Home Classifying BCI signals from novice users with extreme learning machine
Article Open Access

Classifying BCI signals from novice users with extreme learning machine

  • Germán Rodríguez-Bermúdez EMAIL logo , Andrés Bueno-Crespo and F. José Martinez-Albaladejo
Published/Copyright: July 7, 2017

Abstract

Brain computer interface (BCI) allows to control external devices only with the electrical activity of the brain. In order to improve the system, several approaches have been proposed. However it is usual to test algorithms with standard BCI signals from experts users or from repositories available on Internet. In this work, extreme learning machine (ELM) has been tested with signals from 5 novel users to compare with standard classification algorithms. Experimental results show that ELM is a suitable method to classify electroencephalogram signals from novice users.

1 Introduction

The electroencephalogram (EEG) measures and records the electrical activity generated by brain structures. When brain cells (neurons) are activated, local current flows are produced therefore using electrodes placed on the scalp, the electrical activity of the brain can be collected and saved. In this way, electroencephalographic reading is a completely non-invasive procedure that can be applied repeatedly to patients, normal adults, and children with virtually no risk or limitation [14]. As it is widely accepted [5, 6], EEG signal is considered a chaotic dynamical system. EEG signal is chaotic because its amplitude changes randomly with respect to time, see Figure 1 [4, 12, 13].

Figure 1 Five seconds of EEG signal in a Motor Imagery Brain Computer Interface experiment from channel C3.(X axis in seconds and Y axis in microvolts)
Figure 1

Five seconds of EEG signal in a Motor Imagery Brain Computer Interface experiment from channel C3.(X axis in seconds and Y axis in microvolts)

The research on EEG signals offers an excellent opportunity to improve the understanding of the brain function. Thus the analysis of the EEG signal has been used to detect abnormal functions of the brain like disorders such as autism, dementia, schizophrenic, depression etc... [8, 1921]. Besides medical applications, the information extracted in this type of analysis has been used for non-medical purposes such as mental fatigue, emotion recognition or BCI.

A BCI offers an alternative to natural communication and control. A BCI is an artificial system that bypasses the body’s normal afferent pathways, which are the neuromuscular output channels [1]. This means that there is direct communication between the brain signal and the computer. A general scheme of a motor imagery (MI) BCI system could be represented by 5 main steps, as presented in Figure 2. All BCI systems start with a brain signal, thus it is crucial to acquire the brain activity and it is necessary to place electrodes on the scalp in the most suitable areas for each experiment. In a first stage, the user must develop a predefined mental task (motor imagery). The EEG signal changes according to the task and these signals are acquired by electrodes and transmitted to the next step. In step 2, the EEG signal is digitized, amplified and filtered in order to delete undesired signals called artifacts. The artifacts could be bio-signals such as heart beating or breach, or noise such as a power line. Then, the clean signal goes to step 3 where the system applies several techniques in order to compute features to be used as a descriptors of the EEG signals for the pattern recognition machine. The Features are classified in step 4, Pattern Classification, and the predictions are used or presented in step 5. Finally, the user observing the application gets feedback from the system and can modify his EEG signals to improve the performance of the BCI system.

Figure 2 Generic Scheme of a BCI system compound by 5 main blocks: 1) Mental task; 2) EEG acquisition; 3) Feature Extraction techniques; 4) Pattern Classification; 5) Applications
Figure 2

Generic Scheme of a BCI system compound by 5 main blocks: 1) Mental task; 2) EEG acquisition; 3) Feature Extraction techniques; 4) Pattern Classification; 5) Applications

Although there are several studies about BCI systems it is usual that every one selects one or two feature extraction techniques for step 3, and one or more from step 4 due to the lack of a unique way to implement BCI systems. In addition, it is common that researchers use signals from repository data available on Internet such as BCI competitions I-IV or from expert users. It is well known that a BCI system requires the adaptation of the user to the system, so it is necessary to train the user in order to get good results [1517]. In a MI BCI experiment an accuracy between 80% and 90% is expected after 6-9 training sessions of 20 minutes [18]. Nevertheless, and according to the state-of-the-art, certain subjects may face difficulties to use MI-based BCI systems and, in these cases, the classification performances are quite poor even using multiple training sessions [11]. Therefore, it is expected a previous selection of subjects with good classification performances in the experiments. In contrast, in this work the response of a system with EEG signals from 5 novel users without previous selection will be analyzed. We will test power spectrum density (PSD) as a feature extraction method combined with three classifiers: extreme learning machine (ELM); linear discriminant analysis (LDA) and support vector machine (SVM) in order to know which is the combination that reaches the highest classification accuracy.

Extreme learning machine (ELM) provides a fast and efficient multilayer perceptron (MLP) training [28]. Although Huang formalized the idea of ELM algorithm [25, 26], it was previously analyzed in other works [23, 24]. Huang demonstrated that the ELM is a universal approximator for a wide range of random computational nodes. ELM has been used for BCI systems, using it in its classic form, in voting optimized strategy, based on weighted probabilistic model, with adaptive extreme learning machine, and other variants [3740]. However, it has not been tested with novice users.

The main contribution of this work is to test the ELM suitability to classify EEG signals from novice subjects for BCI systems, which until now had not been used with this type of users.

The paper is organized as follows: Section 2 describes the acquisition of the EEG signal, the Feature extraction and, ELM; Section 3 describes the experimental work; Section 4 presents and discuss the experimental results; and in Section 5, the main concluding remarks are stated. Finally, the acknowledgements to the funding organizations and late Master are stated in this article.

2 Material and methods

2.1 EEG signal generation and acquisition

For this work we have used a dataset generated in the University Centre of Defence at the Spanish Air Force Academy, Spain. The dataset is composed by EEG signals from 5 right-handed males volunteers (21, 30, 30, 33, 33 years old) with normal vision implementing a Motor Imagery task. They have imagined the right and left hand movement according to a predefined timing. It is important to remark that none of these subjects have used a BCI system before the current experiment. It entails that there has been no a previous selection of the users, therefore, low classification results are expected in comparison with expert users.

