Skip to main content
Disciplines
Automotive Business IT + Informatics Construction + Real Estate Electrical Engineering + Electronics Energy + Sustainability Insurance + Risk Finance + Banking Management + Leadership Marketing + Sales Mechanical Engineering + Materials
Events
DE
EN
Books
Journals
Topic Page
Marketing
Start single access now
Access for companies
EXTENDED SEARCH
Log in
Top
Health and Technology
Published in: Health and Technology 4/2019

04-12-2018 | Original Paper

A new method for P300 detection in deep belief networks: Nesterov momentum and drop based learning rate

Authors: Sajedeh Morabbi, Mohammadreza Keyvanpour, Seyed Vahab Shojaedini

Published in: Health and Technology | Issue 4/2019

Log in

Activate our intelligent search to find suitable subject content or patents.

search-config
loading …

Abstract

Detecting P300 signal plays a vital role in Brain-Computer Interface (BCI) systems. In recent years, deep neural networks have been vastly utilized for P300 detection. However, by increasing the number of dimensions, the ratio of saddle points to local minima increases exponentially which hampers the performance of these networks for P300 detection. In this paper, a new method is introduced which improves the training procedure of Deep Belief Networks (DBN) by using Nesterov momentum. In another version of the proposed algorithm, the drop-based learning rate is also utilized to improve its performance. These strategies lead to escape saddle points in large scales of dimensions which causes the considerable improvement in P300 detection. Performance of the proposed algorithm is evaluated on a dataset of EPFL BCI group and compared with some other state-of-the-art methods. The results demonstrate that the best recognition rate is obtained by using the proposed method which is equal to 93.47%. The obtained results also show approximately 4.83% superiority in the accuracy of proposed algorithm against its alternatives.
previous article Comparison of PET imaging with a 68Ga-labelled PSMA ligand versus 18F-choline PET/CT for the diagnosis of Prostate Cancer & Radioprotection for involved personnel
next article A novel fall detection algorithm for elderly using SHIMMER wearable sensors

