Intelligent Internet of Things: From Device to Fog and Cloud

Preface
Acknowledgments
Contents
Part I IoT Building Blocks
	1 IoT Fundamentals: Definitions, Architectures, Challenges, and Promises
		Contents
		1.1 What Is IoT
			1.1.1 Internet of Things Terms and Acronyms
			1.1.2 Impact of IoT
			1.1.3 Benefits of IoT
			1.1.4 IoT Challenges
			1.1.5 IoT and Big Data
			1.1.6 IoT and Cloud Computing
			1.1.7 IoT and Digitalization
			1.1.8 IoT and Industry 4.0
		1.2 Architectures and Reference Models of IoT: A Layard View
			1.2.1 IoTWF Reference Model of IoT
			1.2.2 Simplified Reference Model of IoT
		1.3 IoT Frameworks and Platforms
			1.3.1 FIWARE
			1.3.2 SmartThings
			1.3.3 AWS IoT
			1.3.4 Microsoft Azure IoT
				1.3.4.1 Azure Internet of Things (IoT) Hub
				1.3.4.2 Azure IoT Edge
				1.3.4.3 Azure Stream Analytics
				1.3.4.4 Azure Machine Learning
				1.3.4.5 Azure Logic Apps
		1.4 IoT Applications in Vertical Markets
			1.4.1 Smart Agriculture
			1.4.2 Logistics and Transportation
			1.4.3 Smart Grid
			1.4.4 Smart Building
			1.4.5 Smart Factory
				1.4.5.1 Current Manufacturing Model
				1.4.5.2 Potential Use Cases
				1.4.5.3 Major Challenges
			1.4.6 Smart City
				1.4.6.1 Smart City Layers
				1.4.6.2 Applications of IoT in Smart City
				1.4.6.3 Examples of Smart City
		1.5 IoT Business Implications and Opportunities
			1.5.1 Component Supplier: Component Business
			1.5.2 Complete Solution and Product Provider: Additional Revenue
			1.5.3 IoT Customer: Optimization and Cost Reduction
			1.5.4 Important Aspects of Implementation
			1.5.5 Data Monetization
			1.5.6 Business Model
			1.5.7 Minimum Viable Product (MVP)
		1.6 Summary
		References
	2 The Smart “Things” in IoT
		Contents
		2.1 Definition and Architecture of Smart Things
		2.2 Sensors
		2.3 Actuators
			2.3.1 Switches and Relays
			2.3.2 Electrical Motors
		2.4 Processing Unit: Microcontroller
			2.4.1 Classifications of Microcontrollers
				2.4.1.1 Classification by Bus-Width (Number of Bits)
				2.4.1.2 Classification by Instruction Set (RISC vs CISC)
				2.4.1.3 Classification by Memory Structure and Bus Architecture
				2.4.1.4 Classification by IO
			2.4.2 Three Main Types of Microcontrollers
				2.4.2.1 Peripheral Interface Controller (PIC) Microcontrollers
				2.4.2.2 AVR Microcontrollers
				2.4.2.3 ARM Microcontrollers
		2.5 ARM Microcontrollers
			2.5.1 Background
			2.5.2 Architecture
			2.5.3 GPIOs and Interfaces
				2.5.3.1 General-Purpose Input/Output (GPIO)
				2.5.3.2 Analog Inputs
				2.5.3.3 Analog Outputs
				2.5.3.4 Parallel Interfaces vs Serial Interfaces
				2.5.3.5 Universal Asynchronous Receiver/Transmitter (UART)
				2.5.3.6 Serial Peripheral Interface (SPI)
				2.5.3.7 I2C (Inter-integrated Circuit)
				2.5.3.8 Universal Synchronous Asynchronous Receiver Transmitter (USART)
				2.5.3.9 RS232 and RS422
			2.5.4 Clock Tree
			2.5.5 Interrupts
			2.5.6 Addressing Modes
			2.5.7 Timers
			2.5.8 Low-Power Modes
			2.5.9 Programming and Debugging Techniques
				2.5.9.1 JTAG/SWD
				2.5.9.2 Bootloader
			2.5.10 Real-Time Operating System (RTOS)
		2.6 Summary
		References
	3 Engineering IoT Networks
