AIoT stands for Artificial Intelligence of Things, which refers to the integration of artificial intelligence (AI) technologies with Internet of Things (IoT) devices. The combination of AI and IoT is intended to create smarter and more efficient devices, systems, and applications. By using AI to analyse and interpret the large amounts of data gathered from IoT devices, AIoT applications can provide insights, predictions, and automations that can optimize performance, reduce costs, and improve user experiences. Some of the noted examples of AIoT applications include smart homes, connected vehicles, intelligent manufacturing systems, and smart cities.
On the other hand, big data analytics refers to the process of examining and analyzing large and complex data sets to uncover patterns, correlations, and insights that can be used to make better decisions and improve business outcomes. The term “big data” refers to the massive amounts of data generated by various sources such as social media, sensors, mobile devices, and other digital platforms. The primary goal of big data analytics is to extract useful information from large volumes of data that would be impossible or too time-consuming for humans to analyze manually. By using advanced analytical techniques such as data mining, machine learning, and natural language processing, big data analytics can uncover hidden patterns, identify trends, and extract valuable insights from massive data sets. Big data analytics has many applications across a wide range of industries, including healthcare, finance, marketing, retail, and more. It can be used to improve customer engagement, optimize business operations, reduce costs, and develop new products and services.
AIoT and big data analytics have a lot of potential for transforming healthcare by enabling the development of smarter and more efficient healthcare systems. AIoT devices can collect patient data in real-time from wearable devices, sensors, and other connected devices. Big data analytics can then be used to analyze this data to provide personalized treatment recommendations and to detect early warning signs of health problems. By analyzing large amounts of patient data, big data analytics can be used to predict potential health problems before they occur. This can enable healthcare providers to take proactive measures to prevent or treat these problems before they become more severe.
AIoT and big data analytics can be used to develop more accurate and effective diagnostic tools and treatment plans. For example, machine learning algorithms can be used to analyze medical images and other diagnostic data to identify patterns and make more accurate diagnoses. Big data analytics can be used to optimize healthcare resource allocation, such as hospital bed management, staff scheduling, and medical supply inventory management. This can help healthcare providers to reduce costs and improve patient outcomes. AIoT and big data analytics can be used to speed up the drug discovery and development process by identifying potential drug candidates and predicting how they will interact with the body. AIoT and big data analytics can be used to improve patient engagement and adherence to treatment plans. AIoT and big data analytics can be used to manage the health of populations, rather than just individual patients. By analyzing large amounts of data from multiple sources, healthcare providers can identify health trends, risk factors, and patterns of disease across entire populations. This can help healthcare providers to develop targeted interventions and preventive measures to improve population health outcomes.
AIoT and big data analytics can provide real-time insights and decision-making support to healthcare providers. For example, AI algorithms can analyze patient data in real-time to provide clinical decision support to doctors and nurses, such as recommending appropriate treatments based on the patient's condition. AIoT and big data analytics can be used to create smart hospitals that are more efficient and patient-centered. the integration of AIoT and big data analytics in smart healthcare has the potential to revolutionize the healthcare industry, enabling more personalized, efficient, and effective healthcare services. However, it is important to ensure that these technologies are used in a way that protects patient privacy and confidentiality, and that healthcare providers are equipped with the necessary skills and resources to effectively leverage these technologies.
This book discusses open principles, methods, and healthcare AIoT research issues. It also summarises AIoT research efforts and potential directions.
Organization of the Book
The book is organized into 17 chapters discussing the wide range of
AIoT & Big-Data Analytics for Smart Healthcare Applications.
The first chapter focuses on
semantic AIOT concepts and their applications in healthcare. In this, the authors highlight some developments in semantic technology, its effects in the IoT area, and how they are seen in healthcare. Over the last several times, there has been much emphasis on using SWT to enhance the uptake of sensor networks, IoT, and WoT. Indeed, to tackle semantic interoperability and other issues in healthcare domains, there is a need to comprehend its means of construction.
The second chapter discusses
the IoT-based Sleeping Disorder Recognition System for Cognitive impairment Diseases. This chapter focuses on This chapter describes the state of art technologies involved in sleep monitoring and also discusses the challenges and opportunities involved, from the initial step of acquiring the data to the applicability of the acquired data based on the consumer level and clinical settings.
The third chapter, titled
Recent Trends in Smart Health Care: Past, Present and Future information, focuses on The essential technologies that underpin smart healthcare are briefly described, together with the successes and challenges they have faced, the current status of these technologies in important medical areas, and the possibilities for the future of smart healthcare.
The fourth chapter,
A Monitoring System for the Recognition of Sleeping Disorders in Patients with Cognitive Impairment, briefly introduces the chapter and will review the advantages and disadvantages of the extant and novel sensing technologies, focusing on new data-driven technologies that include Artificial Intelligence.
