Abstract | ||
---|---|---|
Identifying users of portable devices from gait signal acquired with three-dimensional accelerometers was studied. Three approaches, correlation, frequency domain and data distribution statistics were used. Test subjects (N=36) walked with fast, normal and slow walking speeds in enrolment and test sessions on separate days wearing the accelerometer device on their belt, at back. Identifying the users with this novel gait recognition method showed to be possible. Best equal error rate (EER=7%) was achieved with signal correlation method, while frequency domain method and two variations of data distribution statistics method produced EER of 10%, 18% and 19%, respectively. |
Year | DOI | Venue |
---|---|---|
2005 | 10.1109/ICASSP.2005.1415569 | 2005 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1-5: SPEECH PROCESSING |
Keywords | Field | DocType |
gait analysis,pattern recognition,fingerprint recognition,testing,frequency domain analysis,object recognition,statistical analysis,three dimensional,signal processing,statistical distributions,accelerometers,frequency domain,biometrics | Frequency domain,Signal processing,Computer vision,Pattern recognition,Gait,Computer science,Accelerometer,Word error rate,Probability distribution,Gait analysis,Artificial intelligence,Preferred walking speed | Conference |
ISSN | Citations | PageRank |
1520-6149 | 150 | 10.30 |
References | Authors | |
9 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jani Mäntyjärvi | 1 | 780 | 84.00 |
Mikko Lindholm | 2 | 316 | 26.41 |
Elena Vildjiounaite | 3 | 347 | 32.45 |
Satu-Marja Mäkelä | 4 | 325 | 27.34 |
Heikki Ailisto | 5 | 347 | 29.72 |