Abstract
The present paper proposes a smart framework for detection of epileptic seizures using the concepts of IoT technologies, cloud computing and machine learning. This framework processes the acquired scalp EEG signals by Fast Walsh Hadamard transform. Then, the transformed frequency-domain signals are examined using higher-order spectral analysis to extract amplitude and entropy-based statistical features. The extracted features have been selected by means of correlation-based feature selection algorithm to achieve more real-time classification with reduced complexity and delay. Finally, the samples containing selected features have been fed to ensemble machine learning techniques for classification into several classes of EEG states, viz. normal, interictal and ictal. The employed techniques include Dagging, Bagging, Stacking, MultiBoost AB and AdaBoost M1 algorithms in integration with C4.5 decision tree algorithm as the base classifier. The results of the ensemble techniques are also compared with standalone C4.5 decision tree and SVM algorithms. The performance analysis through simulation results reveals that the ensemble of AdaBoost M1 and C4.5 decision tree algorithms with higher-order spectral features is an adequate technique for automated detection of epileptic seizures in real-time. This technique achieves 100% classification accuracy, sensitivity and specificity values with optimally small classification time.
References
Abdulhay E, Elamaran V, Chandrasekar M, Balaji V, Narasimhan K (2017) Automated diagnosis of epilepsy from EEG signals using ensemble learning approach. Pattern Recognit Lett. https://doi.org/10.1016/j.patrec.2017.05.021
Acharya UR, Sree SV, Swapna G, Martis RJ, Suri JS (2013) Automated EEG analysis of epilepsy: a review. Knowl Based Syst 45:147–165
Akosa J (2017) Predictive accuracy: a misleading performance measure for highly imbalanced data. In: Proceedings of the SAS Global Forum, pp 1–12
Aksenova S (2004) Machine learning with weka: Weka explorer tutorial. California State University, Scholl of Engineering and Computer Science-Department of Computer Science, Sacramento
Andrzejak RG, Lehnertz K, Mormann F, Rieke C, David P, Elger CE (2001) 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 64(6):061907
Ataei G, Abedi R, Mohammadi Y, Fatouraee N (2020) Analysing the effect of wearable lift-assist vest in squat lifting task using back muscle EMG data and musculoskeletal model. Phys Eng Sci Med. https://doi.org/10.1007/s13246-020-00872-5
Baig MM, GholamHosseini H, Connolly MJ (2015) Mobile healthcare applications: system design review, critical issues and challenges. Australas Phys Eng Sci Med 38(1):23–38
Baratloo A, Hosseini M, Negida A, El Ashal G (2015) Part 1: simple definition and calculation of accuracy, sensitivity and specificity. Emergency 3(2):48–49
Behnam M, Pourghassem H (2017) Seizure-specific wavelet (seizlet) design for epileptic seizure detection using correntropy ellipse features based on seizure modulus maximas patterns. J Neurosci Methods 276:84–107
Benbouzid D, Busa-Fekete R, Casagrande N, Collin FD, Kégl B (2012) MultiBoost: a multi-purpose boosting package. J Mach Learn Res 13(March):549–553
Breiman L (1996a) Bagging predictors. Mach Learn 24(2):123–140
Breiman L (1996) Stacked regressions. Mach Learn 24(1):49–64
Bühlmann P, Yu B et al (2002) Analyzing bagging. Ann Stat 30(4):927–961
Chua KC, Chandran V, Acharya UR, Lim CM (2010) Application of higher order statistics/spectra in biomedical signals—a review. Med Eng Phys 32(7):679–689
Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20(3):273–297
Dietterich TG (2000) Ensemble methods in machine learning. In: International workshop on multiple classifier systems. Springer, pp 1–15
Elshazly HI, Elkorany AM, Hassanien AE, Azar AT (2013) Ensemble classifiers for biomedical data: performance evaluation. In: 2013 8th international conference on computer engineering and systems (ICCES). IEEE, pp 184–189
