Smartwatch-based gait biometrics

Smartwatch-based gait biometrics

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

Buy chapter PDF
(plus tax 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:
Mobile Biometrics — Recommend this title to your library

Thank you

Your recommendation has been sent to your librarian.

Although a reliable implementation of a smartwatch-based gait biometric system would usher in a new era of transparent authentication, the creation of such a system would not be without its own ethical problems. A primary problem of passwords is that users tend to reuse a small set of passwords (or, more realistically a single password; a primary responsibility (at least in the eyes of the commercial cybersecurity world) of biometrics is to replace these systems for that very reason (among others). The problem with an effective gait biometric system-much like many other forms of biometrics-is that once a user's training data is provided to the system that system can effectively impersonate that user; in essence, “reuse” is unavoidable. Thus, it becomes the responsibility of those designing gait biometric systems to create systems that are resistant to replay-style attacks. Similarly, work has to be done to ensure that the sensitive data collected from the smartwatch's sensors is not left in memory (where it could be recovered forensically or by a malicious application); much as traditional systems work to secure passwords. Gait biometrics might be the future of transparent authentication, but that does not allow conventional cybersecurity wisdom to be forgotten.

Chapter Contents:

  • 9.1 Introduction
  • 9.2 Smartwatch hardware
  • 9.3 Biometric tasks: identification and authentication
  • 9.3.1 Identification
  • Closed-set identification
  • Open-set identification
  • 9.3.2 Authentication
  • 9.4 Data preprocessing
  • 9.4.1 Segmentation
  • 9.4.2 Segment selection
  • 9.5 Selecting a feature set
  • 9.5.1 Statistical features
  • 9.5.2 Histogram-based features
  • 9.5.3 Cycle-based features
  • 9.5.4 Time domain
  • 9.5.5 Summary
  • 9.6 System evaluation and testing
  • 9.6.1 Selecting an evaluation metric
  • 9.6.2 Single-instance evaluation and voting schemes
  • 9.7 Template aging: an implementation challenge
  • 9.8 Conclusion
  • References

Inspec keywords: biometrics (access control); mobile computing; message authentication; gait analysis

Other keywords: gait biometric system; transparent authentication; replay-style attacks; smartwatch

Subjects: Ubiquitous and pervasive computing; Data security

Preview this chapter:
Zoom in

Smartwatch-based gait biometrics, Page 1 of 2

| /docserver/preview/fulltext/books/sc/pbse003e/PBSE003E_ch9-1.gif /docserver/preview/fulltext/books/sc/pbse003e/PBSE003E_ch9-2.gif

Related content

This is a required field
Please enter a valid email address