Wearable Systems Based Gait Monitoring and Analysis provides a thorough overview of wearable gait monitoring techniques and their use in health analysis. The text starts with an examination of the relationship between the human body’s physical condition and gait, and then introduces and explains nine mainstream sensing mechanisms, including piezoresistive, resistive, capacitive, piezoelectric, inductive, optical, air pressure, EMG and IMU-based architectures. Gait sensor design considerations in terms of geometry and deployment are also introduced. Diverse processing algorithms for manipulating sensors outputs to transform raw data to understandable gait features are discussed. Furthermore, gait analysis-based health monitoring demonstrations are given at the end of this book, including both medical and occupational applications. The book will enable students of biomedical engineering, electrical engineering, signal processing, and ergonomics and practitioners to understand the medical and occupational applications of engineering-based gait analysis and falling injury prevention methods.
Author(s): Shuo Gao; Junliang Chen; Yanning Dai; Boyi Hu
Publisher: Springer Nature
Year: 2022
Language: English
Pages: 244
Preface
Acknowledgments
Contents
About the Authors
Chapter 1: Introduction
References
Chapter 2: Gait Characteristics
2.1 Physical Parameters of Gait
2.1.1 Time Parameters
2.1.1.1 Stance Phase
2.1.1.2 Swing Phase
2.1.2 Mechanical Parameters
2.1.3 Spatial Parameters
2.1.4 Electrical Parameters
2.2 The Influences of Age, Occupation, and Disease on Gait
2.2.1 Age-Related Gait Changes
2.2.1.1 Gait Changes in Children
2.2.1.2 Gait Changes in the Elderly
2.2.2 Occupation-Related Gait Changes
2.2.2.1 Physical Labor Burden
2.2.2.2 Chronic Knee Strain
2.2.2.3 Prolonged Standing
2.2.2.4 Sedentariness
2.2.3 Disease-Related Gait Changes
2.2.3.1 Low-Level Peripheral Motor Organ Abnormalities
2.2.3.2 Medium-Level Motor Sensory Pathway Abnormalities
2.2.3.3 High-Level Nerve Control Abnormalities
Chapter 3: Gait Detection Technologies
3.1 Footprint and Bulky Systems
3.1.1 Footprint
3.1.2 Force Platforms
3.1.3 Motion Capture System
3.2 Wearable Systems
3.2.1 Wearable Plantar Pressure Detection Systems
3.2.1.1 Insole Sensor Design
Resistive-Based Techniques
Capacitive-Based Sensors
Piezoelectric-Based Sensors
Inductive-Based Sensors
Optical-Based Sensors
Air-Pressure-Based Sensors
Comparison of Plantar Stress Sensing Techniques
3.2.1.2 Layout of the Sensing Elements
Sensor Size
Sensor Layout
3.2.2 IMU-Based Systems
3.2.2.1 Wearable Inertial Measurement Unit
Independent Measuring Devices
IMU Calibration Methods
Zero-Velocity Update (ZUPT)
GPS-Based Sensors
Distance Measurement-Based Sensors
3.2.2.2 Arthrokinematics Calculation
The 2D Arthrokinematics Case
The 3D Arthrokinematics Case
Alignment of Sensing Direction of Inertial Component and Skeleton Orientation
3.2.2.3 Conclusions
3.2.3 EMG-Based Systems
3.2.3.1 Electrodes
Electrodes Forms and Implant Methods
Detected Muscle Selection
Front-End Acquisition Circuit
3.2.3.2 Readout and Transmission Circuit
Chapter 4: Gait Analysis Algorithms
4.1 Plantar Pressure Distribution Interpretation
4.1.1 Plantar Stress Distribution Reconstruction
4.1.1.1 Fitting
4.1.1.2 Compressed Sensing
4.1.1.3 Machine Learning
4.1.2 Pressure-Related Parameters Extraction
4.1.2.1 Direct Means
4.1.2.2 Calculation with Machine Learning
4.1.3 The Registration of Plantar Pressure Mapping
4.1.4 Classification Algorithms
4.2 EMG Pattern Recognition
4.2.1 Denoising Algorithms
4.2.1.1 Wavelet Analysis-Based Methods
Discrete Wavelet Transform (DWT) Method
Wavelet Time-frequency Analysis
4.2.1.2 EMG Signal Denoising Based on Empirical Mode Decomposition (EMD)
4.2.2 Feature Extraction and Dimensionality Reduction Algorithms
4.2.2.1 Feature Extraction
4.2.2.2 Dimensionality Reduction
Feature Projection
Feature Selection
4.2.3 Classification Algorithms
4.3 IMU-Based Motion Classification Algorithms
4.3.1 Feature Extraction and Dimensionality Reduction Algorithms
4.3.1.1 Feature Extraction
4.3.1.2 Dimensionality Reduction
4.3.2 Classification Algorithms
4.3.2.1 Traditional Machine Learning Algorithms
4.3.2.2 Deep Learning Algorithms
4.3.3 Motion Simulation and Generation Algorithms
4.3.3.1 Motion Simulation Algorithms
Motion Sequence Representation
Motion Optimization
4.3.3.2 Data-Driven Motion Generation Algorithms
Motion Graph-Based Methods
Deep Learning-Based Methods
4.3.3.3 Physics-Driven Motion Generation Algorithms
Dynamics-Based Methods
Biomechanics-Based Methods
4.3.3.4 Data-Physics Hybrid Driven Motion Generation Algorithms
4.4 Multi-sensory Fusion
4.4.1 Plantar Pressure with EMG
4.4.2 Plantar Pressure with IMU
4.4.3 IMU with EMG
4.4.4 Fusion of Plantar Pressure, IMU, and EMG Sensors
4.4.5 Two Case Studies of Multisensory Fusion
4.4.5.1 Methodology
Experiment Setup
Data Pre-processing
Feature Extraction
Establishment of SVM Model
Evaluation of the Selected Features and the SVM Model
4.4.5.2 Results and Discussions
EMG and GRF Profiles
Statistical Features in Different Terrains
Training Performance of SVM and Comparison Between the EMG and GRF Features
4.4.5.3 Methodology
System Integration
Algorithm Development
Experimental Protocol
4.4.5.4 Result and Discussion
Hardware Performance
Algorithm Performance
Chapter 5: Medical Applications
5.1 Neural Disease Analysis
5.1.1 Parkinson
5.1.2 Diabetes
5.1.3 Cerebral Palsy
5.1.4 Cerebellar Ataxia
5.1.5 Others
5.2 Orthopaedic Disease Analysis
5.2.1 Flatfoot
5.2.2 Knee Osteoarthritis
5.2.3 Low Back Pain
5.2.4 Total Joint Replacement
5.3 Rehabilitation Progress Tracking
5.3.1 Post-stroke Rehabilitation Tracking
5.3.2 Falling Risk Prediction
5.3.3 Mental Illness Rehabilitation Tracking
5.4 The Internet of Health Things
Chapter 6: Conclusion
6.1 PSD
6.2 IMU
6.3 EMG
Index
