Spatial footstep recognition by convolutional neural networks for biometrie applications

Biblos-e Archivo/Manakin Repository

Biblos-e Archivo

Spatial footstep recognition by convolutional neural networks for biometrie applications

Metadatos
Title: Spatial footstep recognition by convolutional neural networks for biometrie applications
Author: Costilla-Reyes, Omar; Vera-Rodriguez, Rubén; Scull, Patricia; Ozanyan, Krikor B.
Entity: UAM. Departamento de Tecnología Electrónica y de las Comunicaciones
Publisher: Institute of Electrical and Electronics Engineers Inc
Date: 2016
Citation: IEEE Sensors Conference, SENSORS 2016. IEEE, 2016. 1-3
ISSN: 1930-0395
ISBN: 978-147998287-5
DOI: 10.1109/ICSENS.2016.7808890
Subjects: Pattern recognition; Machine learning; Convolutional neural networks; Gait analysis; Floor sensor system; Telecomunicaciones
URI: http://hdl.handle.net/10486/678841
Rights: © 2016 IEEE

Abstract:

We propose a Convolutional Neural Network model to learn spatial footstep features end-to-end from a floor sensor system for biometric applications. Our model’s generalization performance is assessed by independent validation and evaluation datasets from the largest footstep database to date, containing nearly 20,000 footstep signals from 127 users. We report footstep recognition performance as Equal Error Rate in the range of 9% to 13% depending on the test set. This improves previously reported footstep recognition rates in the spatial domain up to 4% EER

Show full item record

Files in this item

Thumbnail
Name: spatial_costilla_ ...
Size: 287.7Kb
Format: PDF
Share

Delicious Save this on Delicious

Citations
G o o g l e ™ Scholar: Costilla-Reyes, Omar - Vera-Rodriguez, Rubén - Scull, Patricia - Ozanyan, Krikor B.

This item appears in the following Collection(s)