Ferreira AJ, Figueiredo MA (2012) Boosting algorithms: a review of methods, theory, and applications. In: Ensemble machine learning, Springer, New York, pp 35–85
Fino BJ, Algazi VR (1976) Unified matrix treatment of the fast Walsh–Hadamard transform. IEEE Trans Comput 11:1142–1146
Freund Y, Schapire RE et al (1996) Experiments with a new boosting algorithm. In: ICML, Citeseer, vol 6, pp 148–156
Gajic D, Djurovic Z, Di Gennaro S, Gustafsson F (2014) Classification of EEG signals for detection of epileptic seizures based on wavelets and statistical pattern recognition. Biomed Eng Appl Basis Commun 26(02):1450021
Gokgoz E, Subasi A (2015) Comparison of decision tree algorithms for EMG signal classification using DWT. Biomed Signal Process Control 18:138–144
Habte TT, Saleh H, Mohammad B, Ismail M (2019) IoT for healthcare. In: Ultra low power ECG processing system for IoT devices. Springer, Cham, pp 7–12
Holmes G, Donkin A, Witten IH (1994) Weka: a machine learning workbench. In: Proceedings of ANZIIS’94—Australian New Zealand Intelligent information systems conference. IEEE, pp 357–361
IEC (2019) What is epilepsy. Indian Epilepsy Centre, New Delhi. http://www.indianepilepsycentre.com/what-is-epilepsy.html. Accessed 23 Nov 2019
Islam SMR, Kwak D, Kabir MH, Hossain M, Kwak K (2015) The Internet of Things for health care: a comprehensive survey. IEEE Access 3:678–708. https://doi.org/10.1109/ACCESS.2015.2437951
Jelinek H, Abawajy J, Kelarev A, Chowdhury M, Stranieri A (2014) Decision trees and multi-level ensemble classifiers for neurological diagnostics. Aust J Med Sci 1(1):1–12
Jović A, Brkić K, Bogunović N (2012) Decision tree ensembles in biomedical time-series classification. In: Joint DAGM (German Association for Pattern Recognition) and OAGM symposium. Springer, pp 408–417
Korting TS (2006) C4.5 algorithm and multivariate decision trees. Image Processing Division, National Institute for Space Research-INPE, Sao Jose dos Campos
Kotsianti S, Kanellopoulos D (2007) Combining bagging, boosting and dagging for classification problems. In: International conference on knowledge-based and intelligent information and engineering systems. Springer, pp 493–500
Kovac S, Vakharia VN, Scott C, Diehl B (2017) Invasive epilepsy surgery evaluation. Seizure 44(25th Anniversary Issue):125–136. https://doi.org/10.1016/j.seizure.2016.10.016
Kowshalya AM, Madhumathi R, Gopika N (2019) Correlation based feature selection algorithms for varying datasets of different dimensionality. Wirel Pers Commun 108(3):1977–1993
Kumar A, Komaragiri R, Kumar M (2018) Design of wavelet transform based electrocardiogram monitoring system. ISA Trans 80:381–398
Kumar A, Komaragiri R, Kumar M (2018) Heart rate monitoring and therapeutic devices: a wavelet transform based approach for the modeling and classification of congestive heart failure. ISA Trans 79:239–250
Kumar A, Komaragiri R, Kumar M (2019) Design of efficient fractional operator for ECG signal detection in implantable cardiac pacemaker systems. Int J Circuit Theory Appl 47(9):1459–1476
Kumar A, Komaragiri R, Kumar M (2019) Time–frequency localization using three-tap biorthogonal wavelet filter bank for electrocardiogram compressions. Biomed Eng Lett 9(3):407–411
Kumar A, Ranganatham R, Komaragiri R, Kumar M (2019) Efficient QRS complex detection algorithm based on fast Fourier transform. Biomed Eng Lett 9(1):145–151
Liu Q, Zhao X, Hou Z, Liu H (2017) Epileptic seizure detection based on the kernel extreme learning machine. Technol Health Care 25(S1):399–409
Liu X, Jiang A, Xu N (2017) Automated epileptic seizure detection in EEGs using increment entropy. In: 2017 IEEE 30th Canadian conference on electrical and computer engineering (CCECE), pp 1–4. https://doi.org/10.1109/CCECE.2017.7946705