		Contents
		3.1 IoT Network Scenarios
		3.2 The Simplified ISO/OSI Reference Model and IoT
			3.2.1 Fundamental Terminology
				3.2.1.1 Network Nodes
				3.2.1.2 Links and Topologies
				3.2.1.3 Quality of Service
				3.2.1.4 Network Size
				3.2.1.5 Communication Patterns
			3.2.2 The ISO/OSI Layers
				3.2.2.1 Application Layer
				3.2.2.2 Transport Layer
				3.2.2.3 Network Layer
				3.2.2.4 Data Link Layer
				3.2.2.5 Physical Layer
			3.2.3 Standardization Bodies
				3GPP
				ITU
				IEEE
				ISO
				ETSI
				IETF
			3.2.4 IoT Network Standards and the Simplified ISO/OSI Model
		3.3 IoT Network Technologies and Standards
			3.3.1 Modbus
			3.3.2 Near-Field Communication (NFC)
			3.3.3 Bluetooth
				3.3.3.1 Bluetooth Versions
				3.3.3.2 Bluetooth Protocols and Profiles
			3.3.4 IEEE 802.15.4
			3.3.5 ZigBee
			3.3.6 ZigBee IP
			3.3.7 WirelessHART
			3.3.8 Wi-Fi (IEEE 802.11 Family)
			3.3.9 LoRaWAN
			3.3.10 Sigfox
			3.3.11 Z-Wave
			3.3.12 Wireless M-Bus
			3.3.13 Optical Wireless Communications
			3.3.14 6LoWPAN
			3.3.15 Thread
			3.3.16 ISA100.11a
			3.3.17 Cellular Network Standards
				3.3.17.1 Second Generation (2G)
				3.3.17.2 Third Generation (3G)
				3.3.17.3 Fourth Generation (4G)
				3.3.17.4 NB-IoT
				3.3.17.5 LTE Cat M1
				3.3.17.6 Fifth Generation (5G)
		3.4 Application Layer Protocols
			3.4.1 HyperText Transfer Protocol (HTTP)
			3.4.2 WebSocket
			3.4.3 Web Services and Representational State Transfer (REST)
			3.4.4 Message Queuing Telemetry Transport (MQTT)
				3.4.4.1 How MQTT Works
			3.4.5 Advanced Message Queuing Protocol (AMQP)
			3.4.6 Constrained Application Protocol (CoAP)
				3.4.6.1 CoAP Request/Response Model
			3.4.7 Extensible Messaging and Presence Protocol (XMPP)
			3.4.8 OPC Unified Architecture (OPC-UA)
		3.5 IoT Network Design Methodology
			3.5.1 Communications for Localization
		3.6 Summary
		References
	4 Architecting IoT Cloud
		Contents
		4.1 The IoT Cloud
		4.2 Fundamentals of Cloud Computing
			4.2.1 Cloud Computing Key Characteristics
			4.2.2 Service Models
			4.2.3 Deployment Models
		4.3 Device Management Layer
			4.3.1 Provisioning
			4.3.2 Software Updates and Maintenance
			4.3.3 Monitoring and Control
		4.4 Data Ingestion Layer
			4.4.1 Data Ingestion Frameworks
				4.4.1.1 Apache Flume
				4.4.1.2 Apache Kafka
				4.4.1.3 Apache Nifi
				4.4.1.4 Elastic Logstash
		4.5 Data Processing Layer
			4.5.1 Data Processing Architectures
				4.5.1.1 Lambda Architecture
				4.5.1.2 Kappa Architecture
			4.5.2 Data Processing Frameworks
				4.5.2.1 Apache Storm
				4.5.2.2 Apache Flink
				4.5.2.3 Apache Spark
		4.6 Data Storage Layer: A Hybrid Architecture
			4.6.1 Database
				4.6.1.1 MongoDB
				4.6.1.2 Cassandra
				4.6.1.3 Redis
				4.6.1.4 InfluxDB
				4.6.1.5 Elasticsearch
				4.6.1.6 Which Database Is Right for Your IoT Project?
				4.6.1.7 CAP Theorem
			4.6.2 Data Warehouse
			4.6.3 Data Lake
				4.6.3.1 ETL (Extract, Transform, and Load) and ELT (Extract, Load, and Transform)
				4.6.3.2 Challenges of Data Lakes
				4.6.3.3 Distributed File Systems
				4.6.3.4 Data Lake Tiers
		4.7 Application Layer
