加速度センサを用いた日常行動識別におけるデータ収集条件の識別性能への影響評価  [in Japanese] Evaluation of data collection parameters on the daily activity classification with accelerometers  [in Japanese]

Search this Article

Author(s)

Abstract

加速度センサを用いた人の日常行動識別の性能を向上させるために,我々は加速度センサの装着数と装着箇所とサンプリング周波数の識別性能への影響に関する評価実験を行った.その結果,10種類の日常行動に関して,両手首と両足首の4箇所に加速度センサを装着し,識別器としてサポートベクターマシンを用いた際に識別率89.8%を得た.また,同一の装着位置と識別器において,50Hzから12.5Hzまでダウンサンプリングしたデータに関しても識別率88.9%を得た.これらの結果はセンサの装着個数の削減によるユーザの負担の軽減,サンプリング周波数の低下による長時間バッテリ駆動に貢献する.

In order to improve the daily activity classification with accelerometers, we have evaluated how the daily activity classification performance depends on 1) the number of sensors and their positions and 2) the sampling frequency. We have obtained the result that the classification performance of 10 kinds of daily activity is 89.8% when the accelerometers are installed in four places (the both hands neck and both ankles) and SVM (Support Vector Machine) is used as a classifier. We have also obtained the result that the classification performance is 88.9% for the same accelerometer data except that they have been re-sampled from 50Hz to 12.5Hz. These results can be reflected to the wearable sensor design with less user load and longer working time.

Journal

  • IEICE technical report

    IEICE technical report 106(73), 43-48, 2006-05-21

    The Institute of Electronics, Information and Communication Engineers

References:  11

Cited by:  3

Codes

  • NII Article ID (NAID)
    110004738470
  • NII NACSIS-CAT ID (NCID)
    AN10541106
  • Text Lang
    JPN
  • Article Type
    Journal Article
  • ISSN
    09135685
  • NDL Article ID
    7939804
  • NDL Source Classification
    ZN33(科学技術--電気工学・電気機械工業--電子工学・電気通信)
  • NDL Call No.
    Z16-940
  • Data Source
    CJP  CJPref  NDL  NII-ELS 
Page Top