Filters








131 Hits in 5.7 sec

Wavelet Energy based Neural Fuzzy Model for Automatic Motor Imagery Classification

Girisha Garg, Shruti Suri, Rachit Garg, Vijander Singh
2011 International Journal of Computer Applications  
This paper presents a method for accurately classifying EEG signals generated by imagery left and right hand movements.  ...  Firstly, wavelet transform and energy of the decomposed signal is used to obtain the final feature vector matrix. Secondly, the feature data is classified using ANFIS. .  ...  Wavelet transform is used for EEG feature extraction in our research.  ... 
doi:10.5120/3403-4745 fatcat:kesvzv4fzjcodoj5q6djkmod24

Decomposition Methods for Machine Learning with Small, Incomplete or Noisy Datasets

Cesar Federico Caiafa, Jordi Solé-Casals, Pere Marti-Puig, Sun Zhe, Toshihisa Tanaka
2020 Applied Sciences  
In this article, we provide a unified review of recently proposed methods based on signal decomposition for missing features imputation (data completion), classification of noisy samples and artificial  ...  In other cases, and for different reasons, the datasets are originally small, and therefore, more data samples are required to derive useful supervised or unsupervised classification methods.  ...  Acknowledgments: We are grateful to the anonymous reviewers for their valuable comments, which helped us to improve the first version of this manuscript.  ... 
doi:10.3390/app10238481 fatcat:2gqm3tos4vdorptqayewqu2mum

A Novel Deep Learning Approach with Data Augmentation to Classify Motor Imagery Signals

Zhiwen Zhang, Feng Duan, Jordi Sole-Casals, Josep Dinares-Ferran, Andrzej Cichocki, Zhenglu Yang, Zhe Sun
2019 IEEE Access  
Recently, the deep learning approaches have been widely used in many fields to extract features and classify various types of data successfully.  ...  We applied the empirical mode decomposition on the EEG frames and mixed their intrinsic mode functions to create new artificial EEG frames, followed by transforming all EEG data into tensors as inputs  ...  Common analysis tools like fast Fourier transform (FFT) and wavelets can not be adequate to extract feature and create new EEG frames in this scenario, because EEG signals are non-linear and non-stationary  ... 
doi:10.1109/access.2019.2895133 fatcat:irxzoczw3rdw7ggdod5z66n56u

LOW-RANK APPROXIMATION BASED NON-NEGATIVE MULTI-WAY ARRAY DECOMPOSITION ON EVENT-RELATED POTENTIALS

FENGYU CONG, GUOXU ZHOU, PIIA ASTIKAINEN, QIBIN ZHAO, QIANG WU, ASOKE K NANDI, JARI K. HIETANEN, TAPANI RISTANIEMI, ANDRZEJ CICHOCKI
2014 International Journal of Neural Systems  
We applied NCPD (LRAHALS and benchmark HALS) and CPD to extract multi-domain features of a visual ERP.  ...  The features and components extracted by LRAHALS NCPD and HALS NCPD were very similar, but LRAHALS NCPD was 70 times faster than HALS NCPD.  ...  In order to reduce noise further, the ERP data were filtered by a fast Fourier Transform (FFT) filter (number of points for FFT was 10,000) with a pass band of 1-30 Hz.  ... 
doi:10.1142/s012906571440005x pmid:25164246 fatcat:36l3wmqy25cnbmj53vzhjprd2u

Tackling EEG signal classification with least squares support vector machines: A sensitivity analysis study

Clodoaldo A.M. Lima, André L.V. Coelho, Marcio Eisencraft
2010 Computers in Biology and Medicine  
Results of experiments conducted over different types of features extracted from a benchmark EEG signal dataset evidence that the sensitivity profiles of the kernel machines are qualitatively similar,  ...  The electroencephalogram (EEG) signal captures the electrical activity of the brain and is an important source of information for studying neurological disorders.  ...  Acknowledgements This work was financially sponsored by CNPq/Brazil, via Grants #474843/2008-4 and #312934/2009-2, and MackPesquisa, via Grant #1349.  ... 
doi:10.1016/j.compbiomed.2010.06.005 pmid:20621291 fatcat:dyveambmkzfh7bvi722g3oqckm