			4.7.1 Microservice Architecture Pattern
				4.7.1.1 API Gateway
				4.7.1.2 Service Invocation
				4.7.1.3 Service Discovery
				4.7.1.4 Service Registry
				4.7.1.5 Deployment Strategy
		4.8 Data Visualization and Reporting Layer
			4.8.1 Data Visualization Frameworks
			4.8.2 Business Intelligence Frameworks
			4.8.3 Advanced Data Analytical and Machine Learning Frameworks
			4.8.4 Load Balancing
		4.9 Orchestration Layer
		4.10 Virtualization
			4.10.1 Main Categories of Virtualization
			4.10.2 Behind the Scene of FaaS: OpenWhisk
		4.11 Scaling
			4.11.1 Vertical Scaling (Scale-Up)
			4.11.2 Horizontal Scaling (Scale-Out or Clustering)
		4.12 A Paradigm Shift from Cloud to Fog Computing
		4.13 Summary
		References
	5 Machine Learning for IoT
		Contents
		5.1 Fundamental of Machine Learning
			5.1.1 Fundamental Terminologies
			5.1.2 Review of Probability Theory
				5.1.2.1 Random Variable
				5.1.2.2 Distribution
				5.1.2.3 Mean, Variance, and Covariance
			5.1.3 Review of Linear Algebra
			5.1.4 Supervised and Unsupervised Learning
				5.1.4.1 Supervised Learning
				5.1.4.2 Unsupervised Learning
			5.1.5 Machine Learning in IoT
			5.1.6 Machine Learning Flow
				5.1.6.1 Overall Flow of Machine Learning Projects
				5.1.6.2 Data Preparation
		5.2 Regression Analysis
			5.2.1 Linear Regression
			5.2.2 Regularization in Linear Regression
				5.2.2.1 Geometric Interpretations of Regularization
				5.2.2.2 Elastic Net Regularization
			5.2.3 Bayesian Linear Regression
		5.3 Feature Selection
			5.3.1 Feature Selection Techniques
				5.3.1.1 Chi-Square Test
				5.3.1.2 Pearson Correlation
				5.3.1.3 Entropy
			5.3.2 Feature Extraction
		5.4 Classification
			5.4.1 Measuring Performance for Classification Problems
				5.4.1.1 Confusion Matrix (Error Matrix)
				5.4.1.2 Performance Metrics
			5.4.2 Over- and Undersampling
			5.4.3 K-Nearest Neighbor (KNN)
			5.4.4 Logistic Regression
				5.4.4.1 Logit and Sigmoid (Logistic) Functions
				5.4.4.2 Decision Boundary (Decision Surface)
				5.4.4.3 Cost Function in Logistic Regression
			5.4.5 Support Vector Machine
			5.4.6 Decision Tree Classifier
			5.4.7 Ensembles
				5.4.7.1 Bootstrap Aggregating (Bagging)
				5.4.7.2 Random Forest
				5.4.7.3 Boosting
		5.5 Dimensionality Reduction
		5.6 Artificial Neural Networks
			5.6.1 Neural Network Models
			5.6.2 Train a Neural Network Model
			5.6.3 Activation Function
			5.6.4 Softmax Function
			5.6.5 Convolution Neural Networks
				5.6.5.1 Convolution Layer
				5.6.5.2 Stride
				5.6.5.3 Padding
				5.6.5.4 Pooling Layers
				5.6.5.5 Fully Connected Layer
				5.6.5.6 Well-Known CNN Architectures
		5.7 Clustering
			5.7.1 K-Means Clustering
			5.7.2 Hierarchical Clustering
		5.8 Summary
		References
	6 Big Data
		Contents
		6.1 Introduction to Big Data
			6.1.1 Defining Big Data
			6.1.2 Volume
			6.1.3 Velocity
			6.1.4 Variety
			6.1.5 Veracity
		6.2 Big Data Management and Computing Platforms
			6.2.1 Big Data System Architecture Components
			6.2.2 Hadoop History
			6.2.3 The Apache Hadoop Framework Components
			6.2.4 Hadoop Distributed File System
				6.2.4.1 Overview of Data Formats
			6.2.5 MapReduce
