Implementation of Smart Healthcare Systems using AI, IoT, and Blockchain

Cover
Implementation of Smart Healthcare Systems using AI, IoT, and Blockchain
Copyright
List of contributors
Contents
Preface
1 Internet of medical things for enhanced smart healthcare systems
1.1 Introduction
1.2 Artificial intelligence-enabled Internet of medical things
1.3 Applications of artificial intelligence in enabled Internet of medical things
1.3.1 Disease diagnosis
1.3.2 Prediction and forecasting
1.3.3 Monitoring system
1.3.4 Personalized treatment
1.4 Challenges of artificial intelligence-enabled Internet of medical things
1.5 Case study for the application of Internet of medical of things-based enabled artificial intelligence for the diagnosis...
1.5.1 Fuzzy logic
1.5.2 Fuzzification
1.6 Conclusions
References
Further reading
2 Sensor and actuators for smart healthcare in post-COVID-19 world
2.1 Introduction
2.2 Sensors for smart healthcare
2.2.1 Radio-frequency identification
2.2.2 Wireless sensor network
2.2.3 Near field communication
2.2.4 Zigbee
2.2.5 Z-wave
2.2.6 Bluetooth low energy
2.3 Actuators for smart healthcare
2.4 Sensors and actuators implementation for smart healthcare
2.4.1 Master patient index
2.4.2 Insurance eligibility system
2.4.3 Appointment scheduling
2.4.4 Nursing application
2.4.5 Pharmacy application
2.4.6 Laboratory information system
2.4.7 Imaging applications or picture archiving and communication system
2.4.8 Imaging application
2.4.9 Billing system
2.4.10 Enterprise resource planning
2.4.11 Electronic medical records
2.4.12 Computerized physician order entry
2.4.13 Clinical decision support systems
2.4.14 Health information exchange
2.5 Internet of things in the healthcare system
2.6 Smart healthcare system design and implementation
2.6.1 Process design
2.6.2 Database design
2.6.3 Artificial neural network design for screening process
2.6.4 Read data from RS-232 and RS-423
2.6.5 Read data from electronic data capture
2.7 General potential ICT risks IN healthcare services
2.8 Results and discussions
2.9 Conclusions
References
3 Voice signal-based disease diagnosis using IoT and learning algorithms for healthcare
3.1 Introduction
3.2 A prologue for analysis of voice signals
3.3 Extraction of parameters from voice signal
3.3.1 Formants
3.3.2 Mel-frequency cepstral coefficients
3.3.3 Signal energy
3.3.4 Pitch
3.3.4.1 Mean pitch
3.3.4.2 Zero-crossing rate
3.4 Classifiers for voice analysis
3.4.1 Gaussian mixture model
3.4.2 Vector quantization systems
3.4.3 Support vector machine
3.4.4 K-means clustering
3.4.5 Artificial neural networks
3.4.6 Multilayer perceptron
3.4.7 Convolutional support vector machine
3.5 Processing of voice signal
3.6 Internet of things–based healthcare sector
3.7 Detection of age and identification of gender using voice signal
3.8 Recognition of emotions through voice signal
3.9 Disease diagnosis using voice signal
3.10 Results and discussion
3.11 Conclusion
References
4 Intelligent and sustainable approaches for medical big data management
4.1 Introduction
4.1.1 Artificial intelligence and Internet of things/IoTM in healthcare
4.1.2 Contribution
4.1.3 Related work
4.1.4 Motivation
4.2 Method
4.2.1 Data
4.2.2 Data management
4.2.3 Data security
4.2.3.1 Security by Kerberos
4.2.3.2 Cloud environment
4.2.4 Data analytics
4.2.4.1 Automated machine learning
4.2.4.2 Working of automated machine learning
4.2.4.3 Basic framework
4.2.4.4 Model selection
4.3 Case study
4.4 Surveillance machine learning healthcare model development
4.5 Result and discussion
4.5.1 Analysis of security issues in the surveillance machine learning health care model
4.5.2 Sustainability of work
4.6 Pros and cons of model
4.7 Application
4.8 Conclusion
4.9 Future scope
References
5 A predictive method for emotional sentiment analysis by machine learning from electroencephalography of brainwave data
5.1 Introduction
5.2 Review of literatures
5.3 Materials and methods
5.3.1 Muse headband
5.3.2 Features selection
5.3.3 Datasets
5.3.3.1 Feature selection algorithms
5.3.3.1.1 Symmetric uncertainty
5.3.4 Artificial intelligence process
5.3.4.1 Contribution of the present research
5.3.4.2 XG Boost
5.3.4.3 Random forest
5.3.4.4 Decision tree
5.4 Result analysis and discussion
5.4.1 Confusion matrix
5.4.2 Execution time
5.4.3 Misclassified samples
5.4.4 Receiver operating curve
5.5 Conclusion and future scope
5.6 Ethical statement
5.7 Conflicts of interest
References
6 Role of artificial intelligence and internet of things based medical diagnostics smart health care system for a post-COVI...