Malasinghe LP, Ramzan N, Dahal K (2019) Remote patient monitoring: a comprehensive study. J Ambient Intell Humaniz Comput 10(1):57–76. https://doi.org/10.1007/s12652-017-0598-x
Mora H, Gil D, Terol RM, Azorín J, Szymanski J (2017) An IoT-based computational framework for healthcare monitoring in mobile environments. Sensors 17(10):2302
Nikias CL, Mendel JM (1993) Signal processing with higher-order spectra. IEEE Signal Process Mag 10(3):10–37
NINDS (2019) Epilepsy. National Institute of Neurological Disorders and Stroke. https://www.ninds.nih.gov/Current-Research/Focus-Research/Focus-Epilepsy. Accessed 20 Nov 2019
Patidar S, Panigrahi T (2017) Detection of epileptic seizure using Kraskov entropy applied on tunable-Q wavelet transform of EEG signals. Biomed Signal Process Control 34:74–80
Petropulu A (1999) Higher-order spectral analysis. In: Digital signal processing handbook. Chapman and Hall/CRCnetBASE, Boca Raton, pp 1599–1613
Powers DM (2011) Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation. J Mach Learn Technol 2(1):37–63
Press WH, Teukolsky SA, Vetterling WT, Flannery BP (2007) Section 16.5. support vector machines. Numerical recipes: the art of scientific computing. Cambridge University Press, New York
Samiee K, Kovacs P, Gabbouj M (2015) Epileptic seizure classification of EEG time-series using rational discrete short-time Fourier transform. IEEE Trans Biomed Eng 62(2):541–552
Sareen S, Sood SK, Gupta SK (2016) An automatic prediction of epileptic seizures using cloud computing and wireless sensor networks. J Med Syst 40(11):1–18. https://doi.org/10.1007/s10916-016-0579-1
Sareen S, Sood SK, Gupta SK (2016) A cloud-based seizure alert system for epileptic patients that uses higher-order statistics. Comput Sci Eng 18(5):56–67. https://doi.org/10.1109/MCSE.2016.82
Satapathy SK, Jagadev AK, Dehuri S (2017) Weighted majority voting based ensemble of classifiers using different machine learning techniques for classification of EEG signal to detect epileptic seizure. Informatica 41:99–110
Schapire RE (2013) Explaining AdaBoost. In: Empirical inference. Springer, Berlin, pp 37–52
Shawe-Taylor J, Cristianini N (2000) Support vector machines, vol 2. Cambridge University Press, Cambridge
Shoeb A, Guttag J (2010) Application of machine learning to epileptic seizure detection. In: Proceedings of the 27th international conference on machine learning, ICML’10. Omnipress, Madison, pp 975–982
Singh K, Agrawal S (2011) Performance evaluation of five machine learning algorithms and three feature selection algorithms for IP traffic classification. IJCA Spec Issue Evol Netw Comput Commun 1:25–32
Singh K, Malhotra J (2019) IoT and cloud computing based automatic epileptic seizure detection using HOS features based Random Forest classification. J Ambient Intell Humaniz Comput. https://doi.org/10.1007/s12652-019-01613-7
Sood SK, Mahajan I (2018) A Fog assisted cyber-physical framework for identifying and preventing coronary heart disease. Wirel Pers Commun 101(1):143–165
Thirunavukkarasu U, Umapathy S, Janardhanan K, Thirunavukkarasu R (2020) A computer aided diagnostic method for the evaluation of type II diabetes mellitus in facial thermograms. Phys Eng Sci Med 43:1–18
Ting KM (2017) Confusion matrix. In: Encyclopedia of machine learning and data mining. Springer, New York, p 260
Ting KM, Witten IH (1997) Stacking bagged and dagged models. In: Proceedings of the fourteenth international conference on machine learning, ICML ’97. Morgan Kaufmann Publishers, Inc., San Francisco, pp 367–375
Tuncer T, Dogan S, Akbal E (2019) A novel local senary pattern based epilepsy diagnosis system using EEG signals. Australas Phys Eng Sci Med 42(4):939–948
Upadhyay R, Kankar P, Padhy P, Gupta V (2012) Classification of drowsy and controlled EEG signals. In: 2012 Nirma University international conference on engineering (NUiCONE). IEEE, pp 1–4
