Smart Wireless Sensing: From IoT to AIoT

✍ Scribed by Zheng Yang, Kun Qian, Chenshu Wu, Yi Zhang

• Publisher: Springer
• Year: 2021
• Tongue: English
• Leaves: 238
• Edition: 1
• Category: Library

✦ Synopsis

Perception of human beings has evolved from natural biosensor to powerful sensors and sensor networks. In sensor networks, trillions of devices are interconnected and sense a broad spectrum of contexts for human beings, laying the foundation of Internet of Things (IoT). However, sensor technologies have several limitations relating to deployment cost and usability, which render them unacceptable for practical use. Consequently, the pursuit of convenience in human perception necessitates a wireless, sensorless and contactless sensing paradigm.

Recent decades have witnessed rapid developments in wireless sensing technologies, in which sensors detect wireless signals (such as acoustic, light, and radio frequency) originally designed for data transmission or lighting. By analyzing the signal measurements on the receiver end, channel characteristics can be obtained to convey the sensing results. Currently, significant effort is being devoted to employing the ambient Wi-Fi, RFID, Bluetooth, ZigBee, and television signals for smart wireless sensing, eliminating the need for dedicated sensors and promoting the prospect of the Artificial Intelligence of Things (AIoT).

This book provides a comprehensive and in-depth discussion of wireless sensing technologies. Specifically, with a particular focus on Wi-Fi-based sensing for understanding human behavior, it adopts a top-down approach to introduce three key topics: human detection, localization, and activity recognition. Presenting the latest advances in smart wireless sensing based on an extensive review of state-of-the-art research, it promotes the further development of this area and also contributes to interdisciplinary research.

