×

Application of S-transform for automated detection of vigilance level using EEG signals. (English) Zbl 1343.92268

Summary: This paper presents an S-transform-based electroencephalogram channel optimization and feature extraction methodology for monitoring mental vigilance level of humans. Vigilance level detection methodology consists of four steps. In the first stage, two types of electroencephalogram signals (alert and drowsy) are acquired from 30 healthy subjects and decomposed into sub-bands using the S-transform. In the second stage, permutation entropy of the S-transform coefficients is calculated and electroencephalogram channel optimization is performed. S-transform-based statistical features are computed from the optimized electroencephalogram channels, in the third stage. In the fourth stage, artificial intelligence techniques such as least square-support vector machine, artificial neural network and naive Bayes classifier are used for the classification of electroencephalogram signals using extracted features. The performance of the feature extraction methodology is tested on the electroencephalogram data of 30 healthy subjects. Experimental results ensured the effectiveness of proposed methodology for the estimation of mental vigilance level by using electroencephalogram signals. It is observed that the artificial neural network classifier is a good candidate for pre-emptive automatic vigilance level detection system for brain-computer interface applications.

MSC:

92C55 Biomedical imaging and signal processing

Software:

LS-SVMlab; ANFIS
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] 1. Brodsky B, Darkhovsky B, Nonparametric Methods in Change Point Problems, Kluwer Academic Publisher, Dordrecht, 1993. genRefLink(16, ’S0218339016500017BIB001’, ’10.1007 · Zbl 1274.62512
[2] 2. Keirn ZA, Aunon JI, A new mode of communication between man and his surroundings, IEEE Trans Biomed Eng37(12) :1209-1214, 1990. genRefLink(16, ’S0218339016500017BIB002’, ’10.1109
[3] 3. Babiloni F, Cincotti F, Lazzarini L, Millan J, Mourino J, Varsta M, Heikkonen J, Bianchi J, Marciani MG, Linear classification of low-resolution EEG patterns produced by imagined hand movements, IEEE Trans Rehab Eng8(2) :184-186, 2000. genRefLink(16, ’S0218339016500017BIB003’, ’10.1109
[4] 4. Wolpaw RJ, Birbaumer N, McFarland JD, Pfurtscheller G, Vaughaun MT, Brain-computer interfaces for communication and control, Clin Neurophysiol113(6) :767-791, 2002. genRefLink(16, ’S0218339016500017BIB004’, ’10.1016
[5] 5. Graimann B, Huggins JE, Schlogl A, Levine SP, Pfurtscheller G, Detection of movement-related desynchronization patterns in ongoing single-channel electrocardiogram, IEEE Trans Neural Syst Rehab Eng11(3) :276-281, 2003. genRefLink(16, ’S0218339016500017BIB005’, ’10.1109
[6] 6. Devinsky O, Canevini MP, Sato S, Bromfield EB, Kufta CV, Theodore WH, Quantitative electrocorticography in patients undergoing temporal lobectomy, J Epilepsy5(3) :178-185, 1992. genRefLink(16, ’S0218339016500017BIB006’, ’10.1016
[7] 7. Friston KJ, Holmes AP, Price CJ, Büchel C, Worsley KJ, Multisubject fMRI studies and conjunction analyses, Neuroimage10(4) :385-396, 1999. genRefLink(16, ’S0218339016500017BIB007’, ’10.1006
[8] 8. Kauhanen L, Nykopp T, Lehtonen J, Jylanki P, Heikkonen J, Rantanen P, Alaranta P, Sams M, EEG and MEG brain-computer interface for tetraplegic patients, IEEE Trans Neural Syst Rehab Eng14(2) :190-193, 2006. genRefLink(16, ’S0218339016500017BIB008’, ’10.1109
[9] 9. Gao X, Dignfeng X, Cheng M, Gao S, A BCI-based environmental controller for the motion-disabled, IEEE Trans Neural Syst Rehab Eng11(2) :137-140, 2003. genRefLink(16, ’S0218339016500017BIB009’, ’10.1109
