Filters








2,110 Hits in 5.9 sec

A Survey on Machine Learning Algorithms in Little-Labeled Data for Motor Imagery-Based Brain-Computer Interfaces

Yuxi Jia, Feng Li, Fei Wang, Yan Gui
2019 Journal of Information Hiding and Privacy Protection  
In this paper, we reviewed the recent development in the machine learning algorithm used in the MI-based BCI, which may provide potential solutions for addressing the issue.  ...  The Brain-Computer Interfaces (BCIs) had been proposed and used in therapeutics for decades.  ...  the problem of selecting an appropriate operational frequency band for extracting discriminating CSP features.  ... 
doi:10.32604/jihpp.2019.05979 fatcat:imzrc6mwkjhuvegkydsfy4cyya

Investigation of EEG Signal Classification Techniques for Brain Computer Interface

2020 International Journal of Engineering and Advanced Technology  
Subsequently classifier algorithms are used to classify selected features into intended MI tasks. The major challenge in a BCI systems is to improve classification accuracy of a BCI system.  ...  Independent component analysis (ICA) technique is used for preprocessing and filter bank common spatial pattern (FBCSP) for feature extraction and selection.  ...  The FBCSP algorithm consist of signal processing and execution of machine learning procedure on EEG data.  ... 
doi:10.35940/ijeat.c5679.029320 fatcat:imtdz3n2hbep7jnfqsp3d2owdm

Random Forest and Filter Bank Common Spatial Patterns for EEG-Based Motor Imagery Classification

Maouia Bentlemsan, ET-Tahir Zemouri, Djamel Bouchaffra, Bahia Yahya-Zoubir, Karim Ferroudji
2014 2014 5th International Conference on Intelligent Systems, Modelling and Simulation  
Performing random forest in the classification avoid the use of feature selection step, since RF combine a bagging (bootstrap aggregation) and a random selection of features.  ...  We propose using filter bank common spatial pattern (FBCSP) feature extraction algorithm, and random forest (RF) technique for classification of EEG motor imagery signals.  ...  FBCSP performs in 4 progressive steps: filter bank, spatial filtering using CSP algorithm, feature selection and classification of the selected features.  ... 
doi:10.1109/isms.2014.46 fatcat:x5pb5fitlvb7bh2736m4s7vidy

Machine learning for constraint solver design -- A case study for the alldifferent constraint [article]

Ian Gent and Lars Kotthoff and Ian Miguel and Peter Nightingale
2010 arXiv   pre-print
We investigate using machine learning to make these decisions automatically depending on the problem to solve. We use the alldifferent constraint as a case study.  ...  Once a design decision has been made, it cannot easily be reversed, although a different decision may be more appropriate for a particular problem.  ...  We thank Jesse Hoey for useful discussions about machine learning and the anonymous reviewers for their feedback. Peter Nightingale is supported by EPSRC grants EP/H004092/1 and EP/E030394/1.  ... 
arXiv:1008.4326v1 fatcat:3dkjodeuybarvhg45nn4y2r2hm

Using machine learning to make constraint solver implementation decisions [article]

Lars Kotthoff and Ian Gent and Ian Miguel
2010 arXiv   pre-print
We investigate using machine learning to make these decisions automatically depending on the problem to solve with the alldifferent constraint as an example.  ...  Once a design decision has been made, it cannot easily be reversed, although a different decision may be more appropriate for a particular problem.  ...  We thank Jesse Hoey for useful discussions about machine learning and the anonymous reviewers for their feedback.  ... 
arXiv:1005.3502v1 fatcat:qbfgcob7mbet7lvhcfbzv4unsy

Ensemble Classification for Constraint Solver Configuration [chapter]

Lars Kotthoff, Ian Miguel, Peter Nightingale
2010 Lecture Notes in Computer Science  
One possible approach is the use of machine learning techniques to learn classifiers which, given the characteristics of a particular problem, make a decision as to which algorithm or what parameters to  ...  The automatic tuning of the parameters of algorithms and automatic selection of algorithms has received a lot of attention recently.  ...  Acknowledgements We thank Chris Jefferson for the description of one of the problem attributes used in the analysis, Jesse Hoey for useful discussions about machine learning, and anonymous reviewers for  ... 
doi:10.1007/978-3-642-15396-9_27 fatcat:4jyoqxia2zdixi54yynan7x2ty

Towards Robust Neuroadaptive HCI

Aurélien Appriou, Andrzej Cichocki, Fabien Lotte
2018 Extended Abstracts of the 2018 CHI Conference on Human Factors in Computing Systems - CHI '18  
This paper thus studies promising modern machine learning algorithms, including Riemannian geometry-based methods and Deep Learning, to estimate workload from EEG signals.  ...  Our results suggested that a shallow Convolutional Neural Network obtained the best performance in both conditions, outperforming state-of-the-art methods on the used data sets.  ...  Acknowledgements: This work received support from the European Research Council (grant ERC-2016-STG-714567) and the Japanese Society for the Promotion of Science (JSPS).  ... 
doi:10.1145/3170427.3188617 dblp:conf/chi/AppriouCL18 fatcat:kyglz2xlq5ck3grqmacp7iqxcm

Preprocessing and Meta-Classification for Brain-Computer Interfaces

Paul S. Hammon, Virginia R. de Sa
2007 IEEE Transactions on Biomedical Engineering  
Her interests include using machine learning methods to analyze neural signals, creating brain-motivated machine learning algorithms, and creating models of visual processing.  ...  Perhaps the most obvious way to improve classification performance is the selection of an advanced learning algorithm.  ...  ACKNOWLEDGMENT The authors would like to thank Dr. B. Allison for useful discussions and recommendations of pertinent background material.  ... 
doi:10.1109/tbme.2006.888833 pmid:17355065 fatcat:u66lop6ob5czboa2ukhl4u7qgu