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

inform now
Footnotes
1
Evoked Related Potential
 
2
Electroencephalogram
 
3
Signal to Noise Ratio
 
4
Stochastic Gradient Descent
 
5
Non-Deterministic Polynomial
 
6
Inter Stimulus Interval
 
7
Root Mean Squared
 
8
True Positive Rate
 
9
True Negative Rate
 
Literature
1.
Chen SW, Lai YC. A signal processing based technique for P300 evoked potential detection with the applications into automated character recognition. EURASIP Journal on Advances in Signal Processing, 2014; Springer.
2.
Zahra Amini et al.: A comparative study of feature extraction methods in P300 detection. 17th Iranian Conference of Biomedical Engineering (ICBME), 2010.
3.
Vareka L, Mautner P. Using the windowed mean paradigm for single trial P300 detection. 38th International Conference of Telecommunication and Signal Processing (TSP), 2015.
4.
Farwell LA, Donchin E. Talking off the top of your head: toward a mental prosthesis utilizing event related brain potentials. Electroenceph Clin Neurophysiology. 1988;13(6):513–23.
5.
C. Morrales et al.: Single trial P300 detection in children using expert knowledge and SOM. 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2014.
6.
Hutagalung SS, et al. P300 detection based on extraction and classification in online BCI. Instrumentation Control and Automation (ICA), 3rd International Conference on IEEE, 2013.
7.
Kee CY, et al. Multi objective genetic algorithm as channel selection method for P300 and motor imagery dataset, Elsevier. Neurcomputing. 2015;161:120–31.CrossRef
8.
Sobhani A. P300 classification using Deep Belief Nets. MSC thesis, Colorado State University, 2014.
9.
Turnip A, et al. Adaptive nonlinear principle component analysis based multilayer neural network for 300 detection. IEEE/SICE International Symposium on System Integration (SII), 2011.
10.
Daubigney L, Pietquin O. Single trial P300 detection with Kalman ltering and SVMs. European Symposium on Artifacial Neural Networks (ESANN), 2011.
11.
Chumerin N, et al. P300 detection based on feature extraction in online Brain Computer Interface. Springer, Advances in Artificial Intelligence, Lecture Notes in Computer Science, Berlin, 2008; 5803.
12.
Rakotomamonjy A, Guigue V. BCI Compeition III: Dataset II - Ensemble of SVMs for BCI P300 speller. IEEE Transaction on Biomedical Engineering, 2008; 55(3).
13.
Jing M, et al. An automatic detection and location of P300 subcomponents using ICA. IEEE Internatinal Workshop on Biomedical Circuits and Systems, 2004.
14.
Jansen BH et al. An Exploratory study of factors affecting single trial P300 detection’, IEEE Transactions on Biomedical Engineering, 2004; 51(6).
15.
Mousavi SA, et al. P300 detection in Electroencephalographic signals for Brain Computer Interface systems: A Neural Network Approach. Springer, 2014; 277:355–363.
16.
Hutagalung SS, et al. P300 detection based on extraction and classification in online BCI. 3rd International Conference on Instrumentation Control and Automation (ICA), 2013.
17.
Zhang J-C, et al. P300 detection using Boosting Neural Networks with application to BCI. IEEE/ICME International Conference on Complex Medical Engineering, 2007.
18.
Cecotti H, Graser A. Convolutional neural networks for P300 detection with application to brain computer interfaces. IEEE Transaction On Pattern Analysis And Mechine Intelligence, 2011;33(3).
19.
Kawaguchi K. Deep learning without poor local minima. Advances in Neural Information Processing Systems. 2016.
20.
Dauphin YN, et al. Identisying and attacking the saddle point problem in high dimensional non-convex optimization. In: NIPS'14 Proceedings of 27th International Conference on Neural Information Processing System, 2014, pp. 2933–2941.
21.
Pascanu R, et al On the saddle point problem for non-convex optimization. arXiv:1405.4604, 2014.
22.
Anandkumar A, Ge R. Efficient approaches for escaping higher order saddle points in non-convex optimization. arXiv:1602.05908, 2016.
23.
Lee JD, et al. Gradient descent converges to minimizers. arXiv:1602.04915, 2016.
24.
Morse G, Stanley KO. Simple evolutionary optimization can rival stochastic gradient descent in neural networks. Proceedings of the Genetic and Evolutionary Computation Conference, 2016.
25.
Ge R, et al. Escaping from saddle points online stochastic gradient for Tensor Decomposition. arXiv:1503.02101v1, 2015.
26.
Wang Z. Adaptive normalized risk averting training for Deep Neural Network. arXiv:1506.02690v3, 2016.
27.
Goodfellow JJ, Courville A, Bengio Y. Deep Learning. MIT Press, 2015.
28.
Hoffmann U, et al. An efficient P300-based brain-compuer interface for disabled subjects. Journal of Neuroscience Methods, 2007.
29.
Bengio Y, et al. Deep learning. Nature. 2015;521:82–4.
30.
Zeiler MD. ADADELTA: an adaptive learning rate method. arXiv preprint arXiv:1212.5701, 2012.
31.
Ruder S. An overview of Gradient Descent optimazation algorithm. arXiv:1609.047477v1, 2016.
32.
Sutton RS. Two problems with backpropagation and other steepest descent learning procedures for networks. In: 8th Annual Conference of Cognitive Science Society, 1986.
33.
34.
35.
36.
Thompson DE. Performance assessment in brain-computer interface-based augmentative and alternative communication. Biomedical engineering online, 2013.
Metadata
Title
A new method for P300 detection in deep belief networks: Nesterov momentum and drop based learning rate
Authors
Sajedeh Morabbi
Mohammadreza Keyvanpour
Seyed Vahab Shojaedini
Publication date
04-12-2018
Publisher
Springer Berlin Heidelberg
Published in
Health and Technology / Issue 4/2019
Print ISSN: 2190-7188
Electronic ISSN: 2190-7196
DOI
https://doi.org/10.1007/s12553-018-0276-9

Other articles of this Issue 4/2019

Health and Technology 4/2019 Go to the issue

Original Paper

The effect of confidentiality and privacy concerns on adoption of personal health record from patient’s perspective

Retracted Article

Apoptotic suppression of inflammatory macrophages and foam cells in vascular tissue by miR-23a

Original Paper

Enhancing the classification of hand movements through sEMG signal and non-iterative methods

Original Paper

Fine-grained access control of EHRs in cloud using CP-ABE with user revocation

Original Paper

Variation in electronic health record adoption in European public hospitals: a configurational analysis of key functionalities

Review

Design for mobile mental health: an exploratory review

Premium Partner

    Image Credits