Оглавление
Saeid Sanei. Body Sensor Networking, Design and Algorithms
Table of Contents
List of Tables
List of Illustrations
Guide
Pages
Body Sensor Networking, Design and Algorithms
Preface
About the Companion Website
1 Introduction. 1.1 History of Wearable Technology
1.2 Introduction to BSN Technology
1.3 BSN Architecture
1.4 Layout of the Book
References
2 Physical, Physiological, Biological, and Behavioural States of the Human Body. 2.1 Introduction
2.2 Physical State of the Human Body
2.3 Physiological State of Human Body
2.4 Biological State of Human Body
2.5 Psychological and Behavioural State of the Human Body
2.6 Summary and Conclusions
References
3 Physical, Physiological, and Biological Measurements. 3.1 Introduction
3.2 Wearable Technology for Gait Monitoring
3.2.1 Accelerometer and Its Application to Gait Monitoring
3.2.1.1 How Accelerometers Operate
3.2.1.2 Accelerometers in Practice
3.2.2 Gyroscope and IMU
3.2.3 Force Plates
3.2.4 Goniometer
3.2.5 Electromyography
3.2.6 Sensing Fabric
3.3 Physiological Sensors
3.3.1 Multichannel Measurement of the Nerves Electric Potentials
3.3.2 Other Sensors
3.4 Biological Sensors
3.4.1 The Structures of Biological Sensors – The Principles
3.4.2 Emerging Biosensor Technologies
3.5 Conclusions
References
4 Ambulatory and Popular Sensor Measurements. 4.1 Introduction
4.2 Heart Rate
4.2.1 HR During Physical Exercise
4.3 Respiration
4.4 Blood Oxygen Saturation Level
4.5 Blood Pressure
4.5.1 Cuffless Blood Pressure Measurement
4.6 Blood Glucose
4.7 Body Temperature
4.8 Commercial Sensors
4.9 Conclusions
References
5 Polysomnography and Sleep Analysis. 5.1 Introduction
5.2 Polysomnography
5.3 Sleep Stage Classification
5.3.1 Sleep Stages
5.3.2 EEG-Based Classification of Sleep Stages
5.3.2.1 Time Domain Features
5.3.2.2 Frequency Domain Features
5.3.2.3 Time-frequency Domain Features
5.3.2.4 Short-time Fourier Transform
5.3.2.5 Wavelet Transform
5.3.2.6 Matching Pursuit
5.3.2.7 Empirical Mode Decomposition
5.3.2.8 Nonlinear Features
5.3.3 Classification Techniques
5.3.3.1 Using Neural Networks
5.3.3.2 Application of CNNs
5.3.4 Sleep Stage Scoring Using CNN
5.4 Monitoring Movements and Body Position During Sleep
5.5 Conclusions
References
6 Noninvasive, Intrusive, and Nonintrusive Measurements. 6.1 Introduction
6.2 Noninvasive Monitoring
6.3 Contactless Monitoring
6.3.1 Remote Photoplethysmography
6.3.1.1 Derivation of Remote PPG
6.3.2 Spectral Analysis Using Autoregressive Modelling
6.3.3 Estimation of Physiological Parameters Using Remote PPG. 6.3.3.1 Heart Rate Estimation
6.3.3.2 Respiratory Rate Estimation
6.3.3.3 Blood Oxygen Saturation Level Estimation
6.3.3.4 Pulse Transmit Time Estimation
6.3.3.5 Video Pre-processing
6.3.3.6 Selection of Regions of Interest
6.3.3.7 Derivation of the rPPG Signal
6.3.3.8 Processing rPPG Signals
6.3.3.9 Calculation of rPTT/dPTT
6.4 Implantable Sensor Systems
6.5 Conclusions
References
7 Single and Multiple Sensor Networking for Gait Analysis. 7.1 Introduction
7.2 Gait Events and Parameters. 7.2.1 Gait Events
7.2.2 Gait Parameters
7.2.2.1 Temporal Gait Parameters
7.2.2.2 Spatial Gait Parameters
7.2.2.3 Kinetic Gait Parameters
7.2.2.4 Kinematic Gait Parameters
7.3 Standard Gait Measurement Systems. 7.3.1 Foot Plantar Pressure System
7.3.2 Force-plate Measurement System
7.3.3 Optical Motion Capture Systems
7.3.4 Microsoft Kinect Image and Depth Sensors
7.4 Wearable Sensors for Gait Analysis. 7.4.1 Single Sensor Platforms
