Edge-AI in Healthcare: Trends and Future Perspectives

Cover
Half Title
Series Page
Title Page
Copyright Page
Dedication
Table of Contents
Foreword
Preface
Editor Profiles
Contributors
Chapter 1 Introduction to edge-AI in healthcare
1.1 Introduction
1.2 Data usage, analytics, and applications of edge-AI in healthcare
1.3 Edge-AI tools and techniques for healthcare
1.3.1 Tools and techniques of edge-AI
1.3.2 Implementation in healthcare
1.4 Architectures, frameworks, and models for edge-AI in healthcare
1.4.1 Architecture of edge-AI (Xu et al. 2020)
1.4.2 Edge-AI benefits
1.4.3 Frameworks for edge-AI
1.4.4 Model for edge-AI
1.5 Modeling and simulation techniques for edge-AI in healthcare
1.6 Edge-AI, machine learning, and deep learning approaches for healthcare
References
Chapter 2 Edge-AI tools and techniques for healthcare
2.1 Introduction
2.2 Edge computing
2.3 Understanding edge-AI
2.4 Scope of edge-AI in healthcare
2.5 Edge-AI and the Internet of Things (IoT)
2.6 Edge-IoT smart healthcare architecture
2.7 Big data and blockchain in IoT-based healthcare frameworks
2.8 Edge intelligence in IoT healthcare frameworks
2.9 Machine learning and IoT in healthcare frameworks
2.10 Emerging edge technology in smart healthcare
2.11 Edge-assisted smart healthcare functionality flow
2.12 Conclusion
References
Chapter 3 Edge-AI, Machine-Learning, and Deep-Learning Approaches for Healthcare
3.1 Introduction
3.2 Edge computing
3.3 Edge-AI or edge intelligence
3.4 Deep learning
3.5 Healthcare with deep learning
3.5.1 Electroencephalogram (EEG)
3.5.2 Multiple sclerosis (MS)
3.5.3 Breast cancer
3.6 Examples of ML applications to healthcare sector AI-based radiology
3.7 ML and data knowledge for legal understanding
3.7.1 AI for patient experience and control of healthcare operations
3.7.2 Drug discoveries
3.7.3 AI in systems for public health
3.8 Case study
3.8.1 Seaborn FacetGrid
3.9 Results and discussion
3.9.1 Performance measures
3.10 Conclusion and future scope
ReferenceS
Chapter 4 Transforming healthcare with machine-learning and deep-learning approaches
4.1 Transforming healthcare with AI
4.2 Artificial intelligence and its applications in healthcare
4.3 Future of AI in health sector
4.4 Role of machine learning in healthcare
4.4.1 Semi-supervised machine learning
4.4.2 Unsupervised machine learning
4.4.3 Reinforcement machine learning
4.5 Applications of machine learning to healthcare
4.6 Various models used in machine learning
4.7 Deep learning and its role in healthcare
4.8 Computer vision
4.9 Natural language processing
4.10 Reinforcement learning (RL)
4.11 Frameworks of deep learning
4.12 Case studies of deep-learning techniques in healthcare
4.13 Challenges facing the deep- learning strategy in the healthcare world
4.14 Conclusion
References
Chapter 5 Enhancing access of the visually impaired through the smart cane
5.1 Introduction
5.2 Global statistics of disabilities faced by people
5.3 Global statistics of visual impairment
5.3.1 Visual impairment and blindness
5.3.2 Need for assistive technologies for people with a disability
5.4 Designing for people with visual disabilities
5.4.1 Using data that make a specific sound when a task is underway or accomplished
5.4.2 Adopting the Braille code
5.4.3 Using speech recognition
5.4.4 Using standard HTML to design websites
5.4.5 Using Screen Readers such as Job Access with Speech (JAWS)
5.4.6 Using auditory icons
5.4.7 CAPTCHA (Completely Automated Public Turing test to tell Computers and Humans Apart)
5.4.8 Website design
5.4.9 Use earcons
5.4.10 Zoom option
5.4.11 The bionic eye
5.5 Smart cane prototype for the visually impaired
5.5.1 Introduction to proximity sensors
5.6 Hardware required for a smart cane prototype