[10] 10. Inoue S, Akiyama Y, Izumi Y, Nishijima S, The development of BCI using alpha waves for controlling the robot arm, IEICE Trans Commun91(7) :2125-2132, 2008. genRefLink(16, ’S0218339016500017BIB010’, ’10.1093
[11] 11. Iturrate , Antelis JM, Kubler A, Minguez J, A non-invasive brain actuated wheelchair based on a P300 neurophysiological protocol and automated navigation, IEEE Trans Robotics25(3) :614-627, 2009. genRefLink(16, ’S0218339016500017BIB011’, ’10.1109
[12] 12. Gupta A, Agrawal RK, Kaur B, Performance enhancement of mental task classification using EEG signal: A study of multivariate feature selection methods, Soft Comput, DOI: 10.1007/s00500-014-1443-1 , 2014. genRefLink(128, ’S0218339016500017BIB012’, ’000361730200007’);
[13] 13. Ravi KVR, Palaniappan R, Neural network classification of late gamma band electroencephalogram features, Soft Comput10(2) :163-169, 2005. genRefLink(16, ’S0218339016500017BIB013’, ’10.1007
[14] 14. Yang J, Singh H, Hines EL, Schlaghecken F, Iliescu DD, Leeson MS, Stocks NG, Channel selection and classification of electroencephalogram signals: An artificial neural network and genetic algorithm-based approach, Artif Intell Med55 :117-126, 2012. genRefLink(16, ’S0218339016500017BIB014’, ’10.1016
[15] 15. Blanco EF, Rivero D, Gestal M, Dorado J, Classification of signals by means of genetic programming, Soft Comput17(10) :1929-1937, 2013. genRefLink(16, ’S0218339016500017BIB015’, ’10.1007
[16] 16. Siuly S, Li Y, Wen P, Modified CC-LR algorithm with three diverse feature sets for motor imagery tasks classification in EEG based brain computer interface, Computer Methods Prog Biomed113(3) :767-780, 2014. genRefLink(16, ’S0218339016500017BIB016’, ’10.1016
[17] 17. Kaya Y, Uyar M, Tekin R, Yildirim S, 1D binary pattern based feature extraction for classification of epileptic EEG signals, Appl Math Comput243 :209-219, 2014. genRefLink(16, ’S0218339016500017BIB017’, ’10.1016
[18] 18. Subasi A, Automatic recognition of alertness level from EEG by using neural network and wavelet coefficients, Expert Syst Appl28 :701-711, 2005. genRefLink(16, ’S0218339016500017BIB018’, ’10.1016
[19] 19. Kousarrizi MRN, Ghanbari AA, Gharaviri A, Teshnehlab M, Classification of alcoholics and non-alcoholics via EEG using SVM and neural networks, Bioinformatics Biomed Eng 1-4, 2009.
[20] 20. Upadhyay R, Kankar PK, Padhy PK, Gupta VK, Classification of drowsy and controlled EEG signals, IEEE Nirma University International Conference on Engineering (NUiCONE), pp. 1-4, 2012.
[21] 21. Puthankattil SD, Joseph PK, Classification of EEG signals in normal and depression conditions by ANN using RWE and signal entropy, J Mech Med Biol14(4) :1240019-13, 2012.
[22] 22. Yildiz A, Akin M, Poyraz M, Kirbas G, Application of adaptive neuro-fuzzy inference system for vigilance level estimation by using wavelet-entropy feature extraction, Expert Syst Appl36 :7390-7399, 2009. genRefLink(16, ’S0218339016500017BIB022’, ’10.1016
[23] 23. Huang RS, Kuo CJ, Tsai LL, Chen OTC, EEG pattern recognition-arousal states detection and classification, Vol. 2, Proc IEEE Intern Conf Neural Networks, pp. 641-646, 1996.
[24] 24. Makeig S, Jung TP, Sejnowski TJ, Using feedforward neural networks to monitor alertness from changes in EEG correlation and coherence, in Advances in Neural Information Processing Systems, MIT Press, Cambridge, MA, pp. 931-937, 1996.
[25] 25. Escourrou P, Luriau S, Rehel M, Nedelcoux H, Lanoe JL, Needs and costs of sleep monitoring, Stud Health Technol Inform78 :69-85, 2000.
