Recently, it has been reported that finger motions could be recognized from the forearm signal detected by accelerometers. However, accelerometers are sensitive to vibration or unintended motions, which could cause large noise when classifying different hand motions. This is why our research group wanted to explore the usability of other kinds of sensors for upper arm motions classification. Therefore, the objective of this study was to examine the usefulness of a piezoelectric film for hand motion classification and its robustness to unintended motions. Experiments were conducted to record signals from the piezoelectric films for different hand motions, while the subject was asked to move the ipsilateral shoulder, the contralateral hand, or the legs. The results showed that the desired hand motion could be distinguished using a piezoelectric film despite of unintended motions.
[1]
Ito Koji,et al.
A Prosthetic Hand Control by Nonstationary EMG at the beginning of Motion
,
2006
.
[2]
Wenwei Yu,et al.
On‐line learning method for EMG prosthetic hand control
,
2001
.
[3]
Wenwei Yu,et al.
Preliminary results of online classification of upper limb motions from around-shoulder muscle activities
,
2011,
2011 IEEE International Conference on Rehabilitation Robotics.
[4]
Wenwei Yu,et al.
On-line supervising mechanism for learning data in surface electromyogram motion classifiers
,
2002,
Systems and Computers in Japan.
[5]
U. Rajendra Acharya,et al.
Finger Motion Classification by Forearm Skin Surface Vibration Signals
,
2010,
The open medical informatics journal.