Research on Biomedical Engineering
https://rbejournal.org/article/doi/10.1590/2446-4740.01815
Research on Biomedical Engineering
Original Article

Influences of the signal border extension in the discrete wavelet transform in EEG spike detection

Pacola, Edras Reily; Quandt, Verônica Isabela; Liberalesso, Paulo Breno Noronha; Pichorim, Sérgio Francisco; Gamba, Humberto Remigio; Sovierzoski, Miguel Antônio

Downloads: 0
Views: 394

Abstract

Introduction: The discrete wavelet transform is used in many studies as signal preprocessor for EEG spike detection. An inherent process of this mathematical tool is the recursive wavelet convolution over the signal that is decomposed into detail and approximation coefficients. To perform these convolutions, firstly it is necessary to extend signal borders. The selection of an unsuitable border extension algorithm may increase the false positive rate of an EEG spike detector. Methods: In this study we analyzed nine different border extensions used for convolution and 19 mother wavelets commonly seen in other EEG spike detectors in the literature. Results: The border extension may degrade an EEG spike detector up to 44.11%. Furthermore, results behave differently for distinct number of wavelet coefficients. Conclusion: There is not a best border extension to be used with any EEG spike detector based on the discrete wavelet transform, but the selection of the most adequate border extension is related to the number of coefficients of a mother wavelet.

Keywords

EEG, Spike, Border extension, Discrete wavelet transform, LDA.

References

Adeli H, Ghosh-Dastidar S, Dadmehr N. A wavelet-chaos methodology for analysis of EEGs and EEG subbands to detect seizure and epilepsy. IEEE Transactions on Biomedical Engineering. 2007; 54(2):205-11. http://dx.doi.org/10.1109/TBME.2006.886855. PMid:17278577.

Birot G, Kachenoura A, Albera L, Benar C, Wendling F. Automatic detection of fast ripples. Journal of Neuroscience Methods. 2013; 213(2):236-49. http://dx.doi.org/10.1016/j.jneumeth.2012.12.013. PMid:23261773.

Chatrian G, Bergamini L, Dondey M, Klass D. A glossary of terms most commonly used by clinical electroencephalographers. Electroencephalography and Clinical Neurophysiology. 1974; 37(5):538-48. http://dx.doi.org/10.1016/0013-4694(74)90099-6. PMid:4138729.

Correa AG, Orosco L, Diez P, Laciar E. Automatic detection of epileptic seizures in long-term EEG records. Computers in Biology and Medicine. 2015; 57:66-73. http://dx.doi.org/10.1016/j.compbiomed.2014.11.013. PMid:25531725.

Daubechies I. The wavelet transform, time-frequency localization and signal analysis. IEEE Transactions on Information Theory. 1990; 36(5):961-1005. http://dx.doi.org/10.1109/18.57199.

Duda RO, Hart PE, Stork DG. Pattern classification. 2nd ed. New York: Wiley Interscience; 2001.

Ercelebi E, Subasi A. Classification of EEG for epilepsy diagnosis in wavelet domain using artificial neural network and multi linear regression. In: Signal Processing and Communications Applications; 2006 Apr 17-19; Antalya. New York: IEEE; 2006. p. 1-4.

Erkel ARV, Pattynama PMT. Receiver operating characteristic (ROC) analysis: basic principles and applications in radiology. European Journal of Radiology. 1998; 27(2):88-94. http://dx.doi.org/10.1016/S0720-048X(97)00157-5. PMid:9639133.

Fawcett T. An introduction to ROC analysis. Pattern Recognition Letters. 2006; 27(8):861-74. http://dx.doi.org/10.1016/j.patrec.2005.10.010.

Gajic D, Djurovic Z, Gennaro S, Gustafsson F. Classification of EEG signals for detection of epileptic seizures based on wavelets and statistical pattern recognition. Biomedical Engineering: Applications, Basis and Communications. 2014; 26(02):1450021. http://dx.doi.org/10.4015/S1016237214500215.

Gotman J. A computer system to assist in the evaluation of the EEGs of epileptic patients. Behavior Research Methods and Instrumentation. 1981; 4(4):525-31. http://dx.doi.org/10.3758/BF03202062.

Indiradevi KP, Elias E, Sathidevi PS, Nayak SD, Radhakrishnan K. A multi-level wavelet approach for automatic detection of epileptic spikes in the electroencephalogram. Computers in Biology and Medicine. 2008; 38(7):805-16. http://dx.doi.org/10.1016/j.compbiomed.2008.04.010. PMid:18550047.

Inuso G, Foresta FL, Mammone N, Morabito FC. Brain activity investigation by EEG processing: wavelet analysis, kurtosis and renyi’s entropy for artifact detection. In: International Conference on Information Acquisition – ICIA 07; 2007 July 9-11; Jeju City, Korea. New York: IEEE; 2007. p. 195-200.

Kalayci T, Ozdamar O, Erdol N. The use of wavelet transform as a preprocessor for the neural network detection of EEG spikes. In: Proceedings of the 1994 IEEE Southeastcon ’94. Creative technology transfer: a global affair; 2014 Apr 10-13; Miami, USA. New York: IEEE; 1994. Vol. 1, p. 1-3. http://dx.doi.org/10.1109/SECON.1994.324252.

Katunin A. Reduction of boundary effect during structural damage identification using wavelet transform. Selected Engineering Problems. 2012; 1:97-102.

Kumar Y, Dewal ML, Anand RS. Epileptic seizures detection in EEG using DWT-based ApEn and artificial neural network. Signal, Video and Image Processing. 2014; 8(7):1323-34. http://dx.doi.org/10.1007/s11760-012-0362-9.