[26] 26. Wilson BJ, Bracewell TD, Alertness monitor using neural networks for EEG analysis, Proc Neural Netw Signal Process2 :814-820, 2000.
[27] 27. Radivojevic VV, Chen CAN, Popovic D, Automatic recognition of alertness and drowsiness from EEG by an artificial neural network, Med Eng Phys24 :349-360, 2002. genRefLink(16, ’S0218339016500017BIB027’, ’10.1016
[28] 28. Jung TP, Makeig S, Estimating level of alertness from EEG, Vol. 1, Proc 16th Annual International Conf IEEE Engineering in Medicine and Biology Society, pp. 103-104, 1994.
[29] 29. Jung TP, Makeig S, Stensmo M, Sejnowski TJ, Estimating alertness from the EEG power spectrum, IEEE Trans Biomed Eng44 :60-69, 1997. genRefLink(16, ’S0218339016500017BIB029’, ’10.1109
[30] 30. Faust O, Yu W, Kadri NA, Computer-based identification of normal and alcoholic EEG signals using wavelet packets and energy measures, J Mech Med Biol13(3) :1350033, 2013. [Abstract] genRefLink(128, ’S0218339016500017BIB030’, ’000319123800012’);
[31] 31. Inouye T, Ukai S, Shinosaki K, Iyama A, Matsumoto Y, Toi S, Changes in the FD of alpha envelope from wakefulness to drowsiness in the human electroencephalogram, Neurosci Lett174(1) :105-108, 1994. genRefLink(16, ’S0218339016500017BIB031’, ’10.1016
[32] 32. Cic M, Soda J, Bonkovic M, Automatic classification of infant sleep based on instantaneous frequencies in a single-channel EEG signal, Comput Biol Med43 :2110-2117, 2013. genRefLink(16, ’S0218339016500017BIB032’, ’10.1016
[33] 33. Begleiter H, Neurodynamics Laboratory, State University of New York Health Center, Brooklyn, Available at https://archive.ics.uci.edu/ml/datasets/EEG+Database.
[34] 34. Lanez E, Furio MC, Azorin JM, Huizzi JA, Fernandez E, Brain-robot interface for controlling a remote robot arm, III International Work-Conf Interplay Between Natural and Artificial Computation IWINAC, Lecture Notes on Computer Sciences, Vol. 5602, Springer Verlag, Berlin, pp. 353-361, 2009.
[35] 35. Lanez E, Azorin JM, Ubeda A, Ferrandez JM, Fernandez E, Mental tasks-based brain-robot interface, Rob Auton Syst58 :1238-1245, 2010. genRefLink(16, ’S0218339016500017BIB035’, ’10.1016
[36] 36. Sukens JAK, Vandewalle J, Least squares support vector machine classifiers, Neural Process Lett.9 :293-300, 1999. genRefLink(16, ’S0218339016500017BIB036’, ’10.1023
[37] 37. Souza SXD, Suykens JAK, Vandewalle J, Bolle D, Coupled simulated annealing, IEEE Trans Syst Man Cybern B40 :320-335, 2010. genRefLink(16, ’S0218339016500017BIB037’, ’10.1109
[38] 38. Brabanter KD, Karsmakers P, Ojeda F, Alzate C, Brabanter JD, Pelckmans K, Moor BD, Vandewalle J, Suykens JAK, LS-SVMlab Toolbox User’s Guide version 1.8, Department of Electrical Engineering, ESAT-SCD-SISTA, Belgium, Available at http://www.esat.kuleuven.be/sista/lssvmlab/.
[39] 39. Mardi Z, Ashtiani SN, Ashtiani M, Mikaili M, EEG-based drowsiness detection for safe driving using chaotic features and statistical tests, J Med Signals Sensors1 :130-137, 2011.