			6.2.6 YARN
		6.3 An Introduction to Big Data Modeling and Manipulation
			6.3.1 Big Table
			6.3.2 Pig
			6.3.3 Sqoop
			6.3.4 Hive
			6.3.5 HBase
			6.3.6 Oozie
			6.3.7 Zookeeper
			6.3.8 Data Lakes and Warehouses
		6.4 An Introduction to Spark: An Innovative Paradigm in Big Data
			6.4.1 The Spark Ecosystem
			6.4.2 The Core Difference Between Spark and Hadoop
			6.4.3 Resilient Distributed Datasets in Spark
			6.4.4 RDD Transformations and Actions
			6.4.5 Datasets and DataFrames in Spark
			6.4.6 The Spark Processing Engine
			6.4.7 Spark Components
			6.4.8 Spark SQL
			6.4.9 Spark DataFrames
			6.4.10 Creating a DataFrame
				6.4.10.1 Example of Reading DataFrame from the Parquet File
			6.4.11 DataFrame Operations
			6.4.12 Spark MLlib
			6.4.13 MLlib Capabilities
			6.4.14 Spark Streaming
			6.4.15 Intro to Batch and Stream Processing
			6.4.16 Spark Streaming
			6.4.17 Spark Functionality
		6.5 Big Data Analytics: Building the Data Pipeline
			6.5.1 Developing Predictive and Prescriptive Models
			6.5.2 The Cross Industry Standard Process for Data Mining (CRISP-DM)
		6.6 Conclusion
		References
	7 Intelligent and Connected Cyber-Physical Systems: A Perspective from Connected Autonomous Vehicles
		Contents
		7.1 Introduction
		7.2 Background
			7.2.1 Cyber Components
			7.2.2 Physical Components
			7.2.3 Cyber and Physical Interactions
		7.3 Case Studies
			7.3.1 Assuring the Safety of Machine Learning-Based Perception for Highly Automated Driving
				7.3.1.1 Introduction
				7.3.1.2 Safety Requirements on the Machine Learning Function
				7.3.1.3 Causes of Functional Insufficiencies in Machine Learning
				7.3.1.4 Sources of Evidence and Structuring the Assurance Case
				7.3.1.5 Summary
			7.3.2 Assuring the Security and Robustness of Connected Vehicle Applications
				7.3.2.1 Introduction
				7.3.2.2 Security Challenges in Connected Vehicle Applications
				7.3.2.3 Key Management System
				7.3.2.4 Intrusion Detection System
				7.3.2.5 System Integration
				7.3.2.6 Summary
		7.4 Concluding Remarks
		References
	8 Distributed Ledger Technology
		Contents
		8.1 Introduction to Distributed Ledger Technology and IoT
			8.1.1 What Is a Distributed Ledger?
			8.1.2 Blockchain
			8.1.3 Types of Blockchain
				8.1.3.1 Permissionless Blockchains
				8.1.3.2 Permissioned Blockchains
			8.1.4 Directed Acyclic Graph (DAG)
			8.1.5 Hybrid DLTs Based on Blockchains and DAGs
			8.1.6 Internet of Things (IoT)
		8.2 Benefits of DLTs
			8.2.1 Blockchain Benefits
			8.2.2 DAG Benefits
		8.3 How Blockchain Works
			8.3.1 Transaction, Block, Ledger, and Blockchain
			8.3.2 Transaction Validation and Block Mining
			8.3.3 Smart Contracts
			8.3.4 Consensus Algorithms
				8.3.4.1 Proof-of-Work (PoW)
				8.3.4.2 Proof-of-Stake (PoS)
				8.3.4.3 Delegated Proof-of-Stake (DPoS)
				8.3.4.4 Practical Byzantine Fault Tolerance (PBFT)
				8.3.4.5 IOTA
		8.4 Directed Acyclic Graph (DAG)
			8.4.1 What Is a DAG
			8.4.2 How IOTA Tangle Works
		8.5 DAG Versus Blockchain
		8.6 Blockchain and Internet of Things
			8.6.1 Internet of Things
			8.6.2 Weaknesses of Internet of Things
			8.6.3 Blockchains and IoT