7.4.2 Multiple Sensor Platforms
7.5 Gait Analysis Algorithms Based on Accelerometer/Gyroscope. 7.5.1 Estimation of Gait Events
7.5.2 Estimation of Gait Parameters
7.5.2.1 Estimation of Orientation
7.5.2.2 Estimating Angles Using Accelerometers
7.5.2.3 Estimating Angles Using Gyroscopes
7.5.2.4 Fusing Accelerometer and Gyroscope Data
7.5.2.5 Quaternion Based Estimation of Orientation
7.5.2.6 Step Length Estimation
7.6 Conclusions
References
8 Popular Health Monitoring Systems. 8.1 Introduction
8.2 Technology for Data Acquisition
8.3 Physiological Health Monitoring Technologies. 8.3.1 Predicting Patient Deterioration
8.3.2 Ambient Assisted Living: Monitoring Daily Living Activities
8.3.3 Monitoring Chronic Obstructive Pulmonary Disease Patients
8.3.4 Movement Tracking and Fall Detection/Prevention
8.3.5 Monitoring Patients with Dementia
8.3.6 Monitoring Patients with Parkinson's Disease
8.3.7 Odour Sensitivity Measurement
8.4 Conclusions
References
9 Machine Learning for Sensor Networks. 9.1 Introduction
9.2 Clustering Approaches. 9.2.1 k-means Clustering Algorithm
9.2.2 Iterative Self-organising Data Analysis Technique
9.2.3 Gap Statistics
9.2.4 Density-based Clustering
9.2.5 Affinity-based Clustering
9.2.6 Deep Clustering
9.2.7 Semi-supervised Clustering
9.2.7.1 Basic Semi-supervised Techniques
9.2.7.2 Deep Semi-supervised Techniques
9.2.8 Fuzzy Clustering
9.3 Classification Algorithms. 9.3.1 Decision Trees
9.3.2 Random Forest
9.3.3 Linear Discriminant Analysis
9.3.4 Support Vector Machines
9.3.5 k-nearest Neighbour
9.3.6 Gaussian Mixture Model
9.3.7 Logistic Regression
9.3.8 Reinforcement Learning
9.3.9 Artificial Neural Networks
9.3.9.1 Deep Neural Networks
9.3.9.2 Convolutional Neural Networks
9.3.9.3 Recent DNN Approaches
9.3.10 Gaussian Processes
9.3.11 Neural Processes
9.3.12 Graph Convolutional Networks
9.3.13 Naïve Bayes Classifier
9.3.14 Hidden Markov Model
9.3.14.1 Forward Algorithm
9.3.14.2 Backward Algorithm
9.3.14.3 HMM Design
9.4 Common Spatial Patterns
9.5 Applications of Machine Learning in BSNs and WSNs
9.5.1 Human Activity Detection
9.5.2 Scoring Sleep Stages
9.5.3 Fault Detection
9.5.4 Gas Pipeline Leakage Detection
9.5.5 Measuring Pollution Level
9.5.6 Fatigue-tracking and Classification System
9.5.7 Eye-blink Artefact Removal from EEG Signals
9.5.8 Seizure Detection
9.5.9 BCI Applications
9.6 Conclusions
References
10 Signal Processing for Sensor Networks. 10.1 Introduction
10.2 Signal Processing Problems for Sensor Networks
10.3 Fundamental Concepts in Signal Processing
10.3.1 Nonlinearity of the Medium
10.3.2 Nonstationarity
10.3.3 Signal Segmentation
10.3.4 Signal Filtering
10.4 Mathematical Data Models. 10.4.1 Linear Models
10.4.1.1 Prediction Method
10.4.1.2 Prony's Method
10.4.1.3 Singular Spectrum Analysis
Decomposition
Reconstruction
Prediction
10.4.2 Nonlinear Modelling
10.4.3 Gaussian Mixture Model
10.5 Transform Domain Signal Analysis
10.6 Time-frequency Domain Transforms
10.6.1 Short-time Fourier Transform
10.6.2 Wavelet Transform
10.6.2.1 Continuous Wavelet Transform
10.6.2.2 Examples of Continuous Wavelets
10.6.2.3 Discrete Time Wavelet Transform
10.6.3 Multiresolution Analysis
10.6.4 Synchro-squeezing Wavelet Transform
10.7 Adaptive Filtering
10.8 Cooperative Adaptive Filtering
10.8.1 Diffusion Adaptation
10.9 Multichannel Signal Processing
10.9.1 Instantaneous and Convolutive BSS Problems
10.9.2 Array Processing
10.10 Signal Processing Platforms for BANs
10.11 Conclusions
References
