Anzeige
Erschienen in:
2014 | OriginalPaper | Buchkapitel
Wrist-Worn Accelerometer to Detect Postural Transitions and Walking Patterns
verfasst von : V. Ahanathapillai, J. D. Amor, M. Tadeusiak, C. J. James
Erschienen in: XIII Mediterranean Conference on Medical and Biological Engineering and Computing 2013
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by (Link öffnet in neuem Fenster)
The identification of postural transitions and walking patterns are important in the recognition of activities of daily living. This paper presents a feasibility study to see if postural transitions and walking patterns can be identified using a wrist-worn accelerometer-based device. Firstly, the postural transition (i.e. sit-to-stand and stand-to-sit) templates are extracted and template matching is used to identify the transitions between daily living activities such as walking within a house. Secondly, the various walking patterns such as walking on a level surface, walking up the stairs and walking down the stairs are classified using statistical features and nearest neighbor classifier. A comparison between the activity pattern from the dominant wrist and the non-dominant wrist is also presented.