Sign In

Communications of the ACM

ACM TechNews

A New Artificial Neural Network Framework for Gait-Based Biometrics

View as: Print Mobile App Share:
A typical 3-tier body sensor network-based healthcare system.

Researchers at Imperial College London have recently devised a biometric cryptosystem approach for securing the wireless communications of wearable and implantable medical devices.

Credit: Sun & Lo

Researchers at Imperial College London in the U.K. have developed an approach for securing wireless communications of wearable and implantable medical devices.

Their biometric cryptosystem (BCS) framework uses an artificial neural network (ANN) and gait signal energy variations to analyze the way in which different people walk.

The researchers used the ANN to extract features from body sensor networks, generating binary keys on demand, without requiring the user's intervention.

The team tested the approach on a gait dataset, and found the binary keys generated had high entropy for all subjects.

The team says the system has significant potential as a biometric security tool, and could eventually help to better protect data collected by wearable and implantable devices.

Imperial College London's Yingnan Sun says, "In the near future, we would like to further improve the performance of our proposed security scheme incorporating other signals."

From Tech Xplore
View Full Article


Abstracts Copyright © 2018 Information Inc., Bethesda, Maryland, USA


No entries found

Sign In for Full Access
» Forgot Password? » Create an ACM Web Account