Intelligent Internet of Things (eBook)
XII, 647 Seiten
Springer International Publishing (Verlag)
978-3-030-30367-9 (ISBN)
This holistic book is an invaluable reference for addressing various practical challenges in architecting and engineering Intelligent IoT and eHealth solutions for industry practitioners, academic and researchers, as well as for engineers involved in product development. The first part provides a comprehensive guide to fundamentals, applications, challenges, technical and economic benefits, and promises of the Internet of Things using examples of real-world applications. It also addresses all important aspects of designing and engineering cutting-edge IoT solutions using a cross-layer approach from device to fog, and cloud covering standards, protocols, design principles, reference architectures, as well as all the underlying technologies, pillars, and components such as embedded systems, network, cloud computing, data storage, data processing, big data analytics, machine learning, distributed ledger technologies, and security. In addition, it discusses the effects of Intelligent IoT, which are reflected in new business models and digital transformation. The second part provides an insightful guide to the design and deployment of IoT solutions for smart healthcare as one of the most important applications of IoT. Therefore, the second part targets smart healthcare-wearable sensors, body area sensors, advanced pervasive healthcare systems, and big data analytics that are aimed at providing connected health interventions to individuals for healthier lifestyles.
Farshad Firouzi is an Assistant Professor at the Electrical and Computer Engineering department of Duke University. Dr. Firouzi is a top-producing expert and technical leader with 10+ years' experience offering strong performance in all aspects of AI/ML, Smart Data, Computer Architecture, VLSI, and IoT including R&D, consulting services, strategic planning, and technology solutions, across vertical industries, e.g., Semiconductor, Automotive, Finance, Manufacturing, Logistics, and eHealth. Dr. Firouzi authored 45+ Conference/Journal papers and served as Guest/Associate Editor of several well-known Journals (e.g., IEEE TVLSI, IEEE TCAD, Elsevier FGCS, and Elsevier MICPRO) as well as chair of 10+ international conferences/workshops on AI/IoT/eHealth, e.g., in the USA, Portugal, Greece, Czech Republic, Spain, and Germany. Dr. Firouzi received his M.S., Ph.D., and Postdoctoral degrees in Computer Engineering from University of Tehran, Karlsruhe Institute of Technology, and KU Leuven (IMEC), respectively.
Krishnendu Chakrabarty is the John Cocke Distinguished Professor and Department Chair of Electrical and Computer Engineering at Duke University. Prof. Chakrabarty has received numerous awards for his research, including the Humboldt Research Award from the Alexander von Humboldt Foundation, Germany, the IEEE Computer Society Technical Achievement Award, the IEEE Circuits and Systems Society Charles A. Desoer Technical Achievement Award, the Semiconductor Research Corporation Technical Excellence Award, and the Japan Society for the Promotion of Science (JSPS) Fellowship in the 'Short Term S: Nobel Prize Level' category. His current research projects include: microfluidic biochips; testing and design-for-testability of integrated circuits and systems; hardware security; machine learning for fault diagnosis and failure prediction; neuromorphic computing systems. He holds over a dozen US patents and his research on microfluidic biochips has been licensed by Advanced Liquid Logic, Illumina, GenMark and Baebies, Inc. He is a Fellow of AAAS, a Fellow of ACM, a Fellow of IEEE, and a Golden Core Member of the IEEE Computer Society. He was a Distinguished Visitor of the IEEE Computer Society (2005-2007, 2010-2012), a Distinguished Lecturer of the IEEE Circuits and Systems Society (2006-2007, 2012-2013), and an ACM Distinguished Speaker (2008-2016). Prof. Chakrabarty served as the Editor-in-Chief of IEEE Design & Test of Computers during 2010-2012, ACM Journal on Emerging Technologies in Computing Systems during 2010-2015, and IEEE Transactions on VLSI Systems during 2015-2018. Prof. Chakrabarty received his M.S. and Ph.D. degrees in Computer Science and Engineering from the University of Michigan.
Sani Nassif has 28 years of research and development experience at Bell Labs and IBM Research where he led teams working on various aspects of integrated circuit modeling, simulation, statistical analysis, and optimization. In 2014 he formed Radyalis, a company focused on applying engineering techniques to the discipline of cancer radiation therapy. He is a widely published and world-renowned expert on simulation, optimization, and statistics. Dr. Nassif has collaborated with key medical research institutions, including: Massachusetts General Hospital, Mayo Clinic, M.D. Anderson Cancer Research Center, and St. Jude Children's Research Hospital, among others. He was a member of the IBM Academy, an IBM Master Inventor with 75 patents, and is an IEEE Fellow. Dr. Nassif received his M.S. and Ph.D. in Electrical Engineering from Carnegie Mellon University.
