Identical fits of nonnegative matrix/tensor factorization may correspond to different extracted event-related potentials

Nonnegative Matrix / Tensor factorization (NMF/NTF) have been used in the study of EEG, and the fit (explained variation) is often used to evaluate the performance of a nonnegative decomposition algorithm. However, this parameter only reveals the information derived from the mathematical model and just exhibits the reliability of the algorithms, and the property of EEG can not be reflected. If fits of two algorithms are identical, it is necessary to examine whether the desired components extracted by them are identical too. In order to verify this doubt, we performed NMF and NTF on the same dataset of an auditory event-related potentials (ERPs), and found that the identical fits of NMF and NTF under the hierarchical alternating least squares algorithms corresponded to different desired ERPs extracted by NMF and NTF, moreover, NTF contributed the ERP with much better timing and spectral properties. Such analysis implies that to combine the fit and property of the desired ERP component together helps evaluate the performance of NMF and NTF algorithms in the study of ERPs.

[1]  H. Sebastian Seung,et al.  Learning the parts of objects by non-negative matrix factorization , 1999, Nature.

[2]  H. Lyytinen,et al.  Independent component analysis on the mismatch negativity in an uninterrupted sound paradigm , 2008, Journal of Neuroscience Methods.

[3]  R. Näätänen,et al.  Measurement of extensive auditory discrimination profiles using the mismatch negativity (MMN) of the auditory event-related potential (ERP) , 2007, Clinical Neurophysiology.

[4]  Wolfgang Skrandies,et al.  EEG/EP: New techniques , 2005, Brain Topography.

[5]  A. Engel,et al.  Opinion TRENDS in Cognitive Sciences Vol.10 No.12 Single-trial EEG–fMRI reveals the dynamics of cognitive function , 2022 .

[6]  Risto N t nen.  Attention and brain function , 1992 .

[7]  John J. B. Allen,et al.  Prelude to and Resolution of an Error: EEG Phase Synchrony Reveals Cognitive Control Dynamics during Action Monitoring , 2009, The Journal of Neuroscience.

[8]  Lars Kai Hansen,et al.  ERPWAVELAB A toolbox for multi-channel analysis of time–frequency transformed event related potentials , 2007, Journal of Neuroscience Methods.

[9]  Arnaud Delorme,et al.  EEGLAB: an open source toolbox for analysis of single-trial EEG dynamics including independent component analysis , 2004, Journal of Neuroscience Methods.

[10]  C. C. Duncan,et al.  Event-related potentials in clinical research: Guidelines for eliciting, recording, and quantifying mismatch negativity, P300, and N400 , 2009, Clinical Neurophysiology.

[11]  Karl J. Friston,et al.  The mismatch negativity: A review of underlying mechanisms , 2009, Clinical Neurophysiology.

[12]  C. Ehlers,et al.  Event-related oscillations as risk markers in genetic mouse models of high alcohol preference , 2009, Neuroscience.

[13]  Lars Kai Hansen,et al.  Parallel Factor Analysis as an exploratory tool for wavelet transformed event-related EEG , 2006, NeuroImage.

[14]  H. Lyytinen,et al.  Brain reacts to occasional changes in duration of elements in a continuous sound , 1995, Neuroreport.

[15]  Fumikazu Miwakeichi,et al.  Decomposing EEG data into space–time–frequency components using Parallel Factor Analysis , 2004, NeuroImage.

[16]  T. Sejnowski,et al.  Functionally Independent Components of the Late Positive Event-Related Potential during Visual Spatial Attention , 1999, The Journal of Neuroscience.

[17]  A. Cichocki,et al.  Multilayer nonnegative matrix factorisation , 2006 .

[18]  A. Cichocki,et al.  Flexible HALS algorithms for sparse non-negative matrix/tensor factorization , 2008, 2008 IEEE Workshop on Machine Learning for Signal Processing.

[19]  J. Joutsensalo,et al.  Optimal Digital Filtering versus Difference Waves on the Mismatch Negativity in an Uninterrupted Sound Paradigm , 2007, Developmental neuropsychology.

[20]  Bernice Porjesz,et al.  Event-Related Oscillations in Offspring of Alcoholics: Neurocognitive Disinhibition as a Risk for Alcoholism , 2006, Biological Psychiatry.

[21]  Gábor P. Háden,et al.  Auditory temporal grouping in newborn infants. , 2007, Psychophysiology.

[22]  Andrzej Cichocki,et al.  Nonnegative Matrix and Tensor Factorization T , 2007 .

[23]  Karl J. Friston,et al.  Mechanisms of evoked and induced responses in MEG/EEG , 2006, NeuroImage.

[24]  H. Lyytinen,et al.  Mismatch negativity (MMN) elicited by duration deviations in children with reading disorder, attention deficit or both. , 2008, International journal of psychophysiology : official journal of the International Organization of Psychophysiology.

[25]  S. Amari,et al.  Nonnegative Matrix and Tensor Factorization [Lecture Notes] , 2008, IEEE Signal Processing Magazine.

[26]  R. Näätänen.  Attention and brain function , 1992 .

[27]  Andrzej Cichocki,et al.  Nonnegative Tensor Factorization for Continuous EEG Classification , 2007, Int. J. Neural Syst..

[28]  R. Näätänen,et al.  Early selective-attention effect on evoked potential reinterpreted. , 1978, Acta psychologica.

[29]  H. Lyytinen,et al.  Does Mismatch Negativity Show Differences in Reading-Disabled Children Compared to Normal Children and Children with Attention Deficit? , 2007, Developmental neuropsychology.

[30]  A. Engel,et al.  Trial-by-Trial Coupling of Concurrent Electroencephalogram and Functional Magnetic Resonance Imaging Identifies the Dynamics of Performance Monitoring , 2005, The Journal of Neuroscience.

[31]  Andrzej Cichocki,et al.  Hierarchical ALS Algorithms for Nonnegative Matrix and 3D Tensor Factorization , 2007, ICA.