✦ Table of Contents

Preface
Organization of the Book
Anticipated Audience
Acknowledgments
Contents
About the Authors
Acronyms
Part I The Background
1 Wireless Sensing Overview
1.1 What Is Wireless Sensing?
1.2 Applications of Wireless Sensing
1.3 Challenges of Wireless Sensing
1.3.1 Representative Signal Feature
1.3.2 Effective Recognition Model
1.3.3 Informative Dataset
References
2 Understanding of Channel State Information
2.1 Definition of CSI
2.2 Noise in CSI
2.3 Signal Features in CSI
2.3.1 Time of Flight
2.3.2 Angle of Arrival and Angle of Departure
2.3.3 Doppler Frequency Shift
2.4 CSI Data Collection
2.4.1 Intel 5300 NIC CSI Tool
2.4.2 Atheros-CSI-Tool
2.4.3 PicoScenes Platform
References
Part II Detection: Passive Human Detection with Wireless Signals
3 Passive Human Detection with Wi-Fi
3.1 Introduction
3.2 Preliminaries
3.2.1 The Omnidirectional Passive Human Detection Problem
3.2.2 Signal Power Features
3.3 Feature Extraction and Classification
3.3.1 Sensitivity to Human Presence
3.3.2 Resistance to Environmental Dynamics
3.3.3 Modeling CFR Amplitude Features
3.3.4 Signature Classification
3.4 Human Detection
3.5 Performance
3.5.1 Experiment Methodology
3.5.2 Static Detection Performance
3.5.3 The Impact of Window Size
3.5.4 Mobile Detection Performance
3.6 Related Work
3.7 Conclusion
References
4 Passive Detection of Moving Targets with Dynamic Speed Using Wi-Fi
4.1 Introduction
4.2 Related Works
4.3 Overview
4.4 Methodology
4.4.1 Data Preprocessing
4.4.1.1 Phase Sanitization
4.4.1.2 Outlier Filter
4.4.2 Feature Extraction
4.4.3 Motion Detection
4.4.4 Enhancement Via Multiple Antennas
4.5 Experiments and Evaluation
4.5.1 Experimental Setup
4.5.2 Performance Evaluation
4.5.2.1 Evaluation Metric
4.5.2.2 Overall Performance
4.5.2.3 Impacts of Sliding Window Size
4.5.2.4 Impacts of Number of Features
4.5.2.5 Impacts of Number of Antennas
4.5.2.6 Performance Against Dynamic Speed
4.6 Conclusion
References
5 Passive Detection of Moving and Stationary Human with Wi-Fi
5.1 Introduction
5.2 Related Works
5.3 Preliminary
5.4 System Design
5.4.1 Overview
5.4.2 Motion Interference Indicator
5.4.3 Moving Target Detection
5.5 Stationary Target Detection
5.5.1 Periodic Alterations from Breathing
5.5.2 Breathing Detection
5.5.2.1 Signal Filter
5.5.2.2 Sinusoidal Model
5.5.2.3 Parameter Estimation
5.5.3 Embracing Frequency Diversity
5.6 Experiments and Evaluation
5.6.1 Implementation
5.6.1.1 Experimental Environments
5.6.1.2 Experimental Methodology
5.6.1.3 Evaluation Metrics
5.6.2 Performance
5.6.2.1 Performance of Detecting Moving Human
5.6.2.2 Performance of Detecting Static Human
5.6.2.3 Putting It All Together
5.7 Discussions and Future Works
5.7.1 Monitoring Breathing Rate
5.7.2 Expanding Detection Coverage Via Space Diversity
5.7.3 Multiple Target Detection
5.7.4 Extending to Through-Wall Detection
5.8 Conclusions
References
Part III Localization: Passive Human Localization with Wireless Signals
6 Decimeter-Level Passive Human Tracking with Multiple Wi-Fi Links
6.1 Introduction
6.2 Preliminary
6.2.1 Channel State Information
6.2.2 From CSI to PLCR
6.2.3 Challenges for Tracking
6.3 Modeling of CSI-Mobility
6.3.1 The Ideal Model
6.3.2 The Real Model
6.4 PLCR Extraction
6.4.1 CSI Preprocessing
6.4.2 PLCR Extraction Algorithm
6.4.3 PLCR Sign Identification
6.5 Tracking Velocity and Location
6.5.1 Movement Detection
6.5.2 Initial Location Estimation
6.5.3 Successive Tracking
6.5.4 Trace Refinement
6.6 Evaluation
6.6.1 Experiment Methodology
6.6.2 Overall Performance
6.6.3 Parameter Study
6.7 Related Work
6.8 Conclusion
References
7 Decimeter-Level Passive Human Tracking with a Single Wi-Fi Link
7.1 Introduction
7.2 Overview
7.3 Motion in CSI
7.3.1 CSI-Motion Model
7.3.2 Joint Multiple Parameter Estimation
7.3.3 CSI Cleaning
7.4 Localization
7.4.1 Path Matching
7.4.2 Range Refinement
7.4.3 Localization Model
7.5 Evaluation
7.5.1 Experiment Methodology
7.5.2 System Performance
7.5.3 Parameter Study
7.6 Discussion
7.7 Related Work
7.8 Conclusion
References
Part IV Recognition: Passive Human Activity Recognition with Wireless Signals
8 Inferring Motion Direction with Wi-Fi
8.1 Introduction
8.2 System Overview
8.3 Doppler Effect in Wi-Fi
8.3.1 Doppler Effect
8.3.2 Doppler Effect in CSI
8.3.3 Doppler Effect by Multiple Antennas
8.3.4 Extraction of Doppler Effect
8.4 Motion Recognition
8.4.1 Player Reaction in Doppler Effect
8.4.2 Motion Recognition Workflow
8.5 Evaluation
8.5.1 Experiment Methodology
8.5.2 Performance
8.5.3 Parameter Study
8.6 Limitations and Discussion
8.7 Related Work
8.8 Conclusion
References
9 Human Gesture Recognition with Wi-Fi
9.1 Introduction
9.2 Motivation
9.3 System Overview
9.4 Body Coordinate Velocity Profile
9.4.1 Doppler Representation of CSI
9.4.2 From DFS to BVP
9.4.3 BVP Estimation
9.4.4 Location and Orientation Prerequisites
9.5 Recognition Mechanism
9.5.1 BVP Normalization
9.5.2 Spatial Feature Extraction
9.5.3 Temporal Modeling
9.6 Evaluation
9.6.1 Experiment Methodology
9.6.2 Overall Accuracy
9.6.3 Cross-Domain Evaluation
9.6.4 Method Comparison
9.6.5 Parameter Study
9.7 Discussions
9.8 Related Work
9.9 Conclusion
References
10 Human Gait Recognition with Wi-Fi
10.1 Introduction
10.2 Related Work and Motivation
10.3 System Design
10.3.1 GBVP Extraction
10.3.2 Recognition Mechanism
10.4 Evaluation
10.4.1 Experimental Methodology
10.4.2 Overall Performance
10.4.3 Generalizability Evaluation
10.4.4 Parameter Study
10.5 Conclusion
References
Part V Conclusions
11 Research Summary and Future Directions
11.1 Summary
11.2 Open Issues