Preface 6
Acknowledgments 8
Contents 9
Part I IoT Building Blocks 11
1 IoT Fundamentals: Definitions, Architectures, Challenges, and Promises 12
Contents 12
1.1 What Is IoT 13
1.1.1 Internet of Things Terms and Acronyms 17
1.1.2 Impact of IoT 18
1.1.3 Benefits of IoT 19
1.1.4 IoT Challenges 21
1.1.5 IoT and Big Data 22
1.1.6 IoT and Cloud Computing 25
1.1.7 IoT and Digitalization 26
1.1.8 IoT and Industry 4.0 26
1.2 Architectures and Reference Models of IoT: A Layard View 28
1.2.1 IoTWF Reference Model of IoT 28
1.2.2 Simplified Reference Model of IoT 29
1.3 IoT Frameworks and Platforms 30
1.3.1 FIWARE 30
1.3.2 SmartThings 30
1.3.3 AWS IoT 31
1.3.4 Microsoft Azure IoT 31
1.3.4.1 Azure Internet of Things (IoT) Hub 31
1.3.4.2 Azure IoT Edge 32
1.3.4.3 Azure Stream Analytics 33
1.3.4.4 Azure Machine Learning 34
1.3.4.5 Azure Logic Apps 34
1.4 IoT Applications in Vertical Markets 35
1.4.1 Smart Agriculture 35
1.4.2 Logistics and Transportation 35
1.4.3 Smart Grid 36
1.4.4 Smart Building 37
1.4.5 Smart Factory 38
1.4.5.1 Current Manufacturing Model 39
1.4.5.2 Potential Use Cases 39
1.4.5.3 Major Challenges 42
1.4.6 Smart City 42
1.4.6.1 Smart City Layers 43
1.4.6.2 Applications of IoT in Smart City 45
1.4.6.3 Examples of Smart City 46
1.5 IoT Business Implications and Opportunities 46
1.5.1 Component Supplier: Component Business 48
1.5.2 Complete Solution and Product Provider: Additional Revenue 49
1.5.3 IoT Customer: Optimization and Cost Reduction 50
1.5.4 Important Aspects of Implementation 51
1.5.5 Data Monetization 51
1.5.6 Business Model 53
1.5.7 Minimum Viable Product (MVP) 56
1.6 Summary 57
References 58
2 The Smart “Things” in IoT 60
Contents 60
2.1 Definition and Architecture of Smart Things 61
2.2 Sensors 64
2.3 Actuators 68
2.3.1 Switches and Relays 68
2.3.2 Electrical Motors 70
2.4 Processing Unit: Microcontroller 72
2.4.1 Classifications of Microcontrollers 72
2.4.1.1 Classification by Bus-Width (Number of Bits) 72
2.4.1.2 Classification by Instruction Set (RISC vs CISC) 73
2.4.1.3 Classification by Memory Structure and Bus Architecture 73
2.4.1.4 Classification by IO 75
2.4.2 Three Main Types of Microcontrollers 76
2.4.2.1 Peripheral Interface Controller (PIC) Microcontrollers 76
2.4.2.2 AVR Microcontrollers 76
2.4.2.3 ARM Microcontrollers 77
2.5 ARM Microcontrollers 77
2.5.1 Background 77
2.5.2 Architecture 79
2.5.3 GPIOs and Interfaces 82
2.5.3.1 General-Purpose Input/Output (GPIO) 82
2.5.3.2 Analog Inputs 83
2.5.3.3 Analog Outputs 84
2.5.3.4 Parallel Interfaces vs Serial Interfaces 85
2.5.3.5 Universal Asynchronous Receiver/Transmitter (UART) 85
2.5.3.6 Serial Peripheral Interface (SPI) 87
2.5.3.7 I2C (Inter-integrated Circuit) 89
2.5.3.8 Universal Synchronous Asynchronous Receiver Transmitter (USART) 91
2.5.3.9 RS232 and RS422 92
2.5.4 Clock Tree 92
2.5.5 Interrupts 93
2.5.6 Addressing Modes 96
2.5.7 Timers 98
2.5.8 Low-Power Modes 99
2.5.9 Programming and Debugging Techniques 101
2.5.9.1 JTAG/SWD 101
2.5.9.2 Bootloader 102
2.5.10 Real-Time Operating System (RTOS) 102
2.6 Summary 103
References 103
3 Engineering IoT Networks 105
Contents 105
3.1 IoT Network Scenarios 106
3.2 The Simplified ISO/OSI Reference Model and IoT 108
3.2.1 Fundamental Terminology 108
3.2.1.1 Network Nodes 108
3.2.1.2 Links and Topologies 108
3.2.1.3 Quality of Service 109
3.2.1.4 Network Size 110
3.2.1.5 Communication Patterns 111
3.2.2 The ISO/OSI Layers 111
3.2.2.1 Application Layer 114
3.2.2.2 Transport Layer 114
