Integrated Emg Source Separation of Ei and Edm Muscles Using Non-negative Matrix Factorization
نویسندگان
چکیده
Electromyographic (EMG) signal directly represents muscle activity. When recording EMG signals of closely located muscles on skin surface the problem of source separation arises, each acquired channel records signals coming from different muscles [1]. Working on extrinsic finger extensors EI (index) and EDM (little finger) provides a system with muscles that are closely located and independently activable at low levels of force. Source separation of EMG signals is difficult to achieve since instantaneity of the mixtures recorded has been shown to be very sensitive to electrode location. Non-negative matrix factorization (NMF) has been applied to the locally integrated EMG (IEMG) signal in order to identify the mixing matrix and Integrated EMG source signals. Values of contrast between EMG activity during EI and EDM contractions was computed before and after source separation and contrast gains turned out to be significantly higher using NMF on IEMG than using a well known source separation algorithm on EMG signal directly.
منابع مشابه
On the use of sparse signal decomposition in the analysis of multi-channel surface electromyograms
The decomposition of surface electromyogram data sets (s-EMG) is studied using blind source separation techniques based on sparseness; namely independent component analysis, sparse nonnegative matrix factorization, and sparse component analysis. When applied to artificial signals we find noticeable differences of algorithm performance depending on the source assumptions. In particular, sparse n...
متن کاملNon-Negative Matrix Factorization for Blind Source Separation in Wavelet Transform Domain
This paper describes a new multilevel decomposition method for the separation of convolutive image mixtures. The proposed method uses an Adaptive Quincunx Lifting Scheme (AQLS) based on wavelet decomposition to preprocess the input data, followed by a Non-Negative Matrix Factorization whose role is to unmix the decomposed images. The unmixed images are, thereafter, reconstructed using the inver...
متن کاملA new approach for building recommender system using non negative matrix factorization method
Nonnegative Matrix Factorization is a new approach to reduce data dimensions. In this method, by applying the nonnegativity of the matrix data, the matrix is decomposed into components that are more interrelated and divide the data into sections where the data in these sections have a specific relationship. In this paper, we use the nonnegative matrix factorization to decompose the user ratin...
متن کاملIterative Weighted Non-smooth Non-negative Matrix Factorization for Face Recognition
Non-negative Matrix Factorization (NMF) is a part-based image representation method. It comes from the intuitive idea that entire face image can be constructed by combining several parts. In this paper, we propose a framework for face recognition by finding localized, part-based representations, denoted “Iterative weighted non-smooth non-negative matrix factorization” (IWNS-NMF). A new cost fun...
متن کاملComparing Separation Quality of Nonnegative Matrix Factorization and Nonnegative Matrix Factor 2D Deconvolution in Audio Source Separation Tasks
The Nonnegative Matrix Factorization (NMF) is widely used in audio source separation tasks. However, the separation quality of NMF varies a lot depending on the mixture. In this paper, we analyze the use of NMF in source separation tasks and show how separation results can be significantly improved by using the Nonnegative Matrix Factor 2D Deconvolution (NMF2D). NMF2D was originally proposed as...
متن کامل