Identity verification of humans performing physical activities

From ISLAB/CAISR
Title Identity verification of humans performing physical activities
Summary To verify the identity of an individual performing a particular activity with sensors placed at different parts of the body
Keywords
TimeFrame
References Mohammad Derawi, Patrick Bours, Gait and activity recognition using commercial phones, Computers & Security, Volume 39, Part B, November 2013, Pages 137-144

Ailisto, Heikki J., et al. "Identifying people from gait pattern with accelerometers." Defense and Security. International Society for Optics and Photonics, 2005.

Prerequisites Background in signal analysis and programming are required. Interest in inertial sensors is a bonus.
Author
Supervisor Siddhartha Khandelwal, Fernando Alonso-Fernandez, Nicholas Wickström
Level Master
Status Open

Generate PDF template

Background: The combination of gait and activity recognition as a biometric is a relatively new area of study. Research on accelerometer-based gait recognition started around 2005. In the initial stages, dedicated accelerometers were used and worn on different body parts like the hip, arm, chest, or ankle. The optimal position to attach the sensor is still an open problem.

Project Description: The goal is to develop an algorithm that can verify the identity of an individual from accelerometers positioned on different body parts like the hip, arm, chest, or ankle; while performing different activities. Additionally, we will evaluate the optimum sensor placement for the above.

Activity Plan: The suggested project could be specified in the following work packages:

WP1 Study the state of the art for identity recognition algorithms using accelerometers.

WP2 Develop the algorithm for the aforementioned goal.

WP3 Evaluate the optimum sensor placement for the task and suggest possible placement combinations.