The EEG signals have been captured with a g.USBamp (g.tec Medical Engineering GmbH, Austria) and two bipolar channels (C3-C4) thus passive electrodes were located at FC3, CP3, FC4 and CP4 positions. In this case Ag/AgCl passive electrodes were used. The amplifier was configured to acquired the data at 256Hz with 8 bits. A band pass filter was also applied between 0.5 and 30 Hz to erase artifacts. The users were comfortably seated in front of a screen to do the experiments. They must be relaxed and imagine the movement of the right or left hand looking at the screen when the BCI system requires it. Each experiment was composed by 40 trials (20 left and 20 right hand).

At the beginning of each trial (see Figure 3) the screen is black, then a cross appears and in second 2 an acoustic beep signal sounds beep to attract the user’s attention. At the third second of the trial the system presents an arrow pointing to the left or right for 1.25 s and the subject must imagine the movement of the right or left hand. Along 4 s the user must imagine the movement, therefore each trial needs 8 s. The system does not provide feedback to the users. Finally, it is important to remark that there is a random time between trials from 0.5 to 2.5 s to avoid adaptation. The system does not offer feedback to the users.

Figure 3 Scheme of BCI paradigm applied
Figure 3

Scheme of BCI paradigm applied

2.2 Feature extraction methods

In BCI, researchers have applied different techniques in step 3 [4, 10, 11]. Power spectrum density (PSD) has been computed as a feature extraction approach to test the ELM as a suitable method to be implemented in BCI systems to classify EEG signals from the first session of novice users. It is important to remark that PSD is a standard method for these systems [8]. Below there is a brief explanation about the algorithm used in this work.

2.2.1 Power spectral density

It is usual to decomposed EEG signals in four bands called α, β, θ and δ [2, 3]. However it is usual that researchers use only two bands in motor imagery BCI systems, α (8-13 Hz) and β (13-30Hz) [7, 10]. α waves are rhythmical waves and they are found in the EEGs of most adults when they are awake. When the awake person’s attention is directed to some specific type of mental activity, the α waves are replaced by higher frequency β waves. θ waves (4-8 Hz) normally occur in parietal and temporal regions in children, but they also appear during emotional stress in some adults [3].

It is important to note that the researchers only calculate α and β bands because they have the most discriminative information for the BCI experiments [7]. For computing these energies, the first step is to obtain the fast Fourier transform (FFT) of the EEG signals. Then, the corresponding coefficients of the α and β bands are added. Finally, the power of this addition is obtained by:

Pα=FFTEEGαFFTEEGαp2;(1)
Pβ=FFTEEGβFFTEEGβp2.(2)

where p is the number of points in the signal temporal window of the signal, FFT (EEGα) denotes the FFT of the EEG signal in α band and FFT* (EEGα) denotes its complex conjugate. The same notation is used for the β band of the EEG signal, (EEGβ).

2.3 Classifier

ELM is an algorithm used to train an MLP. It is based on the concept that if the MLP input weights are fixed to random values, it can be considered as a linear system, so the output weights can be easily obtained using the pseudo-inverse of the hidden neurons outputs matrix H for a given training set [28]. Given a set of N input vectors, an MLP can approximate N cases with zero error, i=1Nyiti=0,yi being the output network for the input vector xi with target vector ti. Thus, there are βj, wj and bj so that,

yi=j=1Mβjf(wjxi+bj)=ti,i=1,...,N.(3)

where βj = [βj1,βj2, …, βjm]T is the weight vector connecting the jth hidden node with the output nodes, wj = [wj1,wj2, …, wjn]T is the weight vector connecting the jth hidden node and the input nodes, and bj is the bias of the jth hidden node.

The previous N equations can be expressed by:

HB=T,(4)

where

H(w1,,wM,b1,,bM,x1,,xN)=f(w1x1+b1)f(wMx1+bM)f(w1xN+b1)f(wMxN+bM)N×M(5)
B=β1TβMTM×mandT=t1TtNTN×m(6)

where H ∈ 𝔎N × M is the hidden layer output matrix of the MLP, B ∈ 𝔎M × m is the output weight matrix, and T ∈ 𝔎N × m is the target matrix of the N training cases. The MLP training is given by the solution of the least square problem of (4). The optimal output weight layer is B^=HT, where H is the Moore-Penrose pseudo-inverse [27].

ELM needs to fix the number of hidden neurons. To do this, several pruned methods have been proposed [2934]. The most commonly used method to avoid the exhaustive search for the optimal value of M, is the ELM optimally pruned (OP-ELM) [34]. The OP-ELM sets a very high initial number of hidden neurons and classifies them according to their importance is solving the problem [35]. The pruning of neurons is done by choosing the combination of neurons that provides lower Leave-One-Out error [34].

3 Experimental work

The aim of the experiments was to test ELM as an algorithm to classify features extracted with a linear method (PSD) from novice subjects. In this study EEG signals have been used as described in Section 2.1. To get the features, in a first step, it has been computed from 2 windows of 1 second located in the center of each trial (5-6s and 6-7s), see Figure 3. Subsequently, each feature has been averaged in a single vector, thus there are two features (α and β) from each channel in each trial that go to the classifier. It is important to remark that we have done a previous evaluation of some of the most used linear feature extraction techniques such as PSD, Hjorth and AAR [8]. However preliminary results show that Hjorth and AAR present very low performance with all the classifiers tested in this work, while PSD could get acceptable results for these signals. Thus we have discarded others approaches and we have chosen PSD as the most suitable method to explore the ELM in BCI systems.

In order to get a reference, the performances of ELM have been compared with the standard LDA and SVM techniques. These methods are widely used by researchers in BCI environments due to the successful results obtained by them [9, 10]. For SVM, a linear kernel has been used, since a standard SVM with linear kernel is the most used method for BCI [9, 22]. For the ELM, a Gaussian kernel has been used, since it provides a non-linear solution and better results. In order to make an accurate and fair performance evaluation of the different classification approaches, this study uses a leave-one-out cross validation (LOO-CV) procedure [36]. LOO-CV avoids undesirable shifts from the random selection of training and test sets. For the N total number of samples involved in the study, one is retained for testing, and the remaining N-1 are used for training the classifier using the ELM approach. This process is repeated N times (i.e. an iteration for each input vector) Note that all cases are used for training and testing purposes during the N iterations of the LOO-CV procedure and, also, the performance evaluation measures are computed at the end of this iterative procedure.

4 Results

Table 1 shows the accuracy results obtained under LOO-CV (in %) using PSD as feature and three classifiers: ELM, LDA and SVM. As may be expected, values were not especially high. This is considered within normality due to the inexperience of the users and the absence of feedback in the system.