3.2.2.3 Network Layer 115
3.2.2.4 Data Link Layer 115
3.2.2.5 Physical Layer 116
3.2.3 Standardization Bodies 116
3GPP 117
ITU 117
IEEE 117
ISO 117
ETSI 118
IETF 118
3.2.4 IoT Network Standards and the Simplified ISO/OSI Model 118
3.3 IoT Network Technologies and Standards 120
3.3.1 Modbus 120
3.3.2 Near-Field Communication (NFC) 121
3.3.3 Bluetooth 122
3.3.3.1 Bluetooth Versions 123
3.3.3.2 Bluetooth Protocols and Profiles 124
3.3.4 IEEE 802.15.4 129
3.3.5 ZigBee 132
3.3.6 ZigBee IP 132
3.3.7 WirelessHART 133
3.3.8 Wi-Fi (IEEE 802.11 Family) 136
3.3.9 LoRaWAN 136
3.3.10 Sigfox 141
3.3.11 Z-Wave 142
3.3.12 Wireless M-Bus 143
3.3.13 Optical Wireless Communications 143
3.3.14 6LoWPAN 144
3.3.15 Thread 146
3.3.16 ISA100.11a 147
3.3.17 Cellular Network Standards 148
3.3.17.1 Second Generation (2G) 149
3.3.17.2 Third Generation (3G) 149
3.3.17.3 Fourth Generation (4G) 149
3.3.17.4 NB-IoT 150
3.3.17.5 LTE Cat M1 151
3.3.17.6 Fifth Generation (5G) 152
3.4 Application Layer Protocols 152
3.4.1 HyperText Transfer Protocol (HTTP) 153
3.4.2 WebSocket 154
3.4.3 Web Services and Representational State Transfer (REST) 155
3.4.4 Message Queuing Telemetry Transport (MQTT) 157
3.4.4.1 How MQTT Works 157
3.4.5 Advanced Message Queuing Protocol (AMQP) 161
3.4.6 Constrained Application Protocol (CoAP) 161
3.4.6.1 CoAP Request/Response Model 164
3.4.7 Extensible Messaging and Presence Protocol (XMPP) 165
3.4.8 OPC Unified Architecture (OPC-UA) 166
3.5 IoT Network Design Methodology 169
3.5.1 Communications for Localization 172
3.6 Summary 174
References 174
4 Architecting IoT Cloud 180
Contents 180
4.1 The IoT Cloud 181
4.2 Fundamentals of Cloud Computing 183
4.2.1 Cloud Computing Key Characteristics 184
4.2.2 Service Models 184
4.2.3 Deployment Models 185
4.3 Device Management Layer 186
4.3.1 Provisioning 186
4.3.2 Software Updates and Maintenance 188
4.3.3 Monitoring and Control 189
4.4 Data Ingestion Layer 189
4.4.1 Data Ingestion Frameworks 191
4.4.1.1 Apache Flume 191
4.4.1.2 Apache Kafka 191
4.4.1.3 Apache Nifi 193
4.4.1.4 Elastic Logstash 194
4.5 Data Processing Layer 194
4.5.1 Data Processing Architectures 196
4.5.1.1 Lambda Architecture 196
4.5.1.2 Kappa Architecture 198
4.5.2 Data Processing Frameworks 198
4.5.2.1 Apache Storm 198
4.5.2.2 Apache Flink 199
4.5.2.3 Apache Spark 199
4.6 Data Storage Layer: A Hybrid Architecture 200
4.6.1 Database 201
4.6.1.1 MongoDB 205
4.6.1.2 Cassandra 206
4.6.1.3 Redis 210
4.6.1.4 InfluxDB 211
4.6.1.5 Elasticsearch 212
4.6.1.6 Which Database Is Right for Your IoT Project? 216
4.6.1.7 CAP Theorem 217
4.6.2 Data Warehouse 218
4.6.3 Data Lake 220
4.6.3.1 ETL (Extract, Transform, and Load) and ELT (Extract, Load, and Transform) 222
4.6.3.2 Challenges of Data Lakes 223
4.6.3.3 Distributed File Systems 224
4.6.3.4 Data Lake Tiers 224
4.7 Application Layer 225
4.7.1 Microservice Architecture Pattern 229
4.7.1.1 API Gateway 229
4.7.1.2 Service Invocation 230
4.7.1.3 Service Discovery 232
4.7.1.4 Service Registry 232
4.7.1.5 Deployment Strategy 232
4.8 Data Visualization and Reporting Layer 234
4.8.1 Data Visualization Frameworks 234
4.8.2 Business Intelligence Frameworks 234
4.8.3 Advanced Data Analytical and Machine Learning Frameworks 235
4.8.4 Load Balancing 236
4.9 Orchestration Layer 238
4.10 Virtualization 239
4.10.1 Main Categories of Virtualization 239
4.10.2 Behind the Scene of FaaS: OpenWhisk 242
4.11 Scaling 244
4.11.1 Vertical Scaling (Scale-Up) 244
4.11.2 Horizontal Scaling (Scale-Out or Clustering) 244
