Front Cover
MODERN METHODS FOR AFFORDABLE CLINICAL GAIT ANALYSIS
MODERN METHODS FOR AFFORDABLE CLINICAL GAIT ANALYSIS
Copyright
Contents
About the authors
Preface
Acknowledgment
1
Introduction
1.1 What is gait?
1.2 Gait cycle
1.3 Features of gait
1.3.1 Spatio-temporal
1.3.2 Kinematic
1.3.3 Kinetic
1.3.4 Anthropometric
1.3.5 Electromyography
1.4 Model-based versus model-free gait assessment
1.4.1 Model-based human gait analysis
1.4.2 Model-free human gait analysis
1.5 Applications of gait analysis

1.6 Clinical aspects of human gait
1.6.1 Gait signal segmentation
1.6.2 Pathological gait detection
1.6.3 Injury prevention and recovery prediction
1.7 Sensors for gait data acquisition
1.8 Summary
References
2
Statistics and computational intelligence in clinical gait analysis
2.1 Introduction
2.2 Statistics in clinical gait data
2.2.1 Confidence interval, p-value, and effect size
2.2.2 Statistics in clinical trials
2.2.3 Systematic review and meta-analysis
2.3 Computational intelligence in clinical gait data

2.3.1 Why computational intelligence is important?
2.3.2 Learning paradigm
2.3.3 Applications of computational intelligence in clinical gait data
2.4 Statistics versus computational intelligence
2.5 Summary
References
3
Low-cost sensors for gait analysis
3.1 Introduction
3.2 Motion capture sensors for gait
3.2.1 Classification of sensors
3.2.2 Gold standard sensors
3.2.3 Affordable sensors
3.3 Microsoft kinect
3.3.1 First and second generation
3.3.2 Hardware and software specification
3.3.3 Data streams of kinect

3.3.4 Application in clinical gait assessment
3.4 Wearable sensors
3.4.1 Inertial sensors
3.4.1.1 Types of inertial sensors
3.4.1.2 Cost analysis of inertial sensors
3.4.1.3 Applications of inertial sensor in clinical gait assessment
3.4.2 Electromyography sensors
3.4.2.1 MyoWare muscle sensor
3.4.3 Others: force sensitive resistors, goniometers
3.5 Summary
References
4
Validation study of low-cost sensors
4.1 Introduction
4.2 Kinect validation for clinical usages
4.3 Inertial sensor validation on estimating joint angles

4.3.1 Evaluation metrics for validation of estimated joint angles
4.4 Summary
References
5
Gait segmentation and event detection techniques
5.1 Introduction
5.2 Why gait cycle segmentation?
5.3 Vision sensor-based gait cycle segmentation
5.3.1 Threshold-based methods
5.3.2 Machine learning-based methods
5.4 Kinect in gait cycle segmentation
5.5 Inertial sensor-based gait segmentation
5.5.1 Threshold-based methods
5.5.2 Machine intelligence-based methods
5.6 Electromyography sensor-based gait segmentation
5.6.1 Statistical methods