Table 1

Obtained PSD results (Accuracy -ACC-) by several classifier of five novel users. Performance evaluation has been done under a LOO-CV procedure.

Novel userMethodACC (%)
User1LDA66.67
SVM71.79
ELM67.23±02.84
User2LDA66.67
SVM51.28
ELM71.36±04.02
User3LDA56.41
SVM56.41
ELM69.79±02.40
User4LDA41.03
SVM53.81
ELM58.54±04.70
User5LDA71.79
SVM64.10
ELM65.67±03.21

For the three classifiers, LOO-CV has been used. LDA and SVM produce stable performance, however, ELM showed a random initialization of the weights, so 30 initializations were made, and the results have been shown in relation to mean and standard deviation.

According to the results ELM improves the LDA and SVM performance for User 2 with 71.36% ± 02.84% vs 66.67% of LDA, for User 3 with 69.79% ± 02.40% vs 56.41% of LDA and SVM, and for User 4 with 58.54% ± 04.70% vs 53.81% of SVM. However for User 1 SVM showed the best result with 71.79%, and for User 5 LDA improved the other results with 71.79%. It is interesting to note that ELM gets results between 65.67%± 3.21% and 71.36%± 4.02% in contrast to LDA that showed a low value for User 4 (41.03%) and SVM that presents 51.28% for User 2. Therefore, in this study, ELM achieved acceptable results for all users. As is shown in Figure 3, from the average data of the three methods, ELM improves significantly the mean classification performance of the LDA and SVM approaches: 66.51% vs. 60.51% and 59.47% respectively.

To validate this assertion, a non parametric statistical test has been performed. Specifically, the Wilcoxon Signed Ranks Test is used [41]. A peer review has been performed. Comparing ELM to LDA, the p-value obtained is 0.04, Which indicates that there are significant differences to 96%, being the best ELM. Likewise, when applying the test with ELM against SVM, the p-value=0.01 indicates that there are significant differences to 99%, being ELM better than SVM. However, there are no significant differences between LDA and SVM, since the p-value = 0.477.

It is widely known each subject is different and the performance of the same experiment and system could be different between users and even for the same user in different trials or sessions. Figure 4 shows the mean accuracy values of all users taking in to account the mean of the data of the three classifiers applied for each user. Thus, Users 1, 2 and 5 improved the mean value of the group in contrast with Users 2 and 3. Probably Users 1 and 2 have good skills to control BCI systems under motor imagery paradigms. Therefore, they could be suitable candidates to be trained to develop future experiments.

Figure 4 Comparison of the three methods means
Figure 4

Comparison of the three methods means

Figure 5 Comparison of the five users means
Figure 5

Comparison of the five users means

5 Conclusions and future work

This study tested an ELM with EEG signals from 5 novices users using a MI based BCI system. PSD features were computed and averaged from 2 central windows with 1 second each one. In order to compare the accuracy of the classification results obtained by ELM, two standard classifiers, LDA and SVM have been implemented. The results have been evaluated under LOO-CV and showed that, in contrast to LDA and SVM, ELM reached appropriate results in all the users, and besides that, it outperformed in 3 of 5 users standard methods. Therefore, the tested methodology showed a suitable performance for application in MI BCI systems.

Future research on this topic should be focused on testing ELM with wider data sets, as well as with signals from BCI expert users or from reference signals in BCI approaches such us BCI competitions. In addition, future studies could be accomplished to compute and combine features in three or four temporal windows to take in to account the time course of the signal. Other possibilities of the ELM will be evaluated, such as different variants of pruning and selection of the architecture. Finally, it might be interesting to implement more feature extraction techniques and classifiers.

Acknowledgement

This work has been partially supported by Spanish MINECO grant number MTM2014-51891-P and by the Spanish MINECO under grant TIN2016-78799-P (AEI/FEDER, UE). But the most important is that all the persons that have worked in this paper were fortunate to learn, to work and to be friends of PhD. Pedro José García Laencina. Rest in peace.

References

[1] Wolpaw J.R., Birbaumer N., McFarland D.J., Pfurtscheller G., Vaughan T.M., Brain computer interfaces for communication and control, Clin Neurophysiol, 2002, 113, 767–791.10.1017/CBO9780511545061.036Search in Google Scholar

[2] Sanei D., Chambers J., EEG Signal Processing. John Wiley & Sons., 2008.10.1002/9780470511923Search in Google Scholar

[3] Sabeti M., Boostani R., Katebi S., Price G., Selection of relevant features for EEG signal classification of schizophrenic patients, Biomedical Signal Processing and Control, 2007, 2(2).122-134.10.1016/j.bspc.2007.03.003Search in Google Scholar

[4] Rodríguez-Bermúdez G., García-Laencina P., Analysis of eeg signals using nonlinear dynamics and chaos: A review, Applied Mathematics & Information Sciences, 2015.Search in Google Scholar

[5] Tomasevic N., Neskovic A., Neskovic N., Neural network-based approach to EEG signal simulation, International Journal of Neural Systems, 2012, 22 (3), 1–16.10.1142/S0129065712500086Search in Google Scholar PubMed

[6] Tong S., Thankor N. V., Quantitative EEG Analysis Methods and Clinical Applications, Artech House.Search in Google Scholar

[7] Pfurtscheller G., Brunner C., Schlögl A., da Silva FL. Mu rhythm (de)synchronization and EEG single-trial classification of different motor imagery tasks, NeuroImage, 2006, 31(1), 153-159.10.1016/j.neuroimage.2005.12.003Search in Google Scholar PubMed

[8] Bashashati A., Fatourechi M., Ward R.K., Birch G.E., A survey of signal processing algorithms in brain-computer interfaces based on electrical brain signals, Journal of Neural Engineering, 2007, 4(2), 32-57.10.1088/1741-2560/4/2/R03Search in Google Scholar PubMed

[9] Lotte F., Congedo M., Lécuyer A., Lamarche F., Arnaldi B., A review of classification algorithms for EEG-based brain-computer interfaces, Journal of neural engineering, 2007, 4(2), 1-13.10.1088/1741-2560/4/2/R01Search in Google Scholar PubMed

[10] Nicolas-Alonso L., Gomez-Gil J., Brain computer interfaces, a review, Sensors, 2012, 1211–1279.10.3390/s120201211Search in Google Scholar PubMed PubMed Central