4.12 A Paradigm Shift from Cloud to Fog Computing 245
4.13 Summary 247
References 247
5 Machine Learning for IoT 249
Contents 249
5.1 Fundamental of Machine Learning 250
5.1.1 Fundamental Terminologies 251
5.1.2 Review of Probability Theory 253
5.1.2.1 Random Variable 253
5.1.2.2 Distribution 253
5.1.2.3 Mean, Variance, and Covariance 254
5.1.3 Review of Linear Algebra 256
5.1.4 Supervised and Unsupervised Learning 259
5.1.4.1 Supervised Learning 259
5.1.4.2 Unsupervised Learning 260
5.1.5 Machine Learning in IoT 260
5.1.6 Machine Learning Flow 262
5.1.6.1 Overall Flow of Machine Learning Projects 262
5.1.6.2 Data Preparation 263
5.2 Regression Analysis 266
5.2.1 Linear Regression 269
5.2.2 Regularization in Linear Regression 270
5.2.2.1 Geometric Interpretations of Regularization 272
5.2.2.2 Elastic Net Regularization 274
5.2.3 Bayesian Linear Regression 275
5.3 Feature Selection 276
5.3.1 Feature Selection Techniques 277
5.3.1.1 Chi-Square Test 278
5.3.1.2 Pearson Correlation 280
5.3.1.3 Entropy 280
5.3.2 Feature Extraction 282
5.4 Classification 282
5.4.1 Measuring Performance for Classification Problems 282
5.4.1.1 Confusion Matrix (Error Matrix) 282
5.4.1.2 Performance Metrics 283
5.4.2 Over- and Undersampling 286
5.4.3 K-Nearest Neighbor (KNN) 287
5.4.4 Logistic Regression 288
5.4.4.1 Logit and Sigmoid (Logistic) Functions 288
5.4.4.2 Decision Boundary (Decision Surface) 290
5.4.4.3 Cost Function in Logistic Regression 291
5.4.5 Support Vector Machine 292
5.4.6 Decision Tree Classifier 296
5.4.7 Ensembles 298
5.4.7.1 Bootstrap Aggregating (Bagging) 298
5.4.7.2 Random Forest 299
5.4.7.3 Boosting 300
5.5 Dimensionality Reduction 302
5.6 Artificial Neural Networks 303
5.6.1 Neural Network Models 303
5.6.2 Train a Neural Network Model 304
5.6.3 Activation Function 306
5.6.4 Softmax Function 308
5.6.5 Convolution Neural Networks 310
5.6.5.1 Convolution Layer 310
5.6.5.2 Stride 312
5.6.5.3 Padding 313
5.6.5.4 Pooling Layers 314
5.6.5.5 Fully Connected Layer 316
5.6.5.6 Well-Known CNN Architectures 316
5.7 Clustering 316
5.7.1 K-Means Clustering 316
5.7.2 Hierarchical Clustering 317
5.8 Summary 318
References 318
6 Big Data 320
Contents 320
6.1 Introduction to Big Data 321
6.1.1 Defining Big Data 322
6.1.2 Volume 322
6.1.3 Velocity 323
6.1.4 Variety 323
6.1.5 Veracity 323
6.2 Big Data Management and Computing Platforms 324
6.2.1 Big Data System Architecture Components 325
6.2.2 Hadoop History 326
6.2.3 The Apache Hadoop Framework Components 327
6.2.4 Hadoop Distributed File System 328
6.2.4.1 Overview of Data Formats 330
6.2.5 MapReduce 331
6.2.6 YARN 332
6.3 An Introduction to Big Data Modeling and Manipulation 334
6.3.1 Big Table 334
6.3.2 Pig 334
6.3.3 Sqoop 335
6.3.4 Hive 335
6.3.5 HBase 336
6.3.6 Oozie 336
6.3.7 Zookeeper 336
6.3.8 Data Lakes and Warehouses 337
6.4 An Introduction to Spark: An Innovative Paradigm in Big Data 338
6.4.1 The Spark Ecosystem 339
6.4.2 The Core Difference Between Spark and Hadoop 340
6.4.3 Resilient Distributed Datasets in Spark 341
6.4.4 RDD Transformations and Actions 343
6.4.5 Datasets and DataFrames in Spark 345
6.4.6 The Spark Processing Engine 345
6.4.7 Spark Components 346
6.4.8 Spark SQL 348
6.4.9 Spark DataFrames 349
6.4.10 Creating a DataFrame 349
6.4.10.1 Example of Reading DataFrame from the Parquet File 350
6.4.11 DataFrame Operations 350
6.4.12 Spark MLlib 351
6.4.13 MLlib Capabilities 352
6.4.14 Spark Streaming 353
6.4.15 Intro to Batch and Stream Processing 353
