EMGによるSSARXモデルを用いた疲労の推定

Surface EMG signals

EMG SSARX Recognition of Operator’s Fatigue Based on Stochastic Switched ARX Model and EMG

Fumio KOMETANI,Hiroyuki OKUDA,Shinkichi INAGAKI

and Tatsuya SUZUKI,Nagoya Univ.

When the human muscle is activated,a voltage called electromyographic signal(EMG)can be observed.One of the interesting application of the EMG signal is to estimate a muscle fatigue of human operator.Although the relationship between the EMG and muscle fatigue has been addressed by many researchers,the target task was too simple in most cases,and the effectiveness in real world application, i.e.the estimate through complex task has not been veri?ed yet.This paper proposes a new muscle fatigue recognizer based on a stochastic switched ARX model which can be applicable to the complex task thanks to its switching mechanism.The validity of the proposed idea is veri?ed through experimental results.

1.

ElectroMyoGraphic signal: EMG EMG (1)

Peg-in-Hole

2.SSARX

HMM HMM ARX ARX Stochastic Switched ARX(SSARX)

SSARX (2)

2·1Hidden Markov Model(HMM)t O={o0,...,o t,...,o T} HMM :S={s i} s i s j :A={a i j} s i o t :B={b i(o t)} :π={πi} 3 (3)

2·2SS-ARX SSARX HMM (1),(2) ARX

y t=ψ tθi+e i,t(1)

ψt=[y t?1,y t?2,...,y t?n,u t?1,u t?2,...,u t?n,1] (2)

y t u t θi e i,t 0 σi o t=(y t,ψt) b i(o t) (3)

b i(o t)=

1

2πσi

exp

?

(ψ tθi?y t)2

2σ2i

(3)

b i(o t) 1 HMM ARX HMM (2)

3.

3·1 Fig.1 Peg-in-Hole

‘BA1104-CM’ 1000 ‘BA-U410’ Fig.1 Ch1,Ch2,Ch3

EMGによるSSARXモデルを用いた疲労の推定

Word文档免费下载Word文档免费下载:EMGによるSSARXモデルを用いた疲労の推定 (共2页,当前第1页)

EMGによるSSARXモデルを用いた疲労の推定相关文档

最新文档

返回顶部