[11] Garca-Laencina P. J., Rodriguez-Bermudez G., Roca-Dorda J., Exploring dimensionality reduction of EEG features in motor imagery task classication, Expert Systems with Applications, 2014, 23 (04), 5285-5295.10.1016/j.eswa.2014.02.043Search in Google Scholar

[12] Álvarez-Arenas A., Belmonte-Beitia J., Calvo G.F., Nonlinear waves in a simple model of high-grade glioma, Applied Mathematics and Nonlinear Sciences, 2016, 1 (2), 405-422.10.21042/AMNS.2016.2.00035Search in Google Scholar

[13] Pérez-García V.M., Fitzpatrick S., Pérez-Romasanta L.A., Pesic M., Schucht P., Arana E., Sánchez-Gómez P., Applied mathematics and nonlinear sciences in the war on cancer, Applied Mathematics and Nonlinear Sciences, 2016, 1 (2), 423-436.10.21042/AMNS.2016.2.00036Search in Google Scholar

[14] Taplan M. Fundamentals of EEG measurement. Measurement Science Review, 2002, 2, 1-11.Search in Google Scholar

[15] Nijboer F., Furdea A., Gunst I., Mellinger J., McFarland D.J., Birbaumer N., K¨ubler A., An auditory brain–computer interface (BCI), Journal of Neuroscience Methods, 2008, 167, 43-50.10.1016/j.jneumeth.2007.02.009Search in Google Scholar

[16] Ahn M., Chan Jun S., Performance variation in motor imagery brain–computer interface: A brief review, Journal of Neuroscience Methods, 2015, 243, 103-110.10.1016/j.jneumeth.2015.01.033Search in Google Scholar

[17] Vukelić M., Gharabaghi A., Oscillatory entrainment of the motor cortical network during motor imagery is modulated by the feedback modality, NeuroImage, 2015, 111, 1-11.10.1016/j.neuroimage.2015.01.058Search in Google Scholar

[18] Guger C., Edlinger G., Harkam W., Niedermayer I., Pfurtscheller G.A., How Many People are Able to Operate an EEG-Based Brain-Computer Interface (BCI)?, IEEE Trasanctions on neural systems and rehabilitation engineering, 2003, 11(2), 145-147.10.1109/TNSRE.2003.814481Search in Google Scholar

[19] Stam C., Nonlinear dynamical analysis of EEG and MEG: Review of an emerging field, Clinical Neurophysiology, 2005, 116, 2266-2301.10.1016/j.clinph.2005.06.011Search in Google Scholar

[20] Liu J., Zhang C., Zheng C., EEG-based estimation of mental fatigue by using KPCA-HMM and complexity parameters, Biomedical Signal Processing and Control, 2010, 5, 124-130.10.1016/j.bspc.2010.01.001Search in Google Scholar

[21] Bajaj V., Pachori R., Classification of human emotions based on multiwavelet transform of EEG signals, 2013 AASRI Conference on Intelligent Systems and Control, Elsevier, Vancouver, 2013.10.1007/978-3-319-10978-7_8Search in Google Scholar

[22] Krusienski D. J., Sellers E. W., Cabestaing F., Bayoudh S., McFarland D. J., Vaughan T. M., and Wolpaw J. R., A comparison of classification techniques for the P300 speller, J. Neural Eng, 2006, 3(4), 299–305.10.1088/1741-2560/3/4/007Search in Google Scholar

[23] Pao Y.-H., Park G.-H., Sobajic D. J., Learning and generalization characteristics of the random vector functional-link net Neurocomputing, Elsevier, 1994, 6, 163-180.10.1016/0925-2312(94)90053-1Search in Google Scholar

[24] Igelnik B., Pao Y.-H., Stochastic choice of basis functions in adaptive function approximation and the functional-link net Neural Networks, IEEE Transactions on, 1995, 6, 1320-1329.10.1109/72.471375Search in Google Scholar PubMed

[25] Huang G.-B., Chen L., Convex incremental extreme learning machine, Neurocomputing, 2007, 70 (16), 3056–3062.10.1016/j.neucom.2007.02.009Search in Google Scholar

[26] Huang G.-B., Wang D. H., Lan Y. Extreme learning machines: a survey, International Journal of Machine Learning and Cybernetics, 2011, 2 (2), 107–122.10.1007/s13042-011-0019-ySearch in Google Scholar

[27] Serre D., Matrices: Theory and Applications, Springer, New York, 2002.Search in Google Scholar

[28] Huang G., Zhu Q., Siew C., Extreme learning machine: Theory and applications, Neurocomputing, 2006, 70 (1-3), 489–501.10.1016/j.neucom.2005.12.126Search in Google Scholar

[29] Rong H.-J., Ong Y.-S., Tan A.-H., Zhu Z., A fast pruned-extreme learning machine for classification problem, Neurocomputing, 2008, 72 (1-3), 359–366.10.1016/j.neucom.2008.01.005Search in Google Scholar

[30] Miche Y., Bas P., Jutten C., Simula O., Lendasse A., A methodology for building regression models using extreme learning machine: OP-ELM, In: Proceedings of the European Symposium on Artificial Neural Networks (ESANN), 2008, 247–252.Search in Google Scholar

[31] Miche Y., Sorjamaa A., Lendasse A., OP-ELM: Theory, experiments and a toolbox, In: Proceedings of the International Conference on Artificial Neural Networks (ICANN), LNCS, 2008, 5163, 145–154.10.1007/978-3-540-87536-9_16Search in Google Scholar

[32] Mateo F., Lendasse A., A variable selection approach based on the delta test for extreme learning machine models, In: Proceedings of the European Symposium on Time Series Prediction (ESTP) 2008, 57–66.Search in Google Scholar

[33] Miche Y., Lendasse A., A faster model selection criterion for OPELM and OP-KNN: Hannan-quinn criterion, In: Proceeding of the European Symposium on Artificial Neural Networks (ESANN), 2009, 177–182.Search in Google Scholar

[34] Miche Y., Sorjamaa A., Bas P., Simula O., Jutten C., Lendasse A., OP-ELM: Optimally Pruned Extreme Learning Machine, IEEE Transactions on Neural Networks, 2009, 21 (1), 158–162.10.1109/TNN.2009.2036259Search in Google Scholar PubMed