6.4.16 Spark Streaming 354
6.4.17 Spark Functionality 354
6.5 Big Data Analytics: Building the Data Pipeline 357
6.5.1 Developing Predictive and Prescriptive Models 357
6.5.2 The Cross Industry Standard Process for Data Mining (CRISP-DM) 358
6.6 Conclusion 359
References 359
7 Intelligent and Connected Cyber-Physical Systems: A Perspective from Connected Autonomous Vehicles 362
Contents 362
7.1 Introduction 362
7.2 Background 365
7.2.1 Cyber Components 366
7.2.2 Physical Components 371
7.2.3 Cyber and Physical Interactions 374
7.3 Case Studies 380
7.3.1 Assuring the Safety of Machine Learning-Based Perception for Highly Automated Driving 380
7.3.1.1 Introduction 381
7.3.1.2 Safety Requirements on the Machine Learning Function 382
7.3.1.3 Causes of Functional Insufficiencies in Machine Learning 384
7.3.1.4 Sources of Evidence and Structuring the Assurance Case 386
7.3.1.5 Summary 388
7.3.2 Assuring the Security and Robustness of Connected Vehicle Applications 389
7.3.2.1 Introduction 389
7.3.2.2 Security Challenges in Connected Vehicle Applications 391
7.3.2.3 Key Management System 391
7.3.2.4 Intrusion Detection System 392
7.3.2.5 System Integration 394
7.3.2.6 Summary 394
7.4 Concluding Remarks 395
References 396
8 Distributed Ledger Technology 398
Contents 398
8.1 Introduction to Distributed Ledger Technology and IoT 399
8.1.1 What Is a Distributed Ledger? 399
8.1.2 Blockchain 400
8.1.3 Types of Blockchain 401
8.1.3.1 Permissionless Blockchains 401
8.1.3.2 Permissioned Blockchains 402
8.1.4 Directed Acyclic Graph (DAG) 402
8.1.5 Hybrid DLTs Based on Blockchains and DAGs 403
8.1.6 Internet of Things (IoT) 403
8.2 Benefits of DLTs 404
8.2.1 Blockchain Benefits 404
8.2.2 DAG Benefits 406
8.3 How Blockchain Works 407
8.3.1 Transaction, Block, Ledger, and Blockchain 408
8.3.2 Transaction Validation and Block Mining 409
8.3.3 Smart Contracts 413
8.3.4 Consensus Algorithms 413
8.3.4.1 Proof-of-Work (PoW) 414
8.3.4.2 Proof-of-Stake (PoS) 414
8.3.4.3 Delegated Proof-of-Stake (DPoS) 415
8.3.4.4 Practical Byzantine Fault Tolerance (PBFT) 416
8.3.4.5 IOTA 417
8.4 Directed Acyclic Graph (DAG) 418
8.4.1 What Is a DAG 418
8.4.2 How IOTA Tangle Works 418
8.5 DAG Versus Blockchain 419
8.6 Blockchain and Internet of Things 419
8.6.1 Internet of Things 419
8.6.2 Weaknesses of Internet of Things 420
8.6.3 Blockchains and IoT 422
8.6.4 How to Combine Blockchains and IoT 423
8.7 Prominent Enterprise DLT Platforms 424
8.7.1 Hyperledger Fabric 424
8.7.2 Ethereum 425
8.7.3 IOTA 425
8.8 Applications of Blockchain 426
8.8.1 Financial Services 426
8.8.2 Healthcare 427
8.8.3 Energy 427
8.8.4 Identity Management 428
8.8.5 Supply Chain Management 429
8.8.6 Other Applications 429
8.9 Other Aspects of DLTs 430
8.9.1 Scalability and Other Practical Considerations 430
8.9.1.1 Bitcoin 430
8.9.1.2 Hyperledger Fabric 430
8.9.1.3 Ethereum 431
8.9.1.4 IOTA 431
8.9.1.5 Scalability of DLTs 432
8.9.2 Token and Token Economics 432
8.10 Vulnerabilities of Blockchain 433
8.11 Summary 434
References 434
9 Emerging Hardware Technologies for IoT Data Processing 437
Contents 437
9.1 Challenges for Data Processing in the Era of IoT 438
9.1.1 IoT System Architecture 438
9.1.2 Energy Efficiency as a Paramount Concern 439
9.1.3 Bandwidth Limitation for Big Data Processing 440
9.2 Recent Innovations for Bandwidth and Energy 440
9.2.1 Heterogeneous Computing 440
9.2.2 In-Package Die Stacking 441
9.2.3 Emerging Memory Technologies 442