Lasko T, Bhagwat J, Zou K, Ohno-machado L. The use of receiver operating characteristic curves. Journal of Biomedical Informatics. 2005; 38(5):404-15. http://dx.doi.org/10.1016/j.jbi.2005.02.008. PMid:16198999.

Mallat SG. A theory for multiresolution signal decomposition: the wavelet representation. IEEE Transactions on Pattern Analysis and Machine Intelligence. 1989; 11(7):674-93. http://dx.doi.org/10.1109/34.192463.

Mirzaei A, Ayatollahi A, Vavadi H. Statistical analysis of epileptic activities based on histogram and wavelet-spectral entropy. Biomedical Science and Engineering. 2011; 4(03):207-13. http://dx.doi.org/10.4236/jbise.2011.43029.

Misiti M, Misiti Y, Oppenheim G, Poggi J-M. Wavelet toolbox reference. Natick: The Math Works; 2013.

Montanari L, Basu B, Spagnoli A, Broderick BM. A padding method to reduce edge effects for enhanced damage identification using wavelet analysis. Mechanical Systems and Signal Processing. 2015; 52-53:264-77. http://dx.doi.org/10.1016/j.ymssp.2014.06.014.

Noachtar S, Binnie C, Ebersole J, Mauguière F, Sakamoto A, Westmoreland B. A glossary of terms most commonly used by clinical electroencephalographers and proposal for the report form the EEG Findings. Munich: Elsevier; 1999.

Nunes TM, Coelho AL, Lima CAM, Papa JP, Albuquerque VHC. EEG signal classification for epilepsy diagnosis via optimum path forest: a systematic assessment. Neurocomputing. 2014; 136:103-23. http://dx.doi.org/10.1016/j.neucom.2014.01.020.

Ocak H. Automatic detection of epileptic seizures in EEG using discrete wavelet transform and approximate entropy. Expert Systems with Applications. 2009; 36(2):2027-36. http://dx.doi.org/10.1016/j.eswa.2007.12.065.

Pacola ER, Quandt VI, Schneider FK, Sovierzoski MA. The wavelet transform border effect in EEG spike signals. In: World Congress on Medical Physics and Biomedical Engineering; 2012 May 26-31; Beijing, China. Heidelberg: Springer; 2012. p. 593-6.

Pincus SM. Approximate entropy as a measure of system complexity. Proceedings of the National Academy of Sciences of the United States of America. 1990; 88(6):2297-301. http://dx.doi.org/10.1073/pnas.88.6.2297. PMid:11607165.

Quandt VI, Pacola ER, Pichorim SF, Gamba HR, Sovierzoski MA. Pulmonary crackle characterization: approaches in the use of discrete wavelet transform regarding border effect, mother-wavelet selection, and subband reduction. Research on Biomedical Engineering. 2015; 31(2):148-59. http://dx.doi.org/10.1590/2446-4740.0639.

Sadati N, Mohseni H, Maghsoudi A. Epileptic seizure detection using neural fuzzy networks. In: International Conference on Fuzzy Systems; 2006 July 16-21; Vancouver, Canada. New York: IEEE; 2006. p. 596-600.

Shuren Q, Zhong J. Extraction of feature information in EEG signal by virtual EEG instrument with the functions of time-Frequency analysis. In: Proceedings of 6th International Image and Signal Processing and Analysis; 2009 Sept 16-18; Salzburg. New York: IEEE; 2009. p. 7-11.

Su H, Liu Q, Li J. Boundary effects reduction in wavelet transform for time-frequency analysis. WSEAS Transactions on Signal Processing. 2012; 8:169-79.

Ubeyli ED. Combined neural network model employing wavelet coefficients for EEG signals classification. Digital Signal Processing. 2009; 19(2):297-308. http://dx.doi.org/10.1016/j.dsp.2008.07.004.

Vavadi H, Ayatollahi A, Mirzaei A. A wavelet-approximate entropy method for epileptic activity detection from EEG and its sub-Bands. Biomedical Science and Engineering. 2010; 3(12):1182-9. http://dx.doi.org/10.4236/jbise.2010.312154.

Veneri G, Federighi P, Rosini F, Federico A, Rufa A. Spike removal through multiscale wavelet and entropy analysis of ocular motor noise: a case study in patients with cerebellar disease. Journal of Neuroscience Methods. 2011; 196(2):318-26. http://dx.doi.org/10.1016/j.jneumeth.2011.01.006. PMid:21262262.

Wang C, Zou J, Zhang J, Zhang Z, Zhang C. Classifying detection of epileptic EEG based on approximate entropy in wavelet domain. In: 2nd International Conference on Biomedical Engineering and Informatics; 2009 October 17-19; Tianjin. New York: IEEE; 2009. p. 1-5.

World Health Organization. Fact sheet n° 999: epilepsy [Internet]. Geneva: WHO; 2015 [cited 2015 July 24]. Available from: http://www.who.int/mediacentre/factsheets/fs999/en/

Xu B, Song A. Pattern recognition of motor imagery EEG using Wavelet transform. Journal of Biomedical Science and Engineering Research Publishing. 2008; 1(01):64-7. http://dx.doi.org/10.4236/jbise.2008.11010.

Youden W. Index for rating diagnostic tests. Cancer. 1950; 3(1):32-5. http://dx.doi.org/10.1002/1097-0142(1950)3:1<32::AID-CNCR2820030106>3.0.CO;2-3. PMid:15405679.
5889fbff5d01231a018b48b0 rbejournal Articles
Links & Downloads

Res. Biomed. Eng.

Share this page
Page Sections