Modified kNN Algorithm for Improved Recognition Accuracy of Biometrics System Based on Gait - Computer Information Systems and Industrial Management Access content directly
Conference Papers Year : 2013

Modified kNN Algorithm for Improved Recognition Accuracy of Biometrics System Based on Gait

Marcin Derlatka
  • Function : Author
  • PersonId : 1004700

Abstract

The k-nearest neighbors classifier is one of the most frequently used. It has several interesting properties, though it cannot be used in utilitarian biometric systems. This paper proposes the modification of kNN algorithm which ensures correct work even in the case of an attempt at access to the system by unauthorized people. Work of the algorithm was tested on data presenting ground reaction forces (GRF), generated during human’s walk, obtained from measurements carried out on over 140 people. Differences between particular strides were determined with the Dynamic Time Warping (DTW). The recognition precision obtained was as high as 98% of biometric samples.
Fichier principal
Vignette du fichier
978-3-642-40925-7_6_Chapter.pdf (195.2 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01496099 , version 1 (27-03-2017)

Licence

Attribution

Identifiers

Cite

Marcin Derlatka. Modified kNN Algorithm for Improved Recognition Accuracy of Biometrics System Based on Gait. 12th International Conference on Information Systems and Industrial Management (CISIM), Sep 2013, Krakow, Poland. pp.59-66, ⟨10.1007/978-3-642-40925-7_6⟩. ⟨hal-01496099⟩
139 View
548 Download

Altmetric

Share

Gmail Facebook X LinkedIn More