[35] Similä T., Tikka J., Multiresponse sparse regression with application to multidimensional scaling, In: Proceedings of the 15th International Conference on Artificial Neural Networks: Formal Models and Their Applications - ICANN 2005, LNCS, 2005, 3697, 97–102.10.1007/11550907_16Search in Google Scholar

[36] Alpaydin E., Introduction to Machine Learning, MIT Press. Cambridge, MA, USA, 2010.Search in Google Scholar

[37] Duan L. and Zhong H. and Miao J., Yang Z., Ma W., Zhang X., A voting optimized strategy based on ELM for improving classification of motor imagery BCI data, Cognitive Computation, 2014, 477-483.10.1007/s12559-014-9264-1Search in Google Scholar

[38] Bamdadian A., Guan C., Ang K.K., Xu J., Improving session-to-session transfer performance of motor imagery-based BCI using adaptive extreme learning machine, Engineering in Medicine and Biology Society (EMBC), 2013 35th Annual International Conference of the IEEE, 2013, 2188-2191.10.1109/EMBC.2013.6609969Search in Google Scholar PubMed

[39] Tan P., Tan G.-Z., Cai Z.-X., Sa W.-P., Zou Y.-Q., Using ELM-based weighted probabilistic model in the classification of synchronous EEG BCI, Medical & biological engineering & computing, 2017, 55 (1), 33-43.10.1007/s11517-016-1493-xSearch in Google Scholar PubMed

[40] Tan P., Sa W., Yu L., Applying Extreme Learning Machine to classification of EEG BCI, Cyber Technology in Automation, Control, and Intelligent Systems (CYBER), 2016 IEEE International Conference on, 2016, 228-232.10.1109/CYBER.2016.7574827Search in Google Scholar

[41] Kruskal W. H. Historical notes on the wilcoxon unpaired two-sample test, Journal of the American Statistical Association, 1957, 52 (279), 356–360.10.1080/01621459.1957.10501395Search in Google Scholar

Received: 2017-2-14
Accepted: 2017-4-28
Published Online: 2017-7-7

© 2017 G. Rodríguez-Bermúdez et al.

