science,
University of Petroleum and Energy Studies, Dehradun, India