9.2.4 Machine Learning Accelerators in the IoT Era 443
9.2.5 Approximate Computing 444
9.3 Near-Memory Processing 446
9.4 In Situ Processing for IoT Devices 447
9.4.1 Deep Binary Neural Network 447
9.4.2 The MB-CNN Architecture 449
9.4.3 Memristive XNOR Convolution 450
9.4.3.1 Computing XNOR Within RRAM Crosspoint 450
9.4.3.2 In Situ Bit-Counting 451
9.4.4 The MB-CNN Architecture 452
9.4.4.1 MB-CNN Chip Control 452
9.4.4.2 Bank Organization 453
9.4.4.3 Array Structure 454
9.4.4.4 Data Organization 454
9.4.5 Potentials of the MB-CNN Accelerator 456
9.5 In Situ Data Clustering for IoT Servers 457
9.5.1 Data Clustering 458
9.5.2 Applications of Data Clustering 458
9.5.2.1 Gene Expression Analysis 458
9.5.2.2 Document Clustering 459
9.5.3 Data Clustering with Rank-Order Filters 460
9.5.3.1 Bit-Serial Median Filter 460
9.5.4 Memristive k-Median Clustering 461
9.5.4.1 The MISC Architecture 461
9.5.4.2 The Design Principles for MISC 462
9.5.5 MISC Building Blocks 463
9.5.5.1 Memory Cell 463
9.5.5.2 Analog Bit Counter and Reduction Network 465
9.5.5.3 MISC Array Organization 466
9.5.5.4 MISC Data Representation 467
9.5.5.5 Handling Even Number of Data Points 468
9.5.6 Potentials of the MISC Accelerator 469
References 470
10 IoT Cyber Security 476
Contents 476
10.1 Introduction 477
10.2 A Complex Threat Environment 478
10.2.1 Threat Actors and Risk Likelihood 480
10.2.2 Threat Types 480
10.3 Cyber Security Controls for IoT Systems 483
10.3.1 Establishing a Secure IoT System Development Methodology 484
10.3.1.1 Threat Modeling an IoT System 484
10.3.1.2 Documenting Cyber Security Requirements 485
10.3.1.3 Establishing a Cyber Security Culture 486
10.3.1.4 Conducting Code Audits and Automating Processes 488
10.3.1.5 Gaining Visibility into Your Supply Chain 489
10.3.1.6 Working with the Security Research Community 489
10.3.2 Integrating Safety and Security Engineering 490
10.3.3 Safeguarding Stakeholder Privacy 491
10.4 Securing the IoT Edge 491
10.4.1 Use a Hardware Security Element to Support Trusted Operations 493
10.4.2 Configure a Secure Real-Time Operating System 494
10.4.3 Implement Physical Security Controls 495
10.4.4 Deploy Confidentiality Protections 496
10.4.5 Implement Strong Authentication and Access Controls 498
10.4.5.1 Authorization and Access Control 498
10.4.6 Harden Network Services 499
10.4.7 Implement Logging and Behavioral Analytics 500
10.4.8 Implement Framework Security 500
10.5 A Secure Network 501
10.5.1 Secure Wireless Sensor Network (WSN) Configuration 501
10.5.2 Segment the Network 501
10.5.3 Implement Zero-Trust/Software-Defined Perimeter 502
10.5.4 Protect the Perimeter 502
10.5.5 Secure Discovery Services 502
10.5.6 Implement Asset Management 502
10.5.7 Implement Vulnerability Tracking 503
10.5.8 Audit and Monitoring 503
10.5.9 Vulnerability Scanning 505
10.5.10 Penetration Testing 505
10.6 A Secure Cloud 506
10.6.1 Evaluate the Security of the CSP 507
10.6.2 Design the Cloud Service to be Resilient and Available 508
10.6.3 Securely Configure the Cloud Network 508
10.6.4 Apply Encryption to Cloud Communications 508
10.6.5 Manage Cloud Identities 509
10.6.6 Require Multi-Factor Cloud Authentication 509
10.6.7 Audit Cloud Services 509
10.6.8 Monitor the Cloud 509
10.6.9 Implement Cloud Identity Management 509
10.6.10 Use Zero-Touch Provisioning 510
10.6.11 Role-Based Access Controls 510
10.6.12 Secure Data in the Cloud 511
10.6.13 Secure Web Services 511
10.7 Secure System Users and Administrators 512
