Development of Accelerator-based Activity Recognition Technique Robust for Missing Data

2012 Fiscal Year Final Research Report

• Project/Area Number: 23700230
• Research Category: Grant-in-Aid for Young Scientists (B)
• Allocation Type: Multi-year Fund
• Research Field: Perception information processing/Intelligent robotics
• Research Institution: Toyohashi University of Technology
• Principal Investigator: OMURA Ren 豊橋技術科学大学, 大学院・工学研究科, 講師 (10395163)
• Project Period (FY): 2011 – 2012
• Keywords: 行動認識 / ロバスト性向上 / ウェアラブルコンピュータ / センサネットワーク / 欠損データ補完 / パターン認識

Research Abstract

This study examined the activity recognition technique that can perform even when a part of sensor data is missing. From the process of pattern recognition technique, which is used in most existing activity recognition techniques, completion of missing sensor data, completion of missing feature value, classification with remaining features are examined. For the completion of missing sensor data, the sequential data prediction with the ARAR model is used. For the completion of missing feature value, multiple regression and kernel regression are exploited. For the classification with remaining features, multiple classifiers are learned with sensor data artificially omitted on each sensor, and are selected appropriately in the situation of the loss of sensor. From some experiments, the completion of missing sensor data or feature value achieves better performance than coping with the selection of classifiers in many cases. In addition, the appropriate method differs depending on the position of missing sensor. Then, it was found that using appropriate method for the position of missing sensor achieves almost same performance as no missing case or degradation of about 0.03 point in f-measure for coping with missing sensor data.

Research Products

• [Presentation] ARAR アルゴリズムによる欠損データ補完を用いたウェアラブルセンサ行動認識技術の耐故障性向上 (2013)
  • Author(s): 内田 稜真,堀野 豊人,大村 廉
  • Organizer: 第37回情報処理学会ユビキタスコンピューティングシステム研究会(UBI),情処研報
  • Place of Presentation: 東京大学 駒場リサーチキャンパス
  • Year and Date: 2013-03-15
• [Presentation] Preliminary Evaluation of Feature Level Compensation for Missing Data in Multi-sensor Activity Recognition (2012)
  • Author(s): Ryoma Uchida and Ren Ohmura
  • Organizer: The 14th ACM International Conference on Ubiquitous Computing(UbiComp'12)
  • Place of Presentation: David L. Lawrence Convention Center, Pittsburgh, Pennsylvania, The United States
  • Year and Date: 2012-09-05
• [Presentation] ウェアラブルセンサを用いた行動認識技術の欠損特徴量補完による耐故障性向上 (2012)
  • Author(s): 内田 稜真,大村 廉
  • Organizer: 第34回情報処理学会ユビキタスコンピューティングシステム研究会(UBI),情処研報
  • Place of Presentation: 豊橋技術科学大学
  • Year and Date: 2012-05-18
• [Presentation] Response Time Improvement in Accelerometer-Based Activity Recognition by Activity Change Detection (2011)
  • Author(s): Ren Ohmura and Wataru Takasaki
  • Organizer: In Proc. Of the 2011 ACM Conference on Ubiquitous Computing (UbiComp'11)
  • Place of Presentation: Tsinghua University, Beijing, China
  • Year and Date: 2011-09-19
• [Presentation] 行動の変化点検出による加速度ベース行動認識のレスポンス時間短縮 (2011)
  • Author(s): 高崎 航,大村 廉
  • Organizer: 第31回情報処理学会ユビキタスコンピューティングシステム研究会(UBI),情処研報
  • Place of Presentation: 九州大学西新プラザ
  • Year and Date: 2011-07-15
• [Remarks] 解説記事 大村廉,ユビキタスセンシング技術による看護業務サポートシステム実現への取り組み,映像情報インダストリアル3月号 / 映像情報メディカル3月号, pp.54-59,2 月,2012 年
• [Remarks]
  • URL: http://www.usl.cs.tut.ac.jp