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Articles in the same Issue

  1. Regular Articles
  2. Analysis of a New Fractional Model for Damped Bergers’ Equation
  3. Regular Articles
  4. Optimal homotopy perturbation method for nonlinear differential equations governing MHD Jeffery-Hamel flow with heat transfer problem
  5. Regular Articles
  6. Semi- analytic numerical method for solution of time-space fractional heat and wave type equations with variable coefficients
  7. Regular Articles
  8. Investigation of a curve using Frenet frame in the lightlike cone
  9. Regular Articles
  10. Construction of complex networks from time series based on the cross correlation interval
  11. Regular Articles
  12. Nonlinear Schrödinger approach to European option pricing
  13. Regular Articles
  14. A modified cubic B-spline differential quadrature method for three-dimensional non-linear diffusion equations
  15. Regular Articles
  16. A new miniaturized negative-index meta-atom for tri-band applications
  17. Regular Articles
  18. Seismic stability of the survey areas of potential sites for the deep geological repository of the spent nuclear fuel
  19. Regular Articles
  20. Distributed containment control of heterogeneous fractional-order multi-agent systems with communication delays
  21. Regular Articles
  22. Sensitivity analysis and economic optimization studies of inverted five-spot gas cycling in gas condensate reservoir
  23. Regular Articles
  24. Quantum mechanics with geometric constraints of Friedmann type
  25. Regular Articles
  26. Modeling and Simulation for an 8 kW Three-Phase Grid-Connected Photo-Voltaic Power System
  27. Regular Articles
  28. Application of the optimal homotopy asymptotic method to nonlinear Bingham fluid dampers
  29. Regular Articles
  30. Analysis of Drude model using fractional derivatives without singular kernels
  31. Regular Articles
  32. An unsteady MHD Maxwell nanofluid flow with convective boundary conditions using spectral local linearization method
  33. Regular Articles
  34. New analytical solutions for conformable fractional PDEs arising in mathematical physics by exp-function method
  35. Regular Articles
  36. Quantum mechanical calculation of electron spin
  37. Regular Articles
  38. CO2 capture by polymeric membranes composed of hyper-branched polymers with dense poly(oxyethylene) comb and poly(amidoamine)
  39. Regular Articles
  40. Chain on a cone
  41. Regular Articles
  42. Multi-task feature learning by using trace norm regularization
  43. Regular Articles
  44. Superluminal tunneling of a relativistic half-integer spin particle through a potential barrier
  45. Regular Articles
  46. Neutrosophic triplet normed space
  47. Regular Articles
  48. Lie algebraic discussion for affinity based information diffusion in social networks
  49. Regular Articles
  50. Radiation dose and cancer risk estimates in helical CT for pulmonary tuberculosis infections
  51. Regular Articles
  52. A comparison study of steady-state vibrations with single fractional-order and distributed-order derivatives
  53. Regular Articles
  54. Some new remarks on MHD Jeffery-Hamel fluid flow problem
  55. Regular Articles
  56. Numerical investigation of magnetohydrodynamic slip flow of power-law nanofluid with temperature dependent viscosity and thermal conductivity over a permeable surface
  57. Regular Articles
  58. Charge conservation in a gravitational field in the scalar ether theory
  59. Regular Articles
  60. Measurement problem and local hidden variables with entangled photons
  61. Regular Articles
  62. Compression of hyper-spectral images using an accelerated nonnegative tensor decomposition
  63. Regular Articles
  64. Fabrication and application of coaxial polyvinyl alcohol/chitosan nanofiber membranes
  65. Regular Articles
  66. Calculating degree-based topological indices of dominating David derived networks
  67. Regular Articles
  68. The structure and conductivity of polyelectrolyte based on MEH-PPV and potassium iodide (KI) for dye-sensitized solar cells
  69. Regular Articles
  70. Chiral symmetry restoration and the critical end point in QCD
  71. Regular Articles
  72. Numerical solution for fractional Bratu’s initial value problem
  73. Regular Articles
  74. Structure and optical properties of TiO2 thin films deposited by ALD method
  75. Regular Articles
  76. Quadruple multi-wavelength conversion for access network scalability based on cross-phase modulation in an SOA-MZI
  77. Regular Articles
  78. Application of ANNs approach for wave-like and heat-like equations
  79. Special issue on Nonlinear Dynamics in General and Dynamical Systems in particular
  80. Study on node importance evaluation of the high-speed passenger traffic complex network based on the Structural Hole Theory
  81. Special issue on Nonlinear Dynamics in General and Dynamical Systems in particular
  82. A mathematical/physics model to measure the role of information and communication technology in some economies: the Chinese case
  83. Special issue on Nonlinear Dynamics in General and Dynamical Systems in particular
  84. Numerical modeling of the thermoelectric cooler with a complementary equation for heat circulation in air gaps
  85. Special issue on Nonlinear Dynamics in General and Dynamical Systems in particular
  86. On the libration collinear points in the restricted three – body problem
  87. Special issue on Nonlinear Dynamics in General and Dynamical Systems in particular
  88. Research on Critical Nodes Algorithm in Social Complex Networks
  89. Special issue on Nonlinear Dynamics in General and Dynamical Systems in particular
  90. A simulation based research on chance constrained programming in robust facility location problem
  91. Special issue on Nonlinear Dynamics in General and Dynamical Systems in particular
  92. A mathematical/physics carbon emission reduction strategy for building supply chain network based on carbon tax policy
  93. Special issue on Nonlinear Dynamics in General and Dynamical Systems in particular
  94. Mathematical analysis of the impact mechanism of information platform on agro-product supply chain and agro-product competitiveness
  95. Special issue on Nonlinear Dynamics in General and Dynamical Systems in particular
  96. A real negative selection algorithm with evolutionary preference for anomaly detection
  97. Special issue on Nonlinear Dynamics in General and Dynamical Systems in particular
  98. A privacy-preserving parallel and homomorphic encryption scheme
  99. Special issue on Nonlinear Dynamics in General and Dynamical Systems in particular
  100. Random walk-based similarity measure method for patterns in complex object
  101. Special issue on Nonlinear Dynamics in General and Dynamical Systems in particular
  102. A Mathematical Study of Accessibility and Cohesion Degree in a High-Speed Rail Station Connected to an Urban Bus Transport Network
  103. Special issue on Nonlinear Dynamics in General and Dynamical Systems in particular
  104. Design and Simulation of the Integrated Navigation System based on Extended Kalman Filter
  105. Special issue on Nonlinear Dynamics in General and Dynamical Systems in particular
  106. Oil exploration oriented multi-sensor image fusion algorithm
  107. Special issue on Nonlinear Dynamics in General and Dynamical Systems in particular
  108. Analysis of Product Distribution Strategy in Digital Publishing Industry Based on Game-Theory
  109. Special issue on Nonlinear Dynamics in General and Dynamical Systems in particular
  110. Expanded Study on the accumulation effect of tourism under the constraint of structure
  111. Special issue on Nonlinear Dynamics in General and Dynamical Systems in particular
  112. Unstructured P2P Network Load Balance Strategy Based on Multilevel Partitioning of Hypergraph
  113. Special issue on Nonlinear Dynamics in General and Dynamical Systems in particular
  114. Research on the method of information system risk state estimation based on clustering particle filter
  115. Special issue on Nonlinear Dynamics in General and Dynamical Systems in particular
  116. Demand forecasting and information platform in tourism
  117. Special issue on Nonlinear Dynamics in General and Dynamical Systems in particular
  118. Physical-chemical properties studying of molecular structures via topological index calculating