5.6.1 Infrared sensor
5.6.2 18650 double battery holder
5.6.3 V buzzer/mini speaker-PC mount
5.6.4 Cane/stick
5.6.5 18650 batteries
5.7 Circuit diagram for the proposed prototype (sensor-based smart cane)
5.7.1 Testing of infrared proximity sensor
5.7.2 Result of a working prototype
5.8 Conclusion and future work
References
Chapter 6 Contemporary role of edge-AI in IoT and IoE in healthcare and digital marketing
6.1 Introduction
6.2 Edge essentials
6.3 Edge devices
6.3.1 CPU-based edge devices
6.3.2 FPGA-based edge devices
6.3.3 GPU-based edge devices
6.4 Knowledge market in edge-AI-enabled IoT
6.4.1 Trusted authority (TA)
6.4.2 Edge-AI nodes
6.4.3 Knowledge aggregators
6.5 Safety and confidentiality concerns for edge-AI in digital advertising and healthcare in IoT/IoE environments
6.6 Conclusion and future scope
References
Chapter 7 Authentication of edge-AI-based smart healthcare system: A review-based study
7.1 Introduction
7.2 A detailed review: Edge-AI-based smart healthcare system
7.3 Conclusion
References
Chapter 8 Automated Wheelchair for the Physically Challenged with AIoT Modules
8.1 Introduction
8.2 Implications of COVID-19 on differently abled individuals
8.2.1 Obstacles faced during the pandemic to facilitate disabled
8.2.1.1 Barriers faced by people with disabilities
8.2.1.2 Impact of barriers, especially during pandemics, on people with disabilities
8.3 Technology in assisting the physically challenged
8.3.1 Aarogya Setu
8.3.2 Working of Aarogya Setu
8.3.3 Challenges faced by Aarogya Setu to assist quadriplegics
8.4 Importance of Artificial Intelligence of Things (AIoT) in healthcare
8.5 Revolutionizing healthcare using the Artificial Intelligence of Things (AIoT)
8.6 Dichotomy between the Internet of Things (IoT) and embedded systems
8.6.1 Embedded systems
8.6.2 The Internet of Things (IoT)
8.7 Future of Industry 4.0: smart wheelchair with AIoT
8.8 Modules common to the Automated Wheelchair and the Smart Wheelchair
8.9 Smart Wheelchair (SWC) modules
8.9.1 Social distancing module
8.9.2 EERG headsets and robotic arm module
8.9.3 Alexa assistant module
8.10 Conclusion and future work
Acknowledgment
References
Chapter 9 Comparison of machine-learning and deep-learning algorithms for stroke prediction
9.1 Introduction
9.2 Problem Statement
9.3 Literature Survey
9.4 Proposed model
9.4.1 Dataset description
9.4.2 Data preprocessing
9.4.3 Data visualisation
9.4.4 Data splitting
9.5 Classification algorithms
9.6 Smartwatch based on IoT
9.7 Experimental set-up
9.7.1 Result analysis
9.8 Conclusion
9.9 Future scope
References
Chapter 10 Edge computing-based containerized deep-learning approach for intrusion detection in healthcare IoT
10.1 Introduction
10.2 Background
10.2.1 Edge computing
10.2.2 Deep learning for IoT
10.2.3 Containerisation
10.3 Related work
10.4 Proposed edge computing-based IDS for healthcare IoT
10.4.1 Building deep-learning-based IDS at the cloud system
10.4.2 Containerising the built model at edge nodes
10.5 Conclusion and future work
References
Chapter 11 Human mental experience through chatbots: A thematical analysis of human engagement with evidence-based cognitive-behavioral techniques
11.1 Introduction
11.2 Literature review
11.3 Research problem and aim
11.4 Research methodology
11.4.1 Research design
11.4.2 Sample instrument
11.4.3 Sample
11.4.4 Data collection method
11.4.5 Data analysis
11.5 Data analysis and interpretation
11.6 Limitations and future scope
11.7 Conclusion
Data availability statement
References
Chapter 12 An early diagnosis of cardiac disease using feature-optimization-based deep neural network
12.1 Introduction
12.2 Literature survey
12.3 Proposed cardiac image-based automatic heart disease diagnosis model