10.7.1 User Training 512
10.7.2 Administrator Training 512
10.7.3 Incident Response Planning 513
10.8 Conclusion 514
References 514
Part II IoT Technologies for Smart Healthcare 516
11 Healthcare IoT 517
Contents 517
11.1 Modern Healthcare Challenges 518
11.2 What Is IoT-Driven Healthcare: Transitioning from Hospital-Centric to Patient-Centric 519
11.3 Benefits of Adopting IoT Healthcare 521
11.4 Fog-Driven IoT Healthcare Architecture: A Layered View 524
11.4.1 Things Layer 524
11.4.2 Network Layer 527
11.4.3 Cloud Layer 530
11.5 Key Services and Applications of IoT Healthcare 533
11.5.1 Mobile Health (m-Health) 533
11.5.2 IoT in Ambient Assisted Living 533
11.5.3 IoT Medication 533
11.5.4 IoT to Assist Individuals with Disabilities or Special Needs 534
11.5.5 Smart Medical Implants 534
11.5.6 IoT for Early Warning Score (EWS) 535
11.5.7 IoT-Based Anomaly Detection 535
11.5.8 Population Health Management 536
11.6 Major Challenges of IoT Healthcare 537
11.6.1 Interoperability, Standardization, and Regulation 537
11.6.2 Heterogeneity 537
11.6.3 Interfaces and Human Factor Engineering 538
11.6.4 Scalability 538
11.6.5 Power Consumption 539
11.6.6 Intrusiveness 539
11.6.7 Design Automation Challenges 539
11.6.8 Data Management 540
11.6.9 Context Awareness 540
11.6.10 Availability and Reliability 541
11.6.11 Data Transmission 541
11.6.12 Security and Privacy 542
11.7 Case Study: Collaborative Machine Learning-Driven Healthcare Internet of Things 543
11.8 Summary 545
References 546
12 Biomedical Engineering Fundamentals 548
Contents 548
12.1 Introduction of Bioelectricity and Biomechanics 549
12.2 Biosensors 550
12.2.1 Temperature Sensors 550
12.2.1.1 Thermocouple 551
12.2.1.2 Thermistor 552
12.2.1.3 Diode Temperature Sensor 552
12.2.1.4 Transistor Temperature Sensor 553
12.2.2 Light Sensors 554
12.2.2.1 Photoresistor 554
12.2.2.2 Photodiode 555
12.2.2.3 Phototransistor 555
12.2.3 Spectrophotometry 556
12.2.4 Fluorescence 557
12.2.5 Immunosensors 557
12.3 Basics of Signals and Systems 558
12.3.1 Types of Signals 558
12.3.1.1 Continuous, Discrete Time, and Digital Signals 558
12.3.1.2 Periodic and Aperiodic Signals 560
12.3.1.3 Deterministic and Random Signals 561
12.3.1.4 Even and Odd Signals 561
12.3.1.5 Energy and Power Signals 563
12.3.2 Types of Systems 563
12.3.2.1 Linear and Nonlinear Systems 563
12.3.2.2 Time-Invariant and Time-Variant Systems 564
12.3.2.3 Linear Time-Invariant and Linear Time-Variant Systems 564
12.3.2.4 Static and Dynamic Systems 564
12.3.2.5 Causal and Noncausal Systems 565
12.3.2.6 Invertible and Non-invertible Systems 565
12.3.2.7 Stable and Unstable Systems 565
12.3.3 Signal Acquisition 566
12.3.4 Time- and Frequency-Domain Representations 566
12.3.5 Finite Impulse Response (FIR) and Infinite Impulse Response (IIR) Filters 570
12.4 Types of Biomedical Signals 571
12.4.1 Electroencephalogram (EEG) 572
12.4.2 Electrocardiogram (ECG) 573
12.4.3 Electromyogram (EMG) 575
12.4.4 Electrooculogram (EOG) 577
12.4.5 Magnetoencephalogram (MEG) 578
12.4.6 Other Biomedical Signals 579
12.5 Physiological Phenomena and Biomedical Signals 580
12.5.1 Vital Phenomena and Their Parameters 581
12.5.1.1 Heartbeat 581
12.5.1.2 Respiration 582
12.5.1.3 Blood Circulation 583
12.5.1.4 Blood Oxygenation 587
12.5.1.5 Body Temperature 587
12.5.2 Parameter Behavior 588
12.6 Sensing by Optic Biomedical Signals 590
12.6.1 Formation Aspects 591
12.6.2 Sensing Aspects 594
12.7 Analysis of Biomedical Signals 596