			8.6.4 How to Combine Blockchains and IoT
		8.7 Prominent Enterprise DLT Platforms
			8.7.1 Hyperledger Fabric
			8.7.2 Ethereum
			8.7.3 IOTA
		8.8 Applications of Blockchain
			8.8.1 Financial Services
			8.8.2 Healthcare
			8.8.3 Energy
			8.8.4 Identity Management
			8.8.5 Supply Chain Management
			8.8.6 Other Applications
		8.9 Other Aspects of DLTs
			8.9.1 Scalability and Other Practical Considerations
				8.9.1.1 Bitcoin
				8.9.1.2 Hyperledger Fabric
				8.9.1.3 Ethereum
				8.9.1.4 IOTA
				8.9.1.5 Scalability of DLTs
			8.9.2 Token and Token Economics
		8.10 Vulnerabilities of Blockchain
		8.11 Summary
		References
	9 Emerging Hardware Technologies for IoT Data Processing
		Contents
		9.1 Challenges for Data Processing in the Era of IoT
			9.1.1 IoT System Architecture
			9.1.2 Energy Efficiency as a Paramount Concern
			9.1.3 Bandwidth Limitation for Big Data Processing
		9.2 Recent Innovations for Bandwidth and Energy
			9.2.1 Heterogeneous Computing
			9.2.2 In-Package Die Stacking
			9.2.3 Emerging Memory Technologies
			9.2.4 Machine Learning Accelerators in the IoT Era
			9.2.5 Approximate Computing
		9.3 Near-Memory Processing
		9.4 In Situ Processing for IoT Devices
			9.4.1 Deep Binary Neural Network
			9.4.2 The MB-CNN Architecture
			9.4.3 Memristive XNOR Convolution
				9.4.3.1 Computing XNOR Within RRAM Crosspoint
				9.4.3.2 In Situ Bit-Counting
			9.4.4 The MB-CNN Architecture
				9.4.4.1 MB-CNN Chip Control
				9.4.4.2 Bank Organization
				9.4.4.3 Array Structure
				9.4.4.4 Data Organization
			9.4.5 Potentials of the MB-CNN Accelerator
		9.5 In Situ Data Clustering for IoT Servers
			9.5.1 Data Clustering
			9.5.2 Applications of Data Clustering
				9.5.2.1 Gene Expression Analysis
				9.5.2.2 Document Clustering
			9.5.3 Data Clustering with Rank-Order Filters
				9.5.3.1 Bit-Serial Median Filter
			9.5.4 Memristive k-Median Clustering
				9.5.4.1 The MISC Architecture
				9.5.4.2 The Design Principles for MISC
			9.5.5 MISC Building Blocks
				9.5.5.1 Memory Cell
				9.5.5.2 Analog Bit Counter and Reduction Network
				9.5.5.3 MISC Array Organization
				9.5.5.4 MISC Data Representation
				9.5.5.5 Handling Even Number of Data Points
			9.5.6 Potentials of the MISC Accelerator
		References
	10 IoT Cyber Security
		Contents
		10.1 Introduction
		10.2 A Complex Threat Environment
			10.2.1 Threat Actors and Risk Likelihood
			10.2.2 Threat Types
		10.3 Cyber Security Controls for IoT Systems
			10.3.1 Establishing a Secure IoT System Development Methodology
				10.3.1.1 Threat Modeling an IoT System
				10.3.1.2 Documenting Cyber Security Requirements
				10.3.1.3 Establishing a Cyber Security Culture
				10.3.1.4 Conducting Code Audits and Automating Processes
				10.3.1.5 Gaining Visibility into Your Supply Chain
				10.3.1.6 Working with the Security Research Community
			10.3.2 Integrating Safety and Security Engineering
			10.3.3 Safeguarding Stakeholder Privacy
		10.4 Securing the IoT Edge
			10.4.1 Use a Hardware Security Element to Support Trusted Operations
			10.4.2 Configure a Secure Real-Time Operating System
			10.4.3 Implement Physical Security Controls