12.3.1 Pre-processing
12.3.2 Feature extraction
12.3.3 Feature selection using the LPSO algorithm
12.3.4 Deep-neural-network-based heart disease prediction
12.4 Results and discussion
12.4.1 Evaluation metrics
12.4.2 Experimental results
12.4.3 Comparative analysis
12.4.3.1 Comparative analysis based on the classification algorithm
12.4.3.2 Comparative analysis based on feature selection algorithm
12.5 Conclusion
References
Chapter 13 Super-resolution in a world of scarce resources for medical imaging applications
13.1 Introduction
13.2 Super-resolution convolutional neural network (SRCNN) architectures
13.2.1 SRCNN
13.2.2 Fast SRCNN (FSRCNN)
13.2.3 Very deep SR convolutional networks (VDSR)
13.2.4 Deeply recursive convolutional networks (DRCN)
13.3 DL-based SR methods
13.4 Discussion and future work
13.5 Conclusion
REFERENCES
Chapter 14 Legal and ethical implications of edge-AI-enabled IoT healthcare monitoring systems
14.1 Introduction: Background and driving forces
14.2 Ethical debate on edge-AI-enabled IoT healthcare monitoring systems
14.3 Legal and regulatory challenges
14.3.1 Data protection
14.3.2 Liability regime
14.3.3 Consumer protection
14.3.4 Intellectual property
14.4 Policy recommendations
14.4.1 AI and law literacy
14.4.2 Standardisation
14.4.3 Research
14.5 Conclusion
References
Chapter 15 The prospective role of artificial intelligence in the development dynamic of healthcare sectors
15.1 Introduction
15.1.1 Healthcare types, services, sectors
15.1.2 The insufficiency of the healthcare system
15.1.3 Artificial intelligence
15.1.4 Expert system, NLP
15.1.5 ML-DL
15.1.6 Robotics
15.2 Transformation of Healthcare
15.2.1 Current trends in healthcare
15.2.1.1 Prediction of disease “data mining” with AI
15.2.1.2 AI in “medical imaging” for diagnosis
15.2.1.3 AI in “lifestyle management”
15.2.1.4 AI in “nutrition”
15.2.1.5 AI in emergency room and surgery
15.2.1.6 AI in hospital information system (HIS)
15.2.1.7 AI in research
15.2.1.8 AI in mental health
15.2.1.9 AI in pharma
15.2.1.10 AI in virtual assistant
15.2.1.11 Wearables with AI
15.2.2 Virtual and in-person services
15.2.3 Advanced precision medicine
15.2.4 Remote monitoring
15.2.5 AI adaptation
15.3 ML/DL in healthcare
15.3.1 Different techniques used by ML
15.3.2 Deep-learning architectures in the healthcare sector
15.4 Robotics in healthcare
15.5 Monitoring health through wearables and personal devices
15.5.1 Promotes preventive healthcare
15.5.2 Ensures patient engagement
15.5.3 Monitors patients who are at risk
15.5.4 Enhance patient satisfaction and care
15.5.5 Benefits for employers and healthcare providers
15.6 Revolutionising clinical decision-making with AI
15.7 Conclusion
References
Chapter 16 Edge-AI-empowered blockchain: A game-changer for the medical tourism industry
16.1 Introduction
16.2 What is medical tourism?
16.3 Categories of medical tourism
16.3.1 International medical tourism
16.3.2 Domestic/intra-country-bound medical tourism
16.4 Medical tourism: Pre- and post-pandemic
16.5 Mapping the market for medical travelers
16.6 Market players in medical tourism
16.7 Blockchain concept
16.8 Blockchain in medical tourism: Scope, role, and impact
16.9 Blockchain technologies for the medical tourism ecosystem
16.10 Edge-AI-empowered blockchain
16.11 Conclusion
References
Chapter 17 System for secure edge healthcare monitoring based on artificial intelligence
17.1 Introduction
17.2 Application of edge-AI in the healthcare sector
17.2.1 Autonomous hospital room monitoring
17.2.2 New radiology applications
17.2.3 Rural health
17.3 Relevant work
17.4 Security of edge-based AI systems
17.5 IoT healthcare monitoring system with edge-AI
17.6 Conclusion
References
Index