Upadhyay R, Jharia S, Padhy PK, Kankar PK (2015) Application of wavelet fractal features for the automated detection of epileptic seizure using electroencephalogram signals. Int J Biomed Eng Technol 19(4):355–372
Upadhyay R, Manglick A, Reddy D, Padhy P, Kankar P (2015) Channel optimization and nonlinear feature extraction for electroencephalogram signals classification. Comput Electr Eng 45:222–234
Upadhyay R, Padhy P, Kankar P (2016) Application of S-transform for automated detection of vigilance level using EEG signals. J Biol Syst 24(01):1–27
Upadhyay R, Padhy P, Kankar P (2016) A comparative study of feature ranking techniques for epileptic seizure detection using wavelet transform. Comput Electr Eng 53:163–176
Vakharia V, Gupta V, Kankar P (2015) A multiscale permutation entropy based approach to select wavelet for fault diagnosis of ball bearings. J Vib Control 21(16):3123–3131
Vuk M, Curk T (2006) ROC curve, lift chart and calibration plot. Metodol zv 3(1):89
Wang G, Deng Z, Choi KS (2017) Detection of epilepsy with electroencephalogram using rule-based classifiers. Neurocomputing 228:283–290
Wang L, Xue W, Li Y, Luo M, Huang J, Cui W, Huang C (2017) Automatic epileptic seizure detection in EEG signals using multi-domain feature extraction and nonlinear analysis. Entropy 19(6):222
Webb GI (2000) Multiboosting: a technique for combining boosting and wagging. Mach Learn 40(2):159–196
WHO (2019) Epilepsy. World Health Organization. https://www.who.int/mentalhealth/. Accessed 22 Nov 2019
Winston P (1992) Learning by building identification trees. In: Artificial intelligence. Addison-Wesley Publishing Company, Boston, pp 423–442
Wolpert DH (1992) Stacked generalization. Neural Netw 5(2):241–259
Yong B, Xu Z, Wang X, Cheng L, Li X, Wu X, Zhou Q (2018) IoT-based intelligent fitness system. J Parallel Distrib Comput 118:14–21. https://doi.org/10.1016/j.jpdc.2017.05.006
Yuvaraj R, Acharya UR, Hagiwara Y (2018) A novel Parkinson’s disease diagnosis index using higher-order spectra features in EEG signals. Neural Comput Appl 30(4):1225–1235
Zhang C, Ma Y (2012) Ensemble machine learning: methods and applications. Springer, New York
Zhou M, Tian C, Cao R, Wang B, Niu Y, Hu T, Guo H, Xiang J (2018) Epileptic seizure detection based on EEG signals and CNN. Front Neuroinform 12:95
Zhou ZH (2009) Ensemble learning. Encycl Biom 1:270–273
Funding
The authors of this manuscript have not received any financial support to carry out present research.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors of this manuscript declare that they have no conflict of interest with any person or organization for carrying out this research work.
Ethical approval
This article contains studies performed on a publicly available EEG dataset, which was developed at University of Bonn, Germany. There is no direct involvement of human participants and/or animals to carry out this research work.
Informed consent
This manuscript uses a publicly available EEG dataset, which was developed at the Department of Epileptology in the University of Bonn, Germany. The authors of this manuscript have cited the article corresponding to this dataset as per the recommendations of its developers. The developers of this dataset had also acknowledged the support of the Deutsche Forschungsgemeinschaft (a German Research Funding Organization). The appropriate informed consent has already taken by the developers of this dataset from the concerned organization before making it online.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Singh, K., Malhotra, J. Cloud based ensemble machine learning approach for smart detection of epileptic seizures using higher order spectral analysis. Phys Eng Sci Med 44, 313–324 (2021). https://doi.org/10.1007/s13246-021-00970-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13246-021-00970-y