|
Abstract
|
|
|---|---|
| This paper describes the development of a Gait-based Person Identi?cation (GPI) system based on a Gaussian Mixture Model-Universal Background Model (GMM-UBM) approach that uses inertial signals from a smartphone. The system integrates ?ve main modules or steps: signal pre-processing, feature extraction, GMM-UBM training, Maximum A Posteriori (MAP) adaptation, and a comparison module for providing the identi?ed user. This system also integrates new feature extraction strategies proposed recently (Mel Frequency Cepstral Coe?cients (MFCCs) and Perceptual Lineal Prediction (PLP) coe?cients) for improving the results. This study has been done using the public available dataset called UCI Human Activity Recognition Using Smartphones dataset. A six-fold cross-validation procedure has been carried out, showing the average value for every experiment. The ?nal results demonstrate the capability of the GMM-UBM approach for gait recognition, and show how the PLP coe?cients can improve system performance while reducing drastically the number of features (from 561 to 90). The best result shows a User Recognition Error Rate of 34.0% with 30 enrolled users. When reducing the number of enrolled users, the error rate decreases: for a number smaller than six, the URER error becomes lower than 10%. | |
|
International
|
Si |
|
JCR
|
Si |
|
Title
|
Pattern Recognition Letters |
|
ISBN
|
0167-8655 |
|
Impact factor JCR
|
1,586 |
|
Impact info
|
|
|
Volume
|
73 |
|
|
|
|
Journal number
|
|
|
From page
|
60 |
|
To page
|
67 |
|
Month
|
SIN MES |
|
Ranking
|
Journal Rank in Category 59/130; Quartile in Category Q2 |