Abstract
Electroencephalogram (EEG) signals, generated during the neuron firing, are an effective way of predicting such seizure and it is used widely in recent days for classifying and predicting seizure activity. But EEG signals generated during an epileptic seizure are highly nonstationary and dynamic