The limb is the most common site for sports injuries. The objective of this study is to validate lower limb muscle synergy as a biomarker for movement quality. The proposed method comprises the following steps: (i) ex...
详细信息
The limb is the most common site for sports injuries. The objective of this study is to validate lower limb muscle synergy as a biomarker for movement quality. The proposed method comprises the following steps: (i) extraction of muscle synergies using nonnegativematrixfactorization, (ii) estimation of hip, knee, and ankle joint movements from synergy weights, (iii) identification of common muscle synergies across five walking tasks using kmeans clustering and (iv) conducting cluster-wise analysis of muscle contraction intensity during lower limb joint movements using synergy weights. In this study, we used surface Electromyography signals from the Lencioni et al. 2019 dataset recorded during normal walking, heel walking, toe walking, stair ascending and stair descending tasks involving fifty heterogeneous subjects. For the first time in the literature, we performed a functional interpretation of lower limb joint movements during these five walking tasks based on synergy weights and compared the results with the multiple muscle co-activation index (p < 0.005). Further, the clustering results revealed similarities in muscle synergies among normal, toe, and stair walking tasks (p < 0.05), while highlighting the distinct synergy pattern of the heel walking task. Notably, this study also explored the variations in muscle contraction intensities across different walking tasks that share common muscle synergies. Additionally, we extensively analysed the impact of age-gender factors on stride length and walking speed, uncovering small but discernible gender-specific differences in muscle synergies during different walking tasks. Hence, muscle synergy shows promise as a potential biomarker for the functional assessment of lower limb movements.
The classical clustering methods such as PCA,ICA, SVM, or most recently, NNMF(the nonnegative matrix factorization method) and its extension, NTF(nonnegative tensor factorization), are fatally based upon an assumption...
详细信息
ISBN:
(纸本)9781424464968
The classical clustering methods such as PCA,ICA, SVM, or most recently, NNMF(the nonnegative matrix factorization method) and its extension, NTF(nonnegative tensor factorization), are fatally based upon an assumption that the number of the groups of the data points is already known. But the fact is there are many cases where we have no idea at all whether there exist some or how many patterns for us to recognize in reality. We introduce a novel clustering method based on CPF, the method of completely positive matrixfactorization. An example is supplied to illustrate the implementation of a CPF algorithm.
暂无评论