Discriminant feature level fusion based learning for automatic staging of EEG signals
- Author(s): Anil Hazarika 1 ; Arup Sarmah 2 ; Rupam Borah 3 ; Meenakshi Boro 1 ; Lachit Dutta 1 ; Pankaj Kalita 4 ; Balendra kumar dev Choudhury 2
-
-
View affiliations
-
Affiliations:
1:
Electronics and Communication Engineering, Tezpur University , Tezpur, Napaam, Assam , India ;
2: Department of Computer Science, Gauhati University , Ghy, Guwahati, Assam , India ;
3: Department of Chemistry, IIT Roorkee , Roorkee, Uttarakhand , India ;
4: Department of Biophysics, Pub Kamrup College , Kamrup, Assam , India
-
Affiliations:
1:
Electronics and Communication Engineering, Tezpur University , Tezpur, Napaam, Assam , India ;
- Source:
Volume 5, Issue 6,
December
2018,
p.
226 – 230
DOI: 10.1049/htl.2018.5024 , Online ISSN 2053-3713
- « Previous Article
- Table of contents
- Next Article »
Wide-scale information embedding is a prerequisite to enhance the performance as well as the reliability of decision-making algorithms for viable implementation. Feature fusion technology significantly helps to incorporate such information to provide promising algorithm performance. In this Letter, a fusion-based model with the aid of discriminant correlation analysis to classify electroencephalogram signals is proposed. Sets of multiple feature matrices are generated from signals in both time and wavelet domains for study-specific classes, which are further decomposed to derive a set of sub-multi-view features followed by optimisation to extract statistical features. Features are concatenated using feature fusion technique to derive low order discriminant features. Besides, the analysis of variance was also performed to validate the analysis. The statistically significant features are evaluated for the effective model performance. Experimental results manifest that the proposed feature fusion based algorithm is superior to many state-of-the-art methods and thus promote real-time implementation.
Inspec keywords: feature extraction; statistical analysis; image fusion; medical signal processing; matrix algebra; electroencephalography; learning (artificial intelligence); wavelet transforms
Other keywords: promising algorithm performance; statistical features; wavelet domains; automatic staging; multiple feature matrices; feature fusion based algorithm; viable implementation; effective model performance; wide-scale information embedding; electroencephalogram signals; EEG signals; feature fusion technology; real-time implementation; discriminant correlation analysis; fusion-based model; study-specific classes; decision-making algorithms; discriminant feature level fusion based learning; feature fusion technique; sub-multiview features; statistically significant features; low order discriminant features
Subjects: Computer vision and image processing techniques; Knowledge engineering techniques; Other topics in statistics
References
-
-
1)
-
24. Gajic, D., Zeljko, D., Jovan, G., et al: ‘Detection of epileptiform activity in EEG signals based on time-frequency and non-linear analysis’, Frontiers Comput. Neurosci., 2015, 9, p. 38 (doi: 10.3389/fncom.2015.00038).
-
-
2)
-
3. Hazarika, A., Barthakur, M., Dutta, L., et al: ‘Fusion of projected feature for classification of EMG patterns’. IEEE Conf. on Recent Advances and Innovations in Engineering, India, 2016.
-
-
3)
-
10. Sun, L., Ji, S., Ye, J.: ‘Canonical correlation analysis for multilabel classification: a least-squares formulation, extensions, and analysis’, IEEE Trans. Pattern Anal. Mach. Intell., 2011, 33, (1), pp. 194–200 (doi: 10.1109/TPAMI.2010.160).
-
-
4)
-
11. Dutta, L., Hazarika, A., Bhuyan, M.: ‘Comparison of direct interfacing and ADC based system for gas identification using E-nose’. IEEE Conf. on Inventive Computation Technologies, India, 2016.
-
-
5)
-
2. Hassan, A.R.: ‘Computer-aided obstructive sleep apnea detection using normal inverse Gaussian parameters and adaptive boosting’, Biomed. Signal Proc. Control, 2016, 29, pp. 22–30 (doi: 10.1016/j.bspc.2016.05.009).