  119. Special issue on Nonlinear Dynamics in General and Dynamical Systems in particular
  120. Local kernel nonparametric discriminant analysis for adaptive extraction of complex structures
  121. Special issue on Nonlinear Dynamics in General and Dynamical Systems in particular
  122. City traffic flow breakdown prediction based on fuzzy rough set
  123. Special issue on Nonlinear Dynamics in General and Dynamical Systems in particular
  124. Conservation laws for a strongly damped wave equation
  125. Special issue on Nonlinear Dynamics in General and Dynamical Systems in particular
  126. Blending type approximation by Stancu-Kantorovich operators based on Pólya-Eggenberger distribution
  127. Special issue on Nonlinear Dynamics in General and Dynamical Systems in particular
  128. Computing the Ediz eccentric connectivity index of discrete dynamic structures
  129. Special issue on Nonlinear Dynamics in General and Dynamical Systems in particular
  130. A discrete epidemic model for bovine Babesiosis disease and tick populations
  131. Special issue on Nonlinear Dynamics in General and Dynamical Systems in particular
  132. Study on maintaining formations during satellite formation flying based on SDRE and LQR
  133. Special issue on Nonlinear Dynamics in General and Dynamical Systems in particular
  134. Relationship between solitary pulmonary nodule lung cancer and CT image features based on gradual clustering
  135. Special issue on Nonlinear Dynamics in General and Dynamical Systems in particular
  136. A novel fast target tracking method for UAV aerial image
  137. Special issue on Nonlinear Dynamics in General and Dynamical Systems in particular
  138. Fuzzy comprehensive evaluation model of interuniversity collaborative learning based on network
  139. Special issue on Nonlinear Dynamics in General and Dynamical Systems in particular
  140. Conservation laws, classical symmetries and exact solutions of the generalized KdV-Burgers-Kuramoto equation
  141. Special issue on Nonlinear Dynamics in General and Dynamical Systems in particular
  142. After notes on self-similarity exponent for fractal structures
  143. Special issue on Nonlinear Dynamics in General and Dynamical Systems in particular
  144. Excitation probability and effective temperature in the stationary regime of conductivity for Coulomb Glasses
  145. Special issue on Nonlinear Dynamics in General and Dynamical Systems in particular
  146. Comparisons of feature extraction algorithm based on unmanned aerial vehicle image
  147. Special issue on Nonlinear Dynamics in General and Dynamical Systems in particular
  148. Research on identification method of heavy vehicle rollover based on hidden Markov model
  149. Special issue on Nonlinear Dynamics in General and Dynamical Systems in particular
  150. Classifying BCI signals from novice users with extreme learning machine
  151. Special issue on Nonlinear Dynamics in General and Dynamical Systems in particular
  152. Topics on data transmission problem in software definition network
  153. Special issue on Nonlinear Dynamics in General and Dynamical Systems in particular
  154. Statistical inferences with jointly type-II censored samples from two Pareto distributions
  155. Special issue on Nonlinear Dynamics in General and Dynamical Systems in particular
  156. Estimation for coefficient of variation of an extension of the exponential distribution under type-II censoring scheme
  157. Special issue on Nonlinear Dynamics in General and Dynamical Systems in particular
  158. Analysis on trust influencing factors and trust model from multiple perspectives of online Auction
  159. Special Issue on Advances on Modelling of Flowing and Transport in Porous Media
  160. Coupling of two-phase flow in fractured-vuggy reservoir with filling medium
  161. Special Issue on Advances on Modelling of Flowing and Transport in Porous Media
  162. Production decline type curves analysis of a finite conductivity fractured well in coalbed methane reservoirs
  163. Special Issue on Advances on Modelling of Flowing and Transport in Porous Media
  164. Flow Characteristic and Heat Transfer for Non-Newtonian Nanofluid in Rectangular Microchannels with Teardrop Dimples/Protrusions
  165. Special Issue on Advances on Modelling of Flowing and Transport in Porous Media
  166. The size prediction of potential inclusions embedded in the sub-surface of fused silica by damage morphology
  167. Special Issue on Advances on Modelling of Flowing and Transport in Porous Media
  168. Research on carbonate reservoir interwell connectivity based on a modified diffusivity filter model
  169. Special Issue on Advances on Modelling of Flowing and Transport in Porous Media
  170. The method of the spatial locating of macroscopic throats based-on the inversion of dynamic interwell connectivity
  171. Special Issue on Advances on Modelling of Flowing and Transport in Porous Media
  172. Unsteady mixed convection flow through a permeable stretching flat surface with partial slip effects through MHD nanofluid using spectral relaxation method
  173. Special Issue on Advances on Modelling of Flowing and Transport in Porous Media
  174. A volumetric ablation model of EPDM considering complex physicochemical process in porous structure of char layer
  175. Special Issue on Advances on Modelling of Flowing and Transport in Porous Media
  176. Numerical simulation on ferrofluid flow in fractured porous media based on discrete-fracture model
  177. Special Issue on Advances on Modelling of Flowing and Transport in Porous Media
  178. Macroscopic lattice Boltzmann model for heat and moisture transfer process with phase transformation in unsaturated porous media during freezing process
  179. Special Issue on Advances on Modelling of Flowing and Transport in Porous Media
  180. Modelling of intermittent microwave convective drying: parameter sensitivity
  181. Special Issue on Advances on Modelling of Flowing and Transport in Porous Media
  182. Simulating gas-water relative permeabilities for nanoscale porous media with interfacial effects
  183. Special Issue on Advances on Modelling of Flowing and Transport in Porous Media
  184. Simulation of counter-current imbibition in water-wet fractured reservoirs based on discrete-fracture model
  185. Special Issue on Advances on Modelling of Flowing and Transport in Porous Media
  186. Investigation effect of wettability and heterogeneity in water flooding and on microscopic residual oil distribution in tight sandstone cores with NMR technique
  187. Special Issue on Advances on Modelling of Flowing and Transport in Porous Media
  188. Analytical modeling of coupled flow and geomechanics for vertical fractured well in tight gas reservoirs
  189. Special Issue on Ever-New "Loopholes" in Bell’s Argument and Experimental Tests
  190. Special Issue: Ever New "Loopholes" in Bell’s Argument and Experimental Tests
  191. Special Issue on Ever-New "Loopholes" in Bell’s Argument and Experimental Tests
  192. The ultimate loophole in Bell’s theorem: The inequality is identically satisfied by data sets composed of ±1′s assuming merely that they exist
  193. Special Issue on Ever-New "Loopholes" in Bell’s Argument and Experimental Tests
  194. Erratum to: The ultimate loophole in Bell’s theorem: The inequality is identically satisfied by data sets composed of ±1′s assuming merely that they exist
  195. Special Issue on Ever-New "Loopholes" in Bell’s Argument and Experimental Tests
  196. Rhetoric, logic, and experiment in the quantum nonlocality debate
  197. Special Issue on Ever-New "Loopholes" in Bell’s Argument and Experimental Tests
  198. What If Quantum Theory Violates All Mathematics?
  199. Special Issue on Ever-New "Loopholes" in Bell’s Argument and Experimental Tests
  200. Relativity, anomalies and objectivity loophole in recent tests of local realism
  201. Special Issue on Ever-New "Loopholes" in Bell’s Argument and Experimental Tests
  202. The photon identification loophole in EPRB experiments: computer models with single-wing selection
  203. Special Issue on Ever-New "Loopholes" in Bell’s Argument and Experimental Tests
  204. Bohr against Bell: complementarity versus nonlocality
  205. Special Issue on Ever-New "Loopholes" in Bell’s Argument and Experimental Tests
