Feature Extraction of Human Motion by using Phase Space and Its Application to Car-Driver's Motion Analysis

2015 Fiscal Year Final Research Report

• Project/Area Number: 25870855
• Research Category: Grant-in-Aid for Young Scientists (B)
• Allocation Type: Multi-year Fund
• Research Field: Soft computing; Dynamics/Control
• Research Institution: Toyohashi University of Technology (2015); Yamanashi Eiwa College (2013-2014)
• Principal Investigator: Akiduki Takuma 豊橋技術科学大学, 工学(系)研究科(研究院), 助教 (40632922)
• Project Period (FY): 2013-04-01 – 2016-03-31
• Keywords: 身体動作 / 軌道アトラクタ / 相空間 / 記号化 / 個人性 / 動作特徴

Outline of Final Research Achievements

In this study, we address a time-series analysis method for human motion analysis based on symbolization of sensor data. In our approach, the time series of the periodical signals are expressed by dynamical systems having attractors, which symbolize the time series in state space. For detecting individual characteristics in motion, we discussed differences between our approach and sliding window approach. Then, we conducted computer experiments using the simple pendulum system for investigating the relationship between the physical conditions of motion and the distribution of symbols in the symbol spaces that are designed by two approaches. Moreover, we studied the methodology of application of our approach to actual motion data for clarifying the issues of our approach. These results suggest that symbol space designed by our method can be used to discriminate individual characteristics in motion.

Free Research Field

計測工学