6.1 Introduction
6.2 Challenges
6.3 Smart cardiac monitoring system
6.3.1 Mobile machine learning model
6.3.2 Artificial neural network based diagnostics
6.4 Smart glucose monitoring system
6.4.1 Continuous glucose monitoring system
6.4.2 Mid 20 model
6.5 Smart kidney monitoring system
6.5.1 Real-time monitoring of glomerular filtration rate
6.5.2 Contrast-enhanced ultrasound and other techniques
6.6 Result and discussion
6.7 Future work for monitoring system on pranayama (breathing system)
6.8 Conclusion
References
7 Windowed modified discrete cosine transform based textural descriptor approach for voice disorder detection
7.1 Introduction
7.2 Related works
7.3 Proposed methodology
7.4 Feature extraction and selection
7.4.1 Windowed modified discrete cosine transform
7.4.2 Completed local binary pattern
7.4.3 Local phase quantization
7.5 Experimental results and discussions
7.6 Current trends and future scope
7.7 Conclusion
References
8 Internet of medical things for abnormality detection in infants using mobile phone app with cry signal analysis
8.1 Introduction
8.1.1 Organization of the chapter
8.1.2 Significance of the proposed technology
8.2 Literature survey
8.3 Objectives
8.4 Major contribution
8.5 Gaps identified
8.6 Materials and methods
8.6.1 Classification of deep learning algorithms
8.6.2 Convolutional neural network
8.7 Results and discussion
8.7.1 Baby’s cry signal collection
8.7.2 Methodology—signal processing technique for analysis of baby’s cry signal
8.7.3 Principle of operation
8.7.4 Preprocessing
8.7.5 Feature extraction using wavelet transform
8.7.6 Identification using convolutional neural network
8.7.7 Development of mobile app
8.7.8 Extraction of wavelet coefficients
8.8 Conclusion and future scope
References
9 Internet of things based effective wearable healthcare monitoring system for remote areas
9.1 Introduction
9.2 Parameters of healthcare monitoring
9.2.1 Physiological parameters
9.2.1.1 Body temperature
9.2.1.2 Pulse rate
9.2.1.3 Blood pressure
9.2.1.4 Electrocardiogram
9.2.1.4.1 The heart’s pressures and volumes
9.2.1.4.2 Heart attack and heart-related issues
9.2.1.5 Electroencephalogram
9.2.1.5.1 Nominal range of brain function tests
Cerebral blood flow
Stroke and brain related issues
9.2.1.6 Kidney disease
9.3 Types of physiological parameters measurement
9.4 Related work
9.5 Hardware and software requirements
9.5.1 Hardware requirements
9.5.2 Software requirements
9.6 Need for wearable sensors
9.6.1 Sensors for health monitoring
9.6.2 Sensors needed for health monitoring and rehabilitation
9.6.3 Sensors in continuous health monitoring and medical assistance in home
9.6.4 Sensors in physical rehabilitation
9.6.5 Assistive systems
9.7 Proposed system
9.7.1 Working principle
9.7.2 Hardware components
9.7.2.1 ARM microcontroller—LPC2148 microcontroller
9.7.2.1.1 Features of LPC2148
9.7.2.2 ESP32 processor
9.7.2.3 Heartbeat sensor
9.7.2.4 Heart rate monitor kit with AD8232 electrocardiography sensor module
9.7.2.5 Body temperature sensor (LM35)
9.7.2.6 Room temperature sensor (DHT11)
9.7.2.7 CO sensor (MQ-9)
9.7.2.8 CO2 sensor (MQ-135)
9.8 Results and discussion
9.9 Conclusion and future scope
References
10 Blockchain for transparent, privacy preserved, and secure health data management
10.1 Introduction
10.2 Preliminaries
10.2.1 Security and privacy-preserving on big data
10.2.2 Blockchain
10.3 Artificial intelligence for enhanced healthcare systems
10.4 Blockchain for privacy-preserving on healthcare data
10.5 Consensus algorithms on Blockchain for privacy-preserving on healthcare data
10.6 Using Blockchain for privacy-preserving in data storage phase
10.7 Using Blockchain for privacy-preserving on data sharing
10.8 Blockchain for transparency in healthcare data
10.9 Some exposed models using Blockchain for privacy-preserving and transparency on healthcare data
10.10 Blockchain as an overlay network
10.11 Using multiple blockchain for privacy-preserving on healthcare systems
10.12 Using Blockchain to manage sharing data mining result
10.13 Anonymity contact tracing model using Blockchain-based mechanism
10.14 Using adaptive blockchain-based mechanism to preserve privacy in emergency situations
10.15 Comparing proposed model with similar research
10.16 Conclusions
References
11 Security and privacy concerns in smart healthcare system
11.1 Introduction
11.2 Smart healthcare system
11.2.1 Applications of smart healthcare system
11.2.2 Risks of using the internet of things in smart healthcare system
11.3 Security and privacy threats in smart healthcare system
11.3.1 Mode of distribution
11.3.2 Mobile devices for health services
11.3.3 Unintentional misconduct
11.3.3.1 Insider abuse
11.3.4 Data integrity attack
11.3.5 Denial of service attack
11.3.6 Fingerprint and timing-based snooping
11.3.7 Router attack
11.3.8 Select forwarding attack
11.3.9 Sensor attack
11.3.10 Replay attack
11.3.10.1 Security problem in radio frequency identification
11.3.11 Distributed denial of service attacks
11.4 Security and privacy solution in smart healthcare system
11.4.1 Biometrics
11.4.2 TinySec
11.4.3 ZigBee services security
11.4.4 Bluetooth protocols security
11.4.5 Elliptic curve cryptography
11.4.6 Encryption techniques
11.4.7 Hardware encryption
11.5 Security and privacy requirements in smart healthcare system
11.6 Practical application of a secure medical data using a TEA encryption algorithm
11.7 Conclusion and future directions
References
Index