Linear predictive modelling of gait patterns

Ronny K. Ibrahim, Eliathamby Ambikairajah, Branko G. Celler, Nigel H. Lovell

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionpeer-review

3 Citations (Scopus)

Abstract

The use of a wearable triaxial accelerometer for unsupervised monitoring of human movement has become a major research focus in recent years. In this paper, the relationship between accelerometry signals and human gait is analysed using a linear prediction (LP) model. We explore the use of the LP model for analysing five gait patterns and show that the LP cepstrum can be used for gait pattern classification with high accuracy. This is then compared to a filterbank based approach to estimate the cepstral coefficients. Fifty subjects participated in collection of gait pattern data involving walking on level surfaces, and walking up and down stairs and ramps. The results show that an overall accuracy of 93% can be achieved using features derived from the cepstral coefficients for the five different walking patterns.

Original languageEnglish
Title of host publication2009 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2009
Subtitle of host publicationProceedings
Place of PublicationPiscataway, NJ
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages425-428
Number of pages4
ISBN (Electronic)9781424423545
ISBN (Print)9781424423538
DOIs
Publication statusPublished - 2009
Externally publishedYes
Event2009 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2009 - Taipei, Taiwan, Province of China
Duration: 19 Apr 200924 Apr 2009

Other

Other2009 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2009
CountryTaiwan, Province of China
CityTaipei
Period19/04/0924/04/09

Keywords

  • Gait classification
  • Gait modelling

Fingerprint Dive into the research topics of 'Linear predictive modelling of gait patterns'. Together they form a unique fingerprint.

Cite this