The fifth chapter, titled
Early prediction in AI-enabled IoT environment, discusses Intelligent sensing devices. These machines use internet facilities to communicate with each other. The devices have different capacities and capabilities. They communicate over a common platform.
The sixth chapter, titled
AI and Blockchain-based Solution for Implementing Security for Oral Healthcare 4.0 Bigdata This chapters objective is to review data security applications in the healthcare domain using blockchain technology and present the highlights from selected survey papers and carried out compare the work & implement data security using a web-based prototype based on blockchain technology.
The seventh chapter,
An Artificial Intelligence-based method for detecting false news in Health Sector during a pandemic, focuses on developing a Machine Learning model for deception detection using Natural Language processing techniques and machine learning algorithms. It detects fake news from non-reputable sources, which misleads people and distracts them from fraud messages and unnecessary texts, by building a model using count vectorize, TF-IDF and logistic regression algorithm.
The eighth chapter, titled
“Intelligent Framework for Smart Health Application using Image Analysis and Knowledge Relegation Approach”, highlights Diabetic retinopathy and uses fundus images of the eys and used knowledge relegation approach. This chapter also illustrated five classes of retinopathy and classifier accuracy.
In the ninth chapter, titled
Brain Stroke Prediction Using Deep Learning, The proposed system is contrasted with the existing system, showing an enhancement in the capability to anticipate the stroke. The proposed system achieved an accuracy of 89%.
The tenth chapter, titled
Secure Electronic Health Records Sharing System using IoT and Blockchain, focuses on combining blockchain and cryptography to develop a secure platform for providing patients full control over their health records and maintaining data integrity.
The eleventh chapter, titled
Geofencing For Elderly To Improve Surrounding Estimation in Automated Electric Vehicles, discusses applications built for older adults. Through this application, the person gets the direction to return home, or the alert message is sent to the family member or the caretaker. The alert message is sent while the person is out of the fencing area, oneself or the caretakers, and the person's location can be tracked.
The twelfth chapter,
I am the Eye-Assistive Eye, describes this device's vision to design and construct the blind-friendly embedded device. The blind and visually handicapped have difficulty utilizing mobile phones because social media and online banking programmes on smartphones are difficult for them to use.
The thirteenth chapter, titled
Stage of retinopathy of prematurity using Convolution Neural Network and Object Segmentation Technique, focuses on The utility of the Convolutional Neural Network was examined to localize ridges in neonatal photos that have been labelled. The KIDROP study and a dataset comprising 220 photos of 45 infants were used. With the segmentation of the ridge region as the ground truth, 175 retinal pictures were used to train the system. The system's detection accuracy was 0.94 with 45 images under test, proving that data augmentation detection in conjunction with image normalizing pre-processing allows accurate identification of ROP inside its early stages.
The fourteenth chapter, titled “
An Overview of Recent Medical Applications in Soft-Robotics, ” discusses how soft robotics can be applied in MIS and Notes. This chapter focuses on robotics applications in the medical field, soft robotics challenges and future directions in the healthcare industry.
The fifteenth chapter, titled
“Applications of AI-enabled Robotics in Healthcare”, describes the importance of AI-enabled medical robots in the healthcare sector and is intended to deliver good outcomes to assist people in doing complex tasks that need a significant amount of time, accuracy, concentration, and other routines that cannot be accomplished solely through human capability.
The sixteenth chapter, titled “
An Overview of Current and Future Applications of Robotics in Surgical Operations”, aims to overview robotics’ current and future applications in surgical operations and the advantages and disadvantages of surgical robots.
The seventeenth chapter titled “
Healthcare Applications Centered on AIoT” Provide interconnection between the AIOT and Healthcare system. It also focuses on issues in IoT Healthcare, remote health monitoring and wearable devices which can be used to take medical readings.
Shreyas Suresh Rao
Department of CSIS, BITS-PILANI, WILPD
Pilani, Rajasthan 333031, India
Steven Lawrence Fernandes
Department of Computer Science, Journalism and Design
Creighton University, NE, Omaha, USA
Chandra Singh
Department of ECE, Sahyadri College of Engineering &
Management Sahyadri Campus,
Adyar Mangalore Taluk, India
Rathishchandra R. Gatti
Department of Mechanical Engineering
Sahyadri College of Engineering & Management
Sahyadri Campus, Adyar
Mangalore Taluk, India
Harisha A.
Department of CS&E, Sahyadri College of Engineering & Management
Sahyadri Campus,
Adyar Mangalore Taluk, India
&
Rohanchandra R. Gatty
Department of Surgical Oncology, Father Muller Oncology Centre
Mangaluru, Karnataka 575002, India