Shared and Unshared Feature Extraction in Major Depression During Music Listening Using Constrained Tensor Factorization

Xiulin Wang, Wenya Liu, Xiaoyu Wang, Zhen Mu, Jing Xu, Yi Chang, Qing Zhang, Jianlin Wu, Fengyu Cong
2021 Frontiers in Human Neuroscience  
In this study, we proposed a data-driven shared and unshared feature extraction framework based on nonnegative and coupled tensor factorization, which aims to conduct group-level analysis for the EEG signals  ...  feature patterns between/in MDD and HC groups.  ...  In this study, we proposed a data-driven shared and unshared feature extraction framework based on nonnegative and coupled tensor factorization, which aims to conduct group-level analysis for the EEG signals  ... 
doi:10.3389/fnhum.2021.799288 pmid:34975439 pmcid:PMC8714749 fatcat:3luyh6iosfa3bdqam3pqf5c2py

Analysis of complex-valued functional magnetic resonance imaging data: are we just going through a "phase"?

V.D. Calhoun, T. Adali
2012 Bulletin of the Polish Academy of Sciences: Technical Sciences  
We discuss the challenges inherent in trying to utilize the phase data, and provide a selective review with emphasis on work in our group for developing biophysical models, preprocessing methods, and statistical  ...  Over the past few years, interest in incorporating the phase information into the analyses has been growing and new methods for modeling and processing the data have been developed.  ...  This work was supported by NSF grants 0715022, 0840895, 0635129 and 0612076. Acknowledgements. This work has been partly supported by the French ANR contract 10-BLAN-MULTIMODEL.  ... 
doi:10.2478/v10175-012-0050-5 fatcat:3vl32ly43bdnhm4okw3y765uzy

Multifactor sparse feature extraction using Convolutive Nonnegative Tucker Decomposition

Qiang Wu, Liqing Zhang, Andrzej Cichocki
2014 Neurocomputing  
We employ the K-CNTD algorithm to extract the shift-invariant sparse features in different subspaces for robust speaker recognition and Alzheimer's Disease(AD) diagnosis task.  ...  In this paper, a flexible two stage algorithm for K-mode Convolutive Nonnegative Tucker Decomposition (K-CNTD) model is proposed using an alternating least square procedure.  ...  Acknowledgment The authors would like to thank anonymous reviewers for their constructive comments on this paper.  ... 
doi:10.1016/j.neucom.2013.04.049 fatcat:7yxilx7u2beh7blcmuhrmo4fru

Multiway array decomposition analysis of EEGs in Alzheimer's disease

Charles-Francois V. Latchoumane, Francois-Benois Vialatte, Jordi Solé-Casals, Monique Maurice, Sunil R. Wimalaratna, Nigel Hudson, Jaeseung Jeong, Andrzej Cichocki
2012 Journal of Neuroscience Methods  
In this study, we applied two state of the art multiway array decomposition (MAD) methods to extract unique features from electroencephalograms (EEGs) of AD patients obtained from multiple sites.  ...  Title page-incl. type of article and authors' name and affiliation Highlights > Multi-Array Decomposition (MAD) method to extract unique, general features for multi-site diagnosis of Alzheimer's disease  ...  D"Annunzio", Chieti, Italy) for their precious contribution in the subjects management, data recording and data management.  ... 
doi:10.1016/j.jneumeth.2012.03.005 pmid:22480988 fatcat:mqkumjw7ezekrlz5fszibep5sq

Recognition of Imbalanced Epileptic EEG Signals by a Graph-Based Extreme Learning Machine

Jie Zhou, Xiongtao Zhang, Zhibin Jiang, Shan Zhong
2021 Wireless Communications and Mobile Computing  
Epileptic EEG signal recognition is an important method for epilepsy detection. In essence, epileptic EEG signal recognition is a typical imbalanced classification task.  ...  To overcome these challenges, a graph-based extreme learning machine method (G-ELM) is proposed for imbalanced epileptic EEG signal recognition.  ...  Acknowledgments This work was supported in part by the National Natural Science Foundation of China under Grant 61772198 and by the Natural Science Foundation of Jiangsu Province under Grant BK20161268  ... 
doi:10.1155/2021/5871684 fatcat:hjnqqs2dy5c3bjc6jprn7bsega