-
-
6)
-
1. Shen, X., Sun, Q.: ‘A novel semi-supervised canonical correlation analysis and extensions for multi-view dimensionality reduction’, J. Vis. Commun. Image Represent., 2014, 25, pp. 1894–1904 (doi: 10.1016/j.jvcir.2014.09.004).
-
-
7)
-
28. Naik, G., Selvan, S., Nguyen, H.: ‘Single-channel EMG classification with ensemble-empirical-mode-decomposition-based ICA for diagnosing neuromuscular disorders’, IEEE Trans. Neural Syst. Rehabil. Eng., 2016, 24, pp. 734–743 (doi: 10.1109/TNSRE.2015.2454503).
-
-
8)
-
15. Chu, J.U., Moon, I., Lee, Y.J., et al: ‘A supervised feature-projection-based real-time EMG pattern recognition for multifunction myoelectric hand control’, IEEE/ASME Trans. Mechatronics, 2007, 12, pp. 282–290 (doi: 10.1109/TMECH.2007.897262).
-
-
9)
-
9. Hassan, A.R., Haque, Md.A.: ‘Computer-aided obstructive sleep apnea screening from single-lead electrocardiogram using statistical and spectral features and bootstrap aggregating’, Biocybern Biomed. Eng., 2016, 36, (1), pp. 256–266 (doi: 10.1016/j.bbe.2015.11.003).
-
-
10)
-
8. Liu, M., Zhang, D., Shen, D.: ‘Inherent structure based multi-view learning with multi-template feature representation for Alzheimer's disease diagnosis’, IEEE Trans. Biomed. Eng., 2016, 63, (7), pp. 1473–1482 (doi: 10.1109/TBME.2015.2496233).
-
-
11)
-
35. Wu, H.T., Ronen, T., Lo, Y.L.: ‘Assess sleep stage by modern signal processing techniques’, IEEE Trans. Biomed. Eng., 2015, 62, (4), pp. 1159–1168 (doi: 10.1109/TBME.2014.2375292).
-
-
12)
-
12. Hargrove, L.J., Li, G., Englehart, K.B., et al: ‘Principal components analysis preprocessing for improved classification accuracies in pattern-recognition-based myoelectric control’, IEEE Trans. Biomed. Eng., 2009, 56, pp. 1407–1414 (doi: 10.1109/TBME.2008.2008171).
-
-
13)
-
32. Hassan, A.R., Mohammed, I.H.B.: ‘A decision support system for automatic sleep staging from EEG signals using tunable Q-factor wavelet transform and spectral features’, J. Neurosci. Methods, 2016, 271, pp. 107–118 (doi: 10.1016/j.jneumeth.2016.07.012).
-
-
14)
-
32. Subasi, A.: ‘EEG signal classification using wavelet feature extraction and a mixture of expert model’, Expert Syst. Appl., 2007, 32, (4), pp. 1084–1093 (doi: 10.1016/j.eswa.2006.02.005).
-
-
15)
-
9. Hazarika, A., Barthakur, M., Dutta, L., et al: ‘Multi-view learning for classification of EMG template’. IEEE Conf. on Signal Processing and Communication, India, 2017.
-
-
16)
-
5. Andrzejak, R.G., Lehnertz, K., Rieke, C., Mormann, F., David, P., Elger, C.E.: ‘Indications of nonlinear deterministic and finite dimensional structures in time series of brain electrical activity: dependence on recording region and brain state’, Phys. Rev. E, 2001, 64, p. 061907 (doi: 10.1103/PhysRevE.64.061907).
-
-
17)
-
42. Barthakur, M., Hazarika, A., Bhuyan, M.: ‘A computer-assisted technique for nerve conduction study in early detection of peripheral neuropathy using ANN’, Int. J. Electron. Commun. Eng. Tech., 2013, 4, pp. 47–65.
