Sensory data fusion of pressure mattress and wireless inertial magnetic measurement units.

Head movement of infants is an important parameter for analysing infant motor patterns. Despite its importance, this field has received little sensory-based research in the past years. Therefore, we present a sensory-supported data fusion model for head movement analysis of infants in supine positio...

Descripción completa

Detalles Bibliográficos
Publicado en:Medical & Biological Engineering & Computing Vol. 53; no. 2; pp. 123 - 136
Autores principales: Rihar, Andraz, Mihelj, Matjaz, Kolar, Janko, Pasic, Jure, Munih, Marko, Rihar, Andraž, Mihelj, Matjaž, Pašič, Jure
Formato: research Journal Article
Publicado: Springer Nature Feb2015
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=109775341&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 109775341
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        01400118
        PO0
      jtl: Medical & Biological Engineering & Computing
      issn: 01400118
      maglogo: N
    pubinfo:
      dt: Feb2015
      vid: 53
      iid: 2
      pid: 237
      pub: Springer Nature
      place: New York, New York
    artinfo:
      ui:
        109775341
        NLM25367736
        2012885913
        10.1007/s11517-014-1217-z
        NLM25367736
        109775341
      ppf: 123
      ppct: 13
      formats:
        fmt:
          @attributes:
            type: P
      tig:
        atl: Sensory data fusion of pressure mattress and wireless inertial magnetic measurement units.
      aug:
        au:
          Rihar, Andraz
          Mihelj, Matjaz
          Kolar, Janko
          Pasic, Jure
          Munih, Marko
          Rihar, Andraž
          Mihelj, Matjaž
          Pašič, Jure
        affil: Laboratory of Robotics, Faculty of Electrical Engineering, University of Ljubljana, Ljubljana, Slovenia
      sug:
        subj:
          Bar Coding Methods
          Movement Physiology
          Motor Activity Physiology
          Supine Position Physiology
          Algorithms
          Computer Simulation
          Head Physiology
          Human
          Infant
          Physical Sciences
          Magnetics Methods
          Orientation
          Pressure
          Videorecording
          Infant: 1-23 months
      ab: Head movement of infants is an important parameter for analysing infant motor patterns. Despite its importance, this field has received little sensory-based research in the past years. Therefore, we present a sensory-supported data fusion model for head movement analysis of infants in supine position. The sensory system comprises a pressure mattress and two wireless inertial magnetic measurement units, rendering precise, objective and non-intrusive information on pressure distribution and 3D trunk orientation, respectively. Algorithms first perform pressure data pre-processing and calculate image moments to acquire 2D trunk orientation. Afterwards, unscented Kalman filter is used for sensory data fusion. After additional data processing, head and trunk coordinates are calculated along with head displacement distance. The sensory system was tested on experimental measurements, performed in eight normally developing infants aged from 1 to 5 months. Results of several algorithm combinations were compared to referential video recordings in terms of head lifts. Combination of algorithms, incorporating head tracking and sensory data fusion provides completely accurate results in comparison to normative data. Statistical data analysis and referential optoelectronic measurements were performed to evaluate accuracy of the sensory fusion model. Suitability of the proposed sensory system for head movement analysis of infants in supine position was verified.
      pubtype: Academic Journal
      doctype:
        research
        Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N