Human-movement identification using the radio signal strength in WBAN

Human-movement identification using the radio signal strength in WBAN

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.

In this chapter, an intensive study of a novel human movement identification scheme using the radio signal strength in wireless body area network (WBAN) is presented. Since the WBAN channel characteristics are highly influenced by the human movement, the radio signal strength and its temporal variation can be used to determine the human movement without additional tools such as an accelerometer/gyroscope. This study included the process of developing the human movement identification system, performance assessment on different conditions including a vector size of the received signal levels, an antenna orientation, a classifier training algorithm, and a receiver location. It was found that the vector size of the received signal levels and the receiver location had strong impact on the identification accuracy. More than 80% of the identification accuracy can be achieved when using 30-40 received signal levels or the receiver location at thigh or upper arm. In addition, a feature selection method based on a correlation coefficient was used to remove redundant and less informative features. The classification results show that the comparable performance to the all feature vectors can be achieved by the subset feature vector with a lower computational cost.

Chapter Contents:

  • 6.1 Introduction
  • 6.2 Related works
  • 6.3 Human motion classification system
  • 6.4 Data collection
  • 6.4.1 Measurement campaign
  • 6.4.2 Measurement results
  • 6.5 Data preprocessing
  • 6.5.1 Mean normalization
  • 6.5.2 Segmentation
  • 6.5.3 Feature extraction
  • Feature computation
  • Optimal threshold selection
  • 6.5.4 Feature scaling
  • 6.6 Classifier training
  • 6.6.1 k-Nearest neighbor
  • 6.6.2 Support vector machine
  • 6.6.3 Decision tree
  • 6.7 Classifier validation
  • 6.7.1 Validation metrics
  • 6.7.2 Validation results
  • Window size of the segmentation
  • Receiver location on human body
  • Classifier algorithm
  • Pair of Tx – Rx antennas
  • 6.8 Subset feature selection
  • 6.8.1 Feature selection method
  • 6.8.2 Evaluation of the subset feature vector compared to the all feature vector
  • 6.9 Summary
  • References

Inspec keywords: feature extraction; accelerometers; gyroscopes; body area networks; learning (artificial intelligence)

Other keywords: wireless body area network; WBAN channel characteristics; receiver location; human movement identification scheme; human movement identification system; radio signal strength; vector size; human-movement identification; 30-40 received signal levels; identification accuracy

Subjects: Radio links and equipment; Other topics in statistics; Knowledge engineering techniques; Other topics in statistics; Computer vision and image processing techniques; Biology and medical computing

Preview this chapter:
Zoom in

Human-movement identification using the radio signal strength in WBAN, Page 1 of 2

| /docserver/preview/fulltext/books/he/pbhe011e/PBHE011E_ch6-1.gif /docserver/preview/fulltext/books/he/pbhe011e/PBHE011E_ch6-2.gif

Related content

This is a required field
Please enter a valid email address