Tensor decomposition of TMS-induced EEG oscillations reveals data-driven profiles of antiepileptic drug effects

C. Tangwiriyasakul, I. Premoli, L. Spyrou, R. F. Chin, J. Escudero, M. P. Richardson
2019 Scientific Reports  
We validated reliability of PARAFAC on TMS-induced oscillations before extracting the features of two common anti-epileptic drugs (levetiracetam and lamotrigine) in an integrated manner.  ...  However, the extraction of specific features related to drug effects is not always straightforward as the complex TMS-EEG induced response profile is multi-dimensional.  ...  After that, for each segment we estimated its time-frequency plot by applying a Hanning taper windowed fast Fourier transform (FFT) with frequency-dependent window length (width: 3.5 cycles per time window  ... 
doi:10.1038/s41598-019-53565-9 pmid:31745223 pmcid:PMC6864053 fatcat:uii6f7le4rcjnffpehsbyo3gcm

Tucker Tensor Regression and Neuroimaging Analysis [article]

Xiaoshan Li and Hua Zhou and Lexin Li
2013 arXiv   pre-print
In this article, we propose a family of generalized linear tensor regression models based upon the Tucker decomposition of regression coefficient arrays.  ...  We demonstrate, both numerically that the new model could provide a sound recovery of even high rank signals, and asymptotically that the model is consistently estimating the best Tucker structure approximation  ...  A typical solution in the literature first employs the subject knowledge to extract a vector of features from images, and then feeds the feature vector into a classical regression model (Mckeown et al  ... 
arXiv:1304.5637v1 fatcat:ovjf5yqppzbfnesb3lv2gqivmu

Automated and ERP-Based Diagnosis of Attention-Deficit Hyperactivity Disorder in Children

HosseinR Jahanshahloo, Mousa Shamsi, Elham Ghasemi, Abolfazl Kouhi
2017 Journal of Medical Signals & Sensors  
To increase the accuracy of the diagnostic process of ADHD, ERP signals were recorded to extract some specific ERP features related to this disease for classifying the two groups.  ...  After a preprocessing step, several features such as band power, fractal dimension, autoregressive (AR) model coefficients and wavelet coefficients were extracted from recorded signals.  ...  Castro-Cabrera University of Universidad National de Colombia, sede Manizales for providing the ERP dataset. Financial support and sponsorship Nil.  ... 
doi:10.4103/2228-7477.199152 fatcat:fgwzjcyxwvctthdvcefzz3upci

Committee report: Publication guidelines and recommendations for studies using electroencephalography and magnetoencephalography

Andreas Keil, Stefan Debener, Gabriele Gratton, Markus Junghöfer, Emily S. Kappenman, Steven J. Luck, Phan Luu, Gregory A. Miller, Cindy M. Yee
2013 Psychophysiology  
The guidelines also include a checklist of key information recommended for inclusion in research reports on EEG/MEG measures.  ...  The scope of concepts, methods, and instruments used by EEG/MEG researchers has dramatically increased and is expected to further increase in the future.  ...  Most authors use Fourier-based algorithms for sampled, noncontinuous data (discrete Fourier transform, DFT; fast Fourier transform, FFT), the principles of which are explained in Pivik et al (1993; see  ... 
doi:10.1111/psyp.12147 pmid:24147581 fatcat:ql6dyx3slfabrgcbpgkbj6vjc4

Tensor-based anomaly detection: An interdisciplinary survey

Hadi Fanaee-T, João Gama
2016 Knowledge-Based Systems  
We survey the interdisciplinary works in which TAD is reported and characterize the learning strategies, methods and applications; extract the important open issues in TAD and provide the corresponding  ...  Traditional spectral-based methods such as PCA are popular for anomaly detection in a variety of problems and domains.  ...  autoregressive processes of several signals modeled by Fast Fourier transform (FFT).  ... 
doi:10.1016/j.knosys.2016.01.027 fatcat:lejxxae63jcutfx2ncahownt7e
« Previous Showing results 1 — 15 out of 131 results