			10.4.4 Deploy Confidentiality Protections
			10.4.5 Implement Strong Authentication and Access Controls
				10.4.5.1 Authorization and Access Control
			10.4.6 Harden Network Services
			10.4.7 Implement Logging and Behavioral Analytics
			10.4.8 Implement Framework Security
		10.5 A Secure Network
			10.5.1 Secure Wireless Sensor Network (WSN) Configuration
			10.5.2 Segment the Network
			10.5.3 Implement Zero-Trust/Software-Defined Perimeter
			10.5.4 Protect the Perimeter
			10.5.5 Secure Discovery Services
			10.5.6 Implement Asset Management
			10.5.7 Implement Vulnerability Tracking
			10.5.8 Audit and Monitoring
			10.5.9 Vulnerability Scanning
			10.5.10 Penetration Testing
		10.6 A Secure Cloud
			10.6.1 Evaluate the Security of the CSP
			10.6.2 Design the Cloud Service to be Resilient and Available
			10.6.3 Securely Configure the Cloud Network
			10.6.4 Apply Encryption to Cloud Communications
			10.6.5 Manage Cloud Identities
			10.6.6 Require Multi-Factor Cloud Authentication
			10.6.7 Audit Cloud Services
			10.6.8 Monitor the Cloud
			10.6.9 Implement Cloud Identity Management
			10.6.10 Use Zero-Touch Provisioning
			10.6.11 Role-Based Access Controls
			10.6.12 Secure Data in the Cloud
			10.6.13 Secure Web Services
		10.7 Secure System Users and Administrators
			10.7.1 User Training
			10.7.2 Administrator Training
			10.7.3 Incident Response Planning
		10.8 Conclusion
		References
Part II IoT Technologies for Smart Healthcare
	11 Healthcare IoT
		Contents
		11.1 Modern Healthcare Challenges
		11.2 What Is IoT-Driven Healthcare: Transitioning from Hospital-Centric to Patient-Centric
		11.3 Benefits of Adopting IoT Healthcare
		11.4 Fog-Driven IoT Healthcare Architecture: A Layered View
			11.4.1 Things Layer
			11.4.2 Network Layer
			11.4.3 Cloud Layer
		11.5 Key Services and Applications of IoT Healthcare
			11.5.1 Mobile Health (m-Health)
			11.5.2 IoT in Ambient Assisted Living
			11.5.3 IoT Medication
			11.5.4 IoT to Assist Individuals with Disabilities or Special Needs
			11.5.5 Smart Medical Implants
			11.5.6 IoT for Early Warning Score (EWS)
			11.5.7 IoT-Based Anomaly Detection
			11.5.8 Population Health Management
		11.6 Major Challenges of IoT Healthcare
			11.6.1 Interoperability, Standardization, and Regulation
			11.6.2 Heterogeneity
			11.6.3 Interfaces and Human Factor Engineering
			11.6.4 Scalability
			11.6.5 Power Consumption
			11.6.6 Intrusiveness
			11.6.7 Design Automation Challenges
			11.6.8 Data Management
			11.6.9 Context Awareness
			11.6.10 Availability and Reliability
			11.6.11 Data Transmission
			11.6.12 Security and Privacy
		11.7 Case Study: Collaborative Machine Learning-Driven Healthcare Internet of Things
		11.8 Summary
		References
	12 Biomedical Engineering Fundamentals
		Contents
		12.1 Introduction of Bioelectricity and Biomechanics
		12.2 Biosensors
			12.2.1 Temperature Sensors
				12.2.1.1 Thermocouple
				12.2.1.2 Thermistor
				12.2.1.3 Diode Temperature Sensor
				12.2.1.4 Transistor Temperature Sensor
			12.2.2 Light Sensors
				12.2.2.1 Photoresistor
				12.2.2.2 Photodiode
				12.2.2.3 Phototransistor