-
-
18)
-
33. Soomro, M.H., Musavi, S.H.A., Pandey, B.: ‘Canonical correlation analysis and neural network (CCA-NN) based method to detect epileptic seizures from EEG signals’, Int. J. Bio-Sci. Bio-Tech., 2016, 8, pp. 11–20 (doi: 10.14257/ijbsbt.2016.8.4.02).
-
-
19)
-
27. Subasi, A., Gursoy, M.I.: ‘EEG signal classification using PCA, ICA, LDA and support vector machines’, Expert Syst. Appl., 2010, 37, pp. 8659–8666 (doi: 10.1016/j.eswa.2010.06.065).
-
-
20)
-
19. Zhang, J., Zhang, D.: ‘A novel ensemble construction method for multi-view data using random cross-view correlation between within-class examples’, Pattern Recognit., 2011, 44, pp. 1162–1171 (doi: 10.1016/j.patcog.2010.12.011).
-
-
21)
-
18. Hotelling, H.: ‘Relations between two sets of variates’, Biometrika, 1936, 28, pp. 321–377 (doi: 10.1093/biomet/28.3-4.321).
-
-
22)
-
3. Sun, B.Y., Zhang, X.M., Li, J., et al: ‘Feature fusion using locally linear embedding for classification’, IEEE Trans. Neural Netw., 2010, 21, (1), pp. 163–168 (doi: 10.1109/TNN.2009.2036363).
-
-
23)
-
26. Hassanpour, H., Mesbah, M., Boashash, B.: ‘Time-frequency feature extraction of newborn EEG seizure using SVD-based techniques’, EURASIP J. Appl. Signal Process., 2004, 2004, pp. 2544–2554.
-
-
24)
-
29. Hassan, A.R., Subasi, A.: ‘Automatic identification of epileptic seizures from EEG signals using linear programming boosting’, Comput. Methods Programs Biomed., 2016, 136, pp. 65–77 (doi: 10.1016/j.cmpb.2016.08.013).
-
-
25)
-
44. Hekim, M.: ‘The classification of EEG signals using discretization-based entropy and the adaptive neuro-fuzzy inference system’, Turk J. Elec. Eng. Comp. Sci., 2016, 24, pp. 285–297 (doi: 10.3906/elk-1306-164).
-
-
26)
-
20. Clercq, W.De, Vergult, A., Vanrumste, B., Paesschen, W.V., Huffel, S.V.: ‘Canonical correlation analysis applied to remove muscle artifacts from the electroencephalogram’, IEEE Trans. Biomed. Eng., 2006, 53, (12), pp. 2583–2587 (doi: 10.1109/TBME.2006.879459).
-
-
27)
-
41. Barthakur, M., Hazarika, A., Bhuyan, M.: ‘A novel technique of neuropathy detection and classification by using artificial neural network (ANN)’. Proc ACEEE Int. Conf. Advance Signal Process Communication, 2013, pp. 706–713.
-
-
28)
-
18. Peng, Y., Daoqiang, Z., Zhang, J.: ‘A new canonical correlation analysis algorithm with local discrimination’, Neural Process. Lett., 2010, 31, pp. 1–15 (doi: 10.1007/s11063-009-9123-3).
-
-
29)
-
34. Kiymik, M.K., Akin, M., Subasi, A.: ‘Automatic recognition of alertness level by using wavelet transform and artificial neural network’, J. Neurosci. Methods, 2004, 139, pp. 231–240 (doi: 10.1016/j.jneumeth.2004.04.027).
-
-
30)
-
20. Khushaba, R.N.: ‘Correlation analysis of electromyogram signals for multiuser myoelectric interfaces’, IEEE Trans. Neural Syst. Rehabil. Eng., 2014, 22, pp. 745–755 (doi: 10.1109/TNSRE.2014.2304470).
-
-
31)
-
5. Hazarika, A., Bhuyan, M.: ‘A twofold subspace learning-based feature fusion strategy for classification of EMG and EMG spectrogram images’. Biologically Rationalized Computing Techniques for Image Processing Applications, Cham, 2018, pp. 57–84.
