Quantitative Comparison of EEG Compressed Sensing using Gabor and K-SVD Dictionaries

With the fast development of wearable healthcare systems, compressed sensing (CS) has been proposed to be applied in electroencephalogram (EEG) acquisition. For CS, it is desired to build the best-fit dictionary in order to achieve good reconstruction accuracy. While most of existing works focused on static dictionaries such as Gabor, Fourier and wavelets. The dynamic nature of EEG signals motivates us to study learned dictionaries, which are supposed to provide better reconstruction accuracy and lower computation cost. In this paper, we provide the quantitative performance comparison of EEG CS using two different types of dictionaries, i.e., the well-known Gabor dictionaries versus K-SVD learned dictionaries. The performance comparison utilizes the well-established database of scalp EEG from Physiobank, which allows researchers in this field to compare their work with ours. In addition, it also attempts to inspire the systematic study of dictionary learning in EEG CS.

[1]  Jeffrey M. Hausdorff,et al.  Physionet: Components of a New Research Resource for Complex Physiologic Signals". Circu-lation Vol , 2000 .

[2]  Blanco,et al.  Time-frequency analysis of electroencephalogram series. II. Gabor and wavelet transforms. , 1996, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.

[3]  P. Tonella,et al.  EEG data compression techniques , 1997, IEEE Transactions on Biomedical Engineering.

[4]  Pierre Vandergheynst,et al.  Dictionary learning for the sparse modelling of atrial fibrillation in ECG signals , 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

[5]  Tzyy-Ping Jung,et al.  Compressed Sensing of EEG for Wireless Telemonitoring With Low Energy Consumption and Inexpensive Hardware , 2012, IEEE Transactions on Biomedical Engineering.

[6]  Pascal Frossard,et al.  Dictionary Learning , 2011, IEEE Signal Processing Magazine.

[7]  Selin Aviyente,et al.  Compressed Sensing Framework for EEG Compression , 2007, 2007 IEEE/SP 14th Workshop on Statistical Signal Processing.

[8]  Rafał Kuś,et al.  Multivariate matching pursuit in optimal Gabor dictionaries: theory and software with interface for EEG/MEG via Svarog , 2013, BioMedical Engineering OnLine.

[9]  David L Donoho,et al.  Compressed sensing , 2006, IEEE Transactions on Information Theory.

[10]  Stéphane Mallat,et al.  Matching pursuits with time-frequency dictionaries , 1993, IEEE Trans. Signal Process..

[11]  A. Bruckstein,et al.  K-SVD : An Algorithm for Designing of Overcomplete Dictionaries for Sparse Representation , 2005 .

[12]  Jun Luan,et al.  A new approach to compressing ECG signals with trained overcomplete dictionary , 2014, 2014 4th International Conference on Wireless Mobile Communication and Healthcare - Transforming Healthcare Through Innovations in Mobile and Wireless Technologies (MOBIHEALTH).

[13]  Haiqing Wang,et al.  The sparse decomposition and compression of ECG and EEG based on matching pursuits , 2010, 2010 3rd International Conference on Biomedical Engineering and Informatics.

[14]  Rabab Kreidieh Ward,et al.  An Energy Efficient Compressed Sensing Framework for the Compression of Electroencephalogram Signals , 2014, Sensors.

[15]  Cédric Gouy-Pailler,et al.  Multivariate temporal dictionary learning for EEG , 2013, Journal of Neuroscience Methods.

[16]  Angshul Majumdar,et al.  Gabor based analysis prior formulation for EEG signal reconstruction , 2013, Biomed. Signal Process. Control..

[17]  Joel A. Tropp,et al.  Simultaneous sparse approximation via greedy pursuit , 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

[18]  Michael P. Friedlander,et al.  Probing the Pareto Frontier for Basis Pursuit Solutions , 2008, SIAM J. Sci. Comput..

[19]  Michael Elad,et al.  Compression of facial images using the K-SVD algorithm , 2008, J. Vis. Commun. Image Represent..

[20]  Refet Firat Yazicioglu,et al.  An Efficient and Compact Compressed Sensing Microsystem for Implantable Neural Recordings , 2014, IEEE Transactions on Biomedical Circuits and Systems.

[21]  Günther J. L. Gerhardt,et al.  Characteristics of human EEG sleep spindles assessed by Gabor transform , 2003 .

[22]  Esther Rodríguez-Villegas,et al.  Compressive sensing scalp EEG signals: implementations and practical performance , 2011, Medical & Biological Engineering & Computing.

[23]  A. Bruckstein,et al.  On the uniqueness of overcomplete dictionaries, and a practical way to retrieve them , 2006 .

[24]  Liam Kilmartin,et al.  Compressed Sensing for Bioelectric Signals: A Review , 2015, IEEE Journal of Biomedical and Health Informatics.

[25]  Michael A. Saunders,et al.  Atomic Decomposition by Basis Pursuit , 1998, SIAM J. Sci. Comput..

[26]  Michael Elad,et al.  Improving Dictionary Learning: Multiple Dictionary Updates and Coefficient Reuse , 2013, IEEE Signal Processing Letters.

[27]  Zhangang Han,et al.  Feature extraction of EEG signals from epilepsy patients based on Gabor Transform and EMD Decomposition , 2010, 2010 Sixth International Conference on Natural Computation.

[28]  Y. C. Pati,et al.  Orthogonal matching pursuit: recursive function approximation with applications to wavelet decomposition , 1993, Proceedings of 27th Asilomar Conference on Signals, Systems and Computers.

[29]  Marie-Françoise Lucas,et al.  Compression of Biomedical Signals With Mother Wavelet Optimization and Best-Basis Wavelet Packet Selection , 2007, IEEE Transactions on Biomedical Engineering.

[30]  M. Elad,et al.  $rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation , 2006, IEEE Transactions on Signal Processing.