11 Communication Systems for Body Area Networks. 11.1 Introduction
11.2 Short-range Communication Systems
11.2.1 Bluetooth
11.2.2 Wi-Fi
11.2.3 ZigBee
11.2.4 Radio Frequency Identification Devices
11.2.5 Ultrawideband
11.2.6 Other Short-range Communication Methods
11.2.7 RF Modules Available in Market
11.3 Limitations, Interferences, Noise, and Artefacts
11.4 Channel Modelling
11.4.1 BAN Propagation Scenarios
11.4.1.1 On-body Channel
11.4.1.2 In-body Channel
11.4.1.3 Off-body Channel
11.4.1.4 Body-to-body (or Interference) Channel
11.4.2 Recent Approaches to BAN Channel Modelling
11.4.3 Propagation Models
11.4.4 Standards and Guidelines
11.5 BAN-WSN Communications
11.6 Routing in WBAN
11.6.1 Posture-based Routing
11.6.2 Temperature-based Routing
11.6.3 Cross-layer Routing
11.6.4 Cluster-based Routing
11.6.5 QoS-based Routing
11.7 BAN-building Network Integration
11.8 Cooperative BANs
11.9 BAN Security
11.10 Conclusions
References
12 Energy Harvesting Enabled Body Sensor Networks. 12.1 Introduction
12.2 Energy Conservation
12.3 Network Capacity
12.4 Energy Harvesting
12.5 Challenges in Energy Harvesting
12.6 Types of Energy Harvesting
12.6.1 Harvesting Energy from Kinetic Sources
12.6.2 Energy Sources from Radiant Sources
12.6.3 Energy Harvesting from Thermal Sources
12.6.4 Energy Harvesting from Biochemical and Chemical Sources
12.7 Topology Control
12.8 Typical Energy Harvesters for BSNs
12.9 Predicting Availability of Energy
12.10 Reliability of Energy Storage
12.11 Conclusions
References
13 Quality of Service, Security, and Privacy for Wearable Sensor Data. 13.1 Introduction
13.2 Threats to a BAN
13.2.1 Denial-of-service
13.2.2 Man-in-the-middle Attack
13.2.3 Phishing and Spear Phishing Attacks
13.2.4 Drive-by Attack
13.2.5 Password Attack
13.2.6 SQL Injection Attack
13.2.7 Cross-site Scripting Attack
13.2.8 Eavesdropping
13.2.9 Birthday Attack
13.2.10 Malware Attack
13.3 Data Security and Most Common Encryption Methods
13.3.1 Data Encryption Standard (DES)
13.3.2 Triple DES
13.3.3 Rivest–Shamir–Adleman (RSA)
13.3.4 Advanced Encryption Standard (AES)
13.3.5 Twofish
13.4 Quality of Service (QoS)
13.4.1 Quantification of QoS
13.4.1.1 Data Quality Metrics
13.4.1.2 Network Quality Related Metrics
13.5 System Security
13.6 Privacy
13.7 Conclusions
References
14 Existing Projects and Platforms. 14.1 Introduction
14.2 Existing Wearable Devices
14.3 BAN Programming Framework
14.4 Commercial Sensor Node Hardware Platforms
14.4.1 Mica2/MicaZ Motes
14.4.2 TelosB Mote
14.4.3 Indriya-Zigbee Based Platform
14.4.4 IRIS
14.4.5 iSense Core Wireless Module
14.4.6 Preon32 Wireless Module
14.4.7 Wasp Mote
14.4.8 WiSense Mote
14.4.9 panStamp NRG Mote
14.4.10 Jennic JN5139
14.5 BAN Software Platforms
14.5.1 Titan
14.5.2 CodeBlue
14.5.3 RehabSPOT
14.5.4 SPINE and SPINE2
14.5.5 C-SPINE
14.5.6 MAPS
14.5.7 DexterNet
14.6 Popular BAN Application Domains
14.7 Conclusions
References
15 Conclusions and Suggestions for Future Research. 15.1 Summary
15.2 Future Directions in BSN Research
15.2.1 Smart Sensors: Intelligent, Biocompatible, and Wearable
15.2.2 Big Data Problem
15.2.3 Data Processing and Machine Learning
15.2.4 Decentralised and Cooperative Networks
15.2.5 Personalised Medicine Through Personalised Technology
15.2.6 Fitting BSN to 4G and 5G Communication Systems
15.2.7 Emerging Assistive Technology Applications
15.2.8 Solving Problems with Energy Harvesting
15.2.9 Virtual World
15.3 Conclusions
References
Index
WILEY END USER LICENSE AGREEMENT