-
-
32)
-
37. Doulah, A.S.U., Fattah, S.A., Zhu, W.P., et al: ‘Wavelet domain feature extraction scheme based on dominant motor unit action potential of EMG signal for neuromuscular disease classification’, IEEE Trans. Biomed. Circuits Syst., 2014, 8, pp. 155–164 (doi: 10.1109/TBCAS.2014.2309252).
-
-
33)
-
25. Alickovic, E., Subasi, A.: ‘Ensemble SVM method for automatic sleep stage classification’, IEEE Instrum. Meas., 2018, 67, pp. 1–8 (doi: 10.1109/TIM.2018.2799059).
-
-
34)
-
4. Yuan, Y.H., Sun, Q.S., Zhou, Q., et al: ‘A novel multiset integrated canonical correlation analysis framework and its application in feature fusion’, Pattern Recognit., 2011, 44, (5), pp. 1031–1040 (doi: 10.1016/j.patcog.2010.11.004).
-
-
35)
-
2. Hazarika, A., Barthakur, M., Dutta, L., et al: ‘Two-fold feature extraction technique for biomedical signals classification’. IEEE Conf. on Inventive Computation Technologies, India, 2016.
-
-
36)
-
39. Barthakur, M., Hazarika, A., Bhuyan, M.: ‘Rule based fuzzy approach for peripheral motor neuropathy (PMN) diagnosis based on NCS data’. Proc. IEEE int. Conf. Proc. Recent Advances and Innovations in Engineering, Jaipur, India, May 2014, pp. 1–9.
-
-
37)
-
38. Kim, T.K., Kittler, J., Cipolla, R.: ‘Discriminative learning and recognition of image set classes using canonical correlations’, IEEE Trans. Pattern Anal. Mach. Intell., 2007, 29, pp. 1005–1018 (doi: 10.1109/TPAMI.2007.1037).
-
-
38)
-
23. Orhan, U., Hekim, M., Ozer, M.: ‘EEG signals classification using the K-means clustering and a multilayer perceptron neural network model’, Expert Syst. Appl., 2011, 38, pp. 13475–13481 (doi: 10.1016/j.eswa.2011.04.149).
-
-
39)
-
22. Sargin, M.E., YÜcel, Y., Engin, E.: ‘Audiovisual synchronization and fusion using canonical correlation analysis’, IEEE Trans. Multimedia, 2007, 9, pp. 1396–1403 (doi: 10.1109/TMM.2007.906583).
-
-
40)
-
4. Sun, Q.S., Zeng, S.G., Liu, Y., et al: ‘A new method of feature fusion and its application in image recognition’, Pattern Recognit., 2005, 38, pp. 2437–2448 (doi: 10.1016/j.patcog.2004.12.013).
-
-
41)
-
6. Haghighat, M., Abdel-Mottaleb, M., Alhalabi, W.: ‘Discriminant correlation analysis: real-time feature level fusion for multimodal biometric recognition’, IEEE Trans. Inf. Forensics Sec., 2016, 9, pp. 1984–1996 (doi: 10.1109/TIFS.2016.2569061).
-
-
42)
-
40. Barthakur, M., Hazarika, A., Bhuyan, M.: ‘Classification of peripheral neuropathy by using ANN based nerve conduction study (NCS) protocol’, ACEEE Int. J. Commun., 2014, 5, p. 31.
-
-
43)
-
10. Xia, T., Tao, D., Mei, T., et al: ‘Multiview spectral embedding’, IEEE Trans. Syst. Man Cybern. B, Cybern., 2010, 40, pp. 1436–1446.
-
-
44)
-
13. Dutta, L., Hazarika, A., Bhuyan, M.: ‘Direct interfacing circuit based E-nose for gas classification and its uncertainty estimation’, IET Circuits Devices Syst., 2018, 12, (1), pp. 63–72 (doi: 10.1049/iet-cds.2017.0106).
-
-
45)
-
14. Dutta, L., Hazarika, A., Bhuyan, M.: ‘Microcontroller based E-nose for gas classification without using ADC’, Sens. Transducers, 2016, 202, pp. 38–45.
-
-
1)