Implementation study of wearable sensors for human activity recognition systems

Implementation study of wearable sensors for human activity recognition systems

For access to this article, please select a purchase option:

Buy chapter PDF
(plus tax if applicable)
Buy Knowledge Pack
10 chapters for $120.00
(plus taxes if applicable)

IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.

Learn more about IET membership 

Recommend Title Publication to library

You must fill out fields marked with: *

Librarian details
Your details
Why are you recommending this title?
Select reason:
Wearable Technologies and Wireless Body Sensor Networks for Healthcare — Recommend this title to your library

Thank you

Your recommendation has been sent to your librarian.

This chapter addresses a number of activity recognition methods for a wearable sensor system. Three methods for data transmission, namely `stream-based', `feature-based' and `threshold-based' scenarios are applied to study the accuracy against energy efficiency of transmission and processing power that affects the mote's battery lifetime. The impact of variation of sampling frequency and data transmission rate on energy consumption of motes is also analysed for each method. This study leads the authors to propose a cross-layer optimisation of an activity recognition system for provisioning acceptable levels of accuracy and energy efficiency.

Chapter Contents:

  • 4.1 Introduction
  • 4.2 Application requirements
  • 4.2.1 Sensory information
  • Privacy
  • Sensor hardware and measurement circuits
  • Sensor characteristics
  • Types of sensor for HAR systems
  • Number of sensors and sensor placement
  • Adjusting sampling rate
  • Sensor limitations
  • 4.2.2 Data collection phase
  • Controlled/supervised
  • Uncontrolled/unsupervised
  • Controlled vs. uncontrolled
  • 4.2.3 Activity set
  • 4.2.4 Energy consumption
  • Sources of energy consumption
  • Energy-efficient design
  • 4.2.5 Processing
  • 4.2.6 Obtrusiveness and user's quality of experience
  • 4.2.7 Trade-offs
  • 4.3 Recognition architecture
  • 4.3.1 Sensor data acquisition and preprocessing
  • 4.3.2 Data segmentation
  • Sliding window
  • Energy-based segmentation
  • Additional sensors and contextual sources
  • Top-down
  • Bottom-up
  • 4.3.3 Feature extraction
  • Intuitive approach
  • Statistical approach
  • Wavelet approach
  • 4.3.4 Feature selection
  • Filter approach
  • Wrapper approach
  • Embedded approach
  • 4.3.5 Classification methods
  • Threshold-based classification
  • Machine learning
  • Transfer learning
  • Deep learning
  • 4.3.6 Evaluating HAR systems
  • Performance metrics
  • Error analysis
  • 4.4 Communication platforms
  • 4.4.1 Tier-1
  • 4.4.2 Tier-2
  • 4.4.3 Tier-3
  • 4.5 HAR open problems
  • 4.5.1 Recognition challenges
  • 4.5.2 Hardware challenges
  • 4.5.3 Communication challenges
  • 4.6 Summary
  • References

Inspec keywords: health hazards; assisted living; optimisation; patient monitoring; wireless sensor networks

Other keywords: mote; activity recognition system; energy efficiency; sampling frequency; activity recognition methods; wearable sensors; wearable sensor system; implementation study; data transmission; processing power; threshold-based scenarios; human activity recognition systems

Subjects: Biology and medical computing; Optimisation techniques; Wireless sensor networks; Biomedical engineering; Optimisation techniques

Preview this chapter:
Zoom in

Implementation study of wearable sensors for human activity recognition systems, Page 1 of 2

| /docserver/preview/fulltext/books/he/pbhe011e/PBHE011E_ch4-1.gif /docserver/preview/fulltext/books/he/pbhe011e/PBHE011E_ch4-2.gif

Related content

This is a required field
Please enter a valid email address