12.7.1 Time-Domain Analysis 596
12.7.2 Frequency-Domain Analysis 597
12.7.3 Time-Frequency Domain-Based Analysis 599
12.7.4 Other Methods 599
12.8 Modeling of Biomedical Signals 600
12.8.1 Models for ECG Signal Representation 600
12.8.2 Models for EEG Signal Representation 600
12.8.3 Models for EMG Signal Representation 601
12.8.4 Models of Other Biomedical Signals 601
12.9 Applications 601
12.9.1 Detection of Heart-Related Disorders 602
12.9.2 Detection of Brain-Related Diseases 602
12.9.3 Detection of Neuromuscular Diseases 602
12.9.4 Postural Stability Analysis 603
12.9.5 Other Related Applications 603
References 603
13 Smart Learning Using Big and Small Data for Mobile and IOT e-Health 607
Contents 607
13.1 Introduction 608
13.1.1 Key Challenges in Smart Learning for Mobile and IOT e-Health 609
13.1.2 Incorporating Domain Knowledge in Data-Driven Learning 611
13.1.3 Structure of the Book Chapter 611
13.2 Predictive and Reinforcement Learning for Life Coaching 612
13.2.1 Background: Stress-Activity Data 612
13.2.2 Case Study: N-of-1 Analytical Methods 613
13.2.3 Case Study: Actionable Learning Methods 615
13.3 Knowledge Symbiosis Learning for Care Management 618
13.3.1 Application: AI in Intelligent Education for Healthcare 618
13.3.2 Background in Intelligent Tutoring Systems 619
13.3.3 Challenges Facing the Development of ITS 621
13.3.4 Case Study: Implicit Knowledge Learning for Nurses 622
13.3.5 Case Study: Implicit Knowledge Learning for Caregivers 623
13.4 Continuous Learning for In-Field Decision-Making 627
13.4.1 Application: Risk Inference for Traumatic Brain Injury 627
13.5 Discussion 629
References 631
Index 637
| Erscheint lt. Verlag | 21.1.2020 |
|---|---|
| Zusatzinfo | XII, 647 p. 337 illus., 261 illus. in color. |
| Sprache | englisch |
| Themenwelt | Mathematik / Informatik ► Informatik |
| Technik ► Elektrotechnik / Energietechnik | |
| Technik ► Nachrichtentechnik | |
| Schlagworte | AI-driven IoT • Big Data • Internet of Everything • IoT cloud architecture and design • IoT in Healthcare |
| ISBN-10 | 3-030-30367-5 / 3030303675 |
| ISBN-13 | 978-3-030-30367-9 / 9783030303679 |
| Haben Sie eine Frage zum Produkt? |
PDF (Wasserzeichen)Größe: 16,0 MB
DRM: Digitales Wasserzeichen
Dieses eBook enthält ein digitales Wasserzeichen und ist damit für Sie personalisiert. Bei einer missbräuchlichen Weitergabe des eBooks an Dritte ist eine Rückverfolgung an die Quelle möglich.
Dateiformat: PDF (Portable Document Format)
Mit einem festen Seitenlayout eignet sich die PDF besonders für Fachbücher mit Spalten, Tabellen und Abbildungen. Eine PDF kann auf fast allen Geräten angezeigt werden, ist aber für kleine Displays (Smartphone, eReader) nur eingeschränkt geeignet.
Systemvoraussetzungen:
PC/Mac: Mit einem PC oder Mac können Sie dieses eBook lesen. Sie benötigen dafür einen PDF-Viewer - z.B. den Adobe Reader oder Adobe Digital Editions.
eReader: Dieses eBook kann mit (fast) allen eBook-Readern gelesen werden. Mit dem amazon-Kindle ist es aber nicht kompatibel.
Smartphone/Tablet: Egal ob Apple oder Android, dieses eBook können Sie lesen. Sie benötigen dafür einen PDF-Viewer - z.B. die kostenlose Adobe Digital Editions-App.
Zusätzliches Feature: Online Lesen
Dieses eBook können Sie zusätzlich zum Download auch online im Webbrowser lesen.
Buying eBooks from abroad
For tax law reasons we can sell eBooks just within Germany and Switzerland. Regrettably we cannot fulfill eBook-orders from other countries.
aus dem Bereich