  206. Is Einsteinian no-signalling violated in Bell tests?
  207. Special Issue on Ever-New "Loopholes" in Bell’s Argument and Experimental Tests
  208. Bell’s “Theorem”: loopholes vs. conceptual flaws
  209. Special Issue on Ever-New "Loopholes" in Bell’s Argument and Experimental Tests
  210. Nonrecurrence and Bell-like inequalities
  211. Special Issue: The 18th International Symposium on Electromagnetic Fields in Mechatronics, Electrical and Electronic Engineering ISEF 2017
  212. Three-dimensional computer models of electrospinning systems
  213. Special Issue: The 18th International Symposium on Electromagnetic Fields in Mechatronics, Electrical and Electronic Engineering ISEF 2017
  214. Electric field computation and measurements in the electroporation of inhomogeneous samples
  215. Special Issue: The 18th International Symposium on Electromagnetic Fields in Mechatronics, Electrical and Electronic Engineering ISEF 2017
  216. Modelling of magnetostriction of transformer magnetic core for vibration analysis
  217. Special Issue: The 18th International Symposium on Electromagnetic Fields in Mechatronics, Electrical and Electronic Engineering ISEF 2017
  218. Comparison of the fractional power motor with cores made of various magnetic materials
  219. Special Issue: The 18th International Symposium on Electromagnetic Fields in Mechatronics, Electrical and Electronic Engineering ISEF 2017
  220. Dynamics of the line-start reluctance motor with rotor made of SMC material
  221. Special Issue: The 18th International Symposium on Electromagnetic Fields in Mechatronics, Electrical and Electronic Engineering ISEF 2017
  222. Inhomogeneous dielectrics: conformal mapping and finite-element models
  223. Special Issue: The 18th International Symposium on Electromagnetic Fields in Mechatronics, Electrical and Electronic Engineering ISEF 2017
  224. Topology optimization of induction heating model using sequential linear programming based on move limit with adaptive relaxation
  225. Special Issue: The 18th International Symposium on Electromagnetic Fields in Mechatronics, Electrical and Electronic Engineering ISEF 2017
  226. Detection of inter-turn short-circuit at start-up of induction machine based on torque analysis
  227. Special Issue: The 18th International Symposium on Electromagnetic Fields in Mechatronics, Electrical and Electronic Engineering ISEF 2017
  228. Current superimposition variable flux reluctance motor with 8 salient poles
  229. Special Issue: The 18th International Symposium on Electromagnetic Fields in Mechatronics, Electrical and Electronic Engineering ISEF 2017
  230. Modelling axial vibration in windings of power transformers
  231. Special Issue: The 18th International Symposium on Electromagnetic Fields in Mechatronics, Electrical and Electronic Engineering ISEF 2017
  232. Field analysis & eddy current losses calculation in five-phase tubular actuator
  233. Special Issue: The 18th International Symposium on Electromagnetic Fields in Mechatronics, Electrical and Electronic Engineering ISEF 2017
  234. Hybrid excited claw pole generator with skewed and non-skewed permanent magnets
  235. Special Issue: The 18th International Symposium on Electromagnetic Fields in Mechatronics, Electrical and Electronic Engineering ISEF 2017
  236. Electromagnetic phenomena analysis in brushless DC motor with speed control using PWM method
  237. Special Issue: The 18th International Symposium on Electromagnetic Fields in Mechatronics, Electrical and Electronic Engineering ISEF 2017
  238. Field-circuit analysis and measurements of a single-phase self-excited induction generator
  239. Special Issue: The 18th International Symposium on Electromagnetic Fields in Mechatronics, Electrical and Electronic Engineering ISEF 2017
  240. A comparative analysis between classical and modified approach of description of the electrical machine windings by means of T0 method
  241. Special Issue: The 18th International Symposium on Electromagnetic Fields in Mechatronics, Electrical and Electronic Engineering ISEF 2017
  242. Field-based optimal-design of an electric motor: a new sensitivity formulation
  243. Special Issue: The 18th International Symposium on Electromagnetic Fields in Mechatronics, Electrical and Electronic Engineering ISEF 2017
  244. Application of the parametric proper generalized decomposition to the frequency-dependent calculation of the impedance of an AC line with rectangular conductors
  245. Special Issue: The 18th International Symposium on Electromagnetic Fields in Mechatronics, Electrical and Electronic Engineering ISEF 2017
  246. Virtual reality as a new trend in mechanical and electrical engineering education
  247. Special Issue: The 18th International Symposium on Electromagnetic Fields in Mechatronics, Electrical and Electronic Engineering ISEF 2017
  248. Holonomicity analysis of electromechanical systems
  249. Special Issue: The 18th International Symposium on Electromagnetic Fields in Mechatronics, Electrical and Electronic Engineering ISEF 2017
  250. An accurate reactive power control study in virtual flux droop control
  251. Special Issue: The 18th International Symposium on Electromagnetic Fields in Mechatronics, Electrical and Electronic Engineering ISEF 2017
  252. Localized probability of improvement for kriging based multi-objective optimization
  253. Special Issue: The 18th International Symposium on Electromagnetic Fields in Mechatronics, Electrical and Electronic Engineering ISEF 2017
  254. Research of influence of open-winding faults on properties of brushless permanent magnets motor
  255. Special Issue: The 18th International Symposium on Electromagnetic Fields in Mechatronics, Electrical and Electronic Engineering ISEF 2017
  256. Optimal design of the rotor geometry of line-start permanent magnet synchronous motor using the bat algorithm
  257. Special Issue: The 18th International Symposium on Electromagnetic Fields in Mechatronics, Electrical and Electronic Engineering ISEF 2017
  258. Model of depositing layer on cylindrical surface produced by induction-assisted laser cladding process
  259. Special Issue: The 18th International Symposium on Electromagnetic Fields in Mechatronics, Electrical and Electronic Engineering ISEF 2017
  260. Detection of inter-turn faults in transformer winding using the capacitor discharge method
  261. Special Issue: The 18th International Symposium on Electromagnetic Fields in Mechatronics, Electrical and Electronic Engineering ISEF 2017
  262. A novel hybrid genetic algorithm for optimal design of IPM machines for electric vehicle
  263. Special Issue: The 18th International Symposium on Electromagnetic Fields in Mechatronics, Electrical and Electronic Engineering ISEF 2017
  264. Lamination effects on a 3D model of the magnetic core of power transformers
  265. Special Issue: The 18th International Symposium on Electromagnetic Fields in Mechatronics, Electrical and Electronic Engineering ISEF 2017
  266. Detection of vertical disparity in three-dimensional visualizations
  267. Special Issue: The 18th International Symposium on Electromagnetic Fields in Mechatronics, Electrical and Electronic Engineering ISEF 2017
  268. Calculations of magnetic field in dynamo sheets taking into account their texture
  269. Special Issue: The 18th International Symposium on Electromagnetic Fields in Mechatronics, Electrical and Electronic Engineering ISEF 2017
  270. 3-dimensional computer model of electrospinning multicapillary unit used for electrostatic field analysis
  271. Special Issue: The 18th International Symposium on Electromagnetic Fields in Mechatronics, Electrical and Electronic Engineering ISEF 2017
  272. Optimization of wearable microwave antenna with simplified electromagnetic model of the human body
  273. Special Issue: The 18th International Symposium on Electromagnetic Fields in Mechatronics, Electrical and Electronic Engineering ISEF 2017
  274. Induction heating process of ferromagnetic filled carbon nanotubes based on 3-D model
  275. Special Issue: The 18th International Symposium on Electromagnetic Fields in Mechatronics, Electrical and Electronic Engineering ISEF 2017
  276. Speed control of an induction motor by 6-switched 3-level inverter
Downloaded on 3.11.2025 from https://www.degruyterbrill.com/document/doi/10.1515/phys-2017-0056/html
Scroll to top button