Construction of the Estimation Model for Muscular Power Coefficient Based on Ridge Regression for Muscle Strength Assessment

Yuya HIRANO  Daisuke KUSHIDA  Akira KITAMURA  

Publication
D - Abstracts of IEICE TRANSACTIONS on Information and Systems (Japanese Edition)   Vol.J101-D   No.7   pp.1061-1067
Publication Date: 2018/07/01
Online ISSN: 1881-0225
DOI: 
Type of Manuscript: PAPER
Category: 
Keyword: 
EMG,  estimation,  Ridge regression,  generalization capability,  

Full Text(in Japanese): PDF(1.3MB)
>>Buy this Article


Summary: 
Muscular power coefficient is the first-order linear approximation parameter when relating muscle load and EMG proposed by the authors. Authors had tried achieving quantitation of a muscular condition by constructing the estimation model for muscular power coefficient based on patient's bodily features. However, the estimation model has a low generalization capability for unknown subjects, there is a problem that cannot guarantee the reliability. This paper proposes the new method of constructing estimation model for muscular power coefficient, and aim improvement of the generalization capability. In the future, this technique is expected to enable automatic diagnosis and rehabilitation at home.