			12.2.3 Spectrophotometry
			12.2.4 Fluorescence
			12.2.5 Immunosensors
		12.3 Basics of Signals and Systems
			12.3.1 Types of Signals
				12.3.1.1 Continuous, Discrete Time, and Digital Signals
				12.3.1.2 Periodic and Aperiodic Signals
				12.3.1.3 Deterministic and Random Signals
				12.3.1.4 Even and Odd Signals
				12.3.1.5 Energy and Power Signals
			12.3.2 Types of Systems
				12.3.2.1 Linear and Nonlinear Systems
				12.3.2.2 Time-Invariant and Time-Variant Systems
				12.3.2.3 Linear Time-Invariant and Linear Time-Variant Systems
				12.3.2.4 Static and Dynamic Systems
				12.3.2.5 Causal and Noncausal Systems
				12.3.2.6 Invertible and Non-invertible Systems
				12.3.2.7 Stable and Unstable Systems
			12.3.3 Signal Acquisition
			12.3.4 Time- and Frequency-Domain Representations
			12.3.5 Finite Impulse Response (FIR) and Infinite Impulse Response (IIR) Filters
		12.4 Types of Biomedical Signals
			12.4.1 Electroencephalogram (EEG)
			12.4.2 Electrocardiogram (ECG)
			12.4.3 Electromyogram (EMG)
			12.4.4 Electrooculogram (EOG)
			12.4.5 Magnetoencephalogram (MEG)
			12.4.6 Other Biomedical Signals
		12.5 Physiological Phenomena and Biomedical Signals
			12.5.1 Vital Phenomena and Their Parameters
				12.5.1.1 Heartbeat
				12.5.1.2 Respiration
				12.5.1.3 Blood Circulation
				12.5.1.4 Blood Oxygenation
				12.5.1.5 Body Temperature
			12.5.2 Parameter Behavior
		12.6 Sensing by Optic Biomedical Signals
			12.6.1 Formation Aspects
			12.6.2 Sensing Aspects
		12.7 Analysis of Biomedical Signals
			12.7.1 Time-Domain Analysis
			12.7.2 Frequency-Domain Analysis
			12.7.3 Time-Frequency Domain-Based Analysis
			12.7.4 Other Methods
		12.8 Modeling of Biomedical Signals
			12.8.1 Models for ECG Signal Representation
			12.8.2 Models for EEG Signal Representation
			12.8.3 Models for EMG Signal Representation
			12.8.4 Models of Other Biomedical Signals
		12.9 Applications
			12.9.1 Detection of Heart-Related Disorders
			12.9.2 Detection of Brain-Related Diseases
			12.9.3 Detection of Neuromuscular Diseases
			12.9.4 Postural Stability Analysis
			12.9.5 Other Related Applications
		References
	13 Smart Learning Using Big and Small Data for Mobile and IOT e-Health
		Contents
		13.1 Introduction
			13.1.1 Key Challenges in Smart Learning for Mobile and IOT e-Health
			13.1.2 Incorporating Domain Knowledge in Data-Driven Learning
			13.1.3 Structure of the Book Chapter
		13.2 Predictive and Reinforcement Learning for Life Coaching
			13.2.1 Background: Stress-Activity Data
			13.2.2 Case Study: N-of-1 Analytical Methods
			13.2.3 Case Study: Actionable Learning Methods
		13.3 Knowledge Symbiosis Learning for Care Management
			13.3.1 Application: AI in Intelligent Education for Healthcare
			13.3.2 Background in Intelligent Tutoring Systems
			13.3.3 Challenges Facing the Development of ITS
			13.3.4 Case Study: Implicit Knowledge Learning for Nurses
			13.3.5 Case Study: Implicit Knowledge Learning for Caregivers
		13.4 Continuous Learning for In-Field Decision-Making
			13.4.1 Application: Risk Inference for Traumatic Brain Injury
		13.5 Discussion
		References
Index