Learning from other subjects helps reducing Brain-Computer Interface calibration time

Fabien Lotte, Cuntai Guan
2010 2010 IEEE International Conference on Acoustics, Speech and Signal Processing  
More precisely, we propose an algorithm to regularize the Common Spatial Patterns (CSP) and Linear Discriminant Analysis (LDA) algorithms based on the data from a subset of automatically selected subjects  ...  A major limitation of Brain-Computer Interfaces (BCI) is their long calibration time, as much data from the user must be collected in order to tune the BCI for this target user.  ...  Rather, we should select a subset of subjects whose data can be used to classify the target subject's data. To do so, we propose the subject selection algorithm described in Algorithm 1.  ... 
doi:10.1109/icassp.2010.5495183 dblp:conf/icassp/LotteG10 fatcat:pxjzqnrzrfgh7bpoeviljk3kua

Classifying Single-Trial EEG during Motor Imagery with a Small Training Set [article]

Yijun Wang
2013 arXiv   pre-print
Before the operation of a motor imagery based brain-computer interface (BCI) adopting machine learning techniques, a cumbersome training procedure is unavoidable.  ...  The development of a practical BCI posed the challenge of classifying single-trial EEG with a small training set.  ...  ACKNOWLEDGMENTS The authors are grateful to Klaus-Robert Müller, Benjamin Blankertz and Gabriel Curio for providing their data.  ... 
arXiv:1306.3474v1 fatcat:25st36tzxjhqzayifqf35nnwle

Multiclass EEG motor-imagery classification with sub-band common spatial patterns

Javeria Khan, Muhammad Hamza Bhatti, Usman Ghani Khan, Razi Iqbal
2019 EURASIP Journal on Wireless Communications and Networking  
The output of these sub-band filters is sent for feature extraction by applying common spatial pattern (CSP) and linear discriminant analysis (LDA).  ...  As all of the extracted features are not necessary for classification therefore, selection of optimal features is done by passing the extracted features to sequential backward floating selection (SBFS)  ...  Acknowledgements We would like to acknowledge our subjects who helped us with EEG data acquisition.  ... 
doi:10.1186/s13638-019-1497-y fatcat:qlphflzn6ne5vhizzgsy6eadhe

A Comparison Study On Eeg Signal Processing Techniques Using Motor Imagery Eeg Data

Vangelis P. Oikonomou, Kostas Georgiadis, George Liaros, Spiros Nikolopoulos, Ioannis Kompatsiaris
2017 Zenodo  
Furthermore, for the identification of MI tasks, two well-known classifiers are used, the Linear Discriminant Analysis (LDA) and the Support Vector Machines (SVM).  ...  Our results confirm that PSD features demonstrate the most consistent robustness and effectiveness in extracting patterns for accurately discriminating between left and right MI tasks.  ...  ACKNOWLEDGMENT This work is part of project MAMEM that has received funding from the European Union's Horizon 2020 research and innovation programme under grant agreement No 644780.  ... 
doi:10.5281/zenodo.583387 fatcat:mqb4pfudebdxvllppjici2pxge

Discriminative common spatial pattern sub-bands weighting based on distinction sensitive learning vector quantization method in motor imagery based brain-computer interface

Fatemeh Jamaloo, Mohammad Mikaeili
2015 Journal of Medical Signals & Sensors  
Finally, after the classification of the weighted features using a support vector machine classifier, the performance of the suggested method has been compared with the existing methods based on frequency  ...  Besides, a distinction sensitive learning vector quantization based weighting of the selected features has been considered.  ...  ACKNOWLEDGMENT The authors would like to thank Berlin BCI groups for providing the BCI competition dataset.  ... 
doi:10.4103/2228-7477.161482 pmid:26284171 pmcid:PMC4528353 fatcat:ubhex3m67fe4xeepen6ytfn5va

An Empirical Evaluation of Portfolios Approaches for solving CSPs [article]

Roberto Amadini, Maurizio Gabbrielli, Jacopo Mauro
2014 arXiv   pre-print
We compared models developed on top of off-the-shelf machine learning algorithms with respect to approaches used in the SAT field and adapted for CSPs, considering different portfolio sizes and using as  ...  Results indicate that the best SAT approaches have top performances also in the CSP field and are slightly more competitive than simple models built on top of classification algorithms.  ...  Off-the-shelf approaches For the approaches that used off-the-shelf machine learning classification algorithms we used a training set to train a classifier in order to select the best solver among those  ... 
arXiv:1212.0692v2 fatcat:7lts4ogzsbdi7lfketh2p7k6sy

Neural Decoding of EEG Signals with Machine Learning: A Systematic Review

Maham Saeidi, Waldemar Karwowski, Farzad V. Farahani, Krzysztof Fiok, Redha Taiar, P. A. Hancock, Awad Al-Juaid
2021 Brain Sciences  
A total of 75% of DL studies applied convolutional neural networks with various learning algorithms, and 36% of ML studies achieved competitive accuracy by using a support vector machine algorithm.  ...  Artificial intelligence, particularly machine learning (ML) and deep learning (DL) algorithms, are increasingly being applied to EEG data for pattern analysis, group membership classification, and brain-computer  ...  Acknowledgments: The authors would like to thank Pamela K. Douglas for providing valuable comments and suggestions.  ... 
doi:10.3390/brainsci11111525 pmid:34827524 pmcid:PMC8615531 fatcat:4ia7yrcptvgqhla7ccozb46xia
« Previous Showing results 1 — 15 out of 2,110 results