[40] 40. Chandrasekaran M, Muralidhar M, Krishna CM, Dixit US, Application of soft computing techniques in machining performance and optimization, a literature review, Int J Adv Manuf Technol46 :445-464, 2010. genRefLink(16, ’S0218339016500017BIB040’, ’10.1007
[41] 41. Han J, Kamber M, Pei J, Data Mining: Concepts and Techniques, 2nd edn., Morgan Kaufmann, 2005. · Zbl 1230.68018
[42] 42. Acharya UR, Filippo M, Sree SV, Chattopadhyay S, Kwan-Hoong N, Suri JS, Automated diagnosis of epileptic EEG using entropies, Biomed Signal Process Control7 :401-408, 2012. genRefLink(16, ’S0218339016500017BIB042’, ’10.1016
[43] 43. Hand D, Yu K, Idiot’s Bayes – Not so stupid after all? Int Stat Rev69 :385-398, 2001. genRefLink(16, ’S0218339016500017BIB043’, ’10.1111
[44] 44. Stockwell RG, Mansinha L, Lowe RP, Localization of the complex spectrum: S transform, IEEE Trans Signal Process44 :998-1001, 1996. genRefLink(16, ’S0218339016500017BIB044’, ’10.1109
[45] 45. Daubechies , The wavelet transform, time-frequency localization and signal analysis, IEEE Trans Inform Theory36(5) :961-1005, 1990. genRefLink(16, ’S0218339016500017BIB045’, ’10.1109 · Zbl 0738.94004
[46] 46. Poh K, Marziliano P, Analysis of neonatal EEG signals using stockwell transform, IEEE EMBS, Lyon, pp. 594-597, 2007.
[47] 47. Yang W, Little C, Court R, S-Transform and its contribution to wind turbine condition monitoring, Renew Energy62 :137-146, 2014. genRefLink(16, ’S0218339016500017BIB047’, ’10.1016
[48] 48. Bandt C, Pompe B, Permutation entropy: A natural complexity measure for time series, Phys Rev Lett88 :174102-4, 2002. genRefLink(16, ’S0218339016500017BIB048’, ’10.1103
[49] 49. Nicolaou N, Georgiou J, Detection of epileptic electroencephalogram based on permutation entropy and support vector machines, Expert Syst Appl39 :202-209, 2012. genRefLink(16, ’S0218339016500017BIB049’, ’10.1016
[50] 50. Cao Y, Tung WW, Gao JB, Protopopescu VA, Hively LM, Detecting dynamical changes in time series using the permutation entropy, Phys Rev70 :046217-7, 2004.
[51] 51. Bruzzo A, Gesierich B, Santi M, Tassinari CA, Birbaumer N, Rubboli G, Permutation entropy to detect vigilance change sand preictal states from scalp EEG in epileptic patients. A preliminary study, Neurol Sci29 :3-9, 2008. genRefLink(16, ’S0218339016500017BIB051’, ’10.1007
[52] 52. Reddy DK, Manglick A, Upadhyay R, Padhy PK, Feature extraction and classification of electroencephalogram signals for vigilance level detection, IEEE Int Conf Control Automation Robotics and Embedded System, pp. 1-4, 2013.
[53] 53. Bajaj V, Pachori RB, Classification of seizure and nonseizure EEG signals using empirical mode decomposition, IEEE Trans Inform Technol Biomed16(6) :1135-1141, 2012. genRefLink(16, ’S0218339016500017BIB053’, ’10.1109
[54] 54. Vyas A, Mishra G, Tiwari S, Upadhyay R, Padhy PK, Classification of two mental states using electroencephalogram signals, IEEE Conf Control Automation Robotics and Embedded System, pp. 1-4, 2013.
[55] 55. Pan J, Ren QS, Lu HT, Vigilance analysis based on fractal features of EEG signals. International Symp Computer Communication Control and Automation, Tainan, pp. 446-449, 2010.
[56] 56. Breiman L, Random forests, Mach Learning45(1) :5-32, 2001. genRefLink(16, ’S0218339016500017BIB056’, ’10.1023
[57] 57. Fraiwan L, Lweesy K, Khasawneh N, Wenz H, Dickhaus H, Automated sleep stage identification system based on timefrequency analysis of a single EEG channel and random forest classier, Computer Methods Prog Biomed108 :1019, 2012. genRefLink(16, ’S0218339016500017BIB057’, ’10.1016
[58] 58. Jang JSR, ANFIS: Adaptive-network-based fuzzy inference system, IEEE Trans Syst Man Cybern23(3) :665-685, 1993. genRefLink(16, ’S0218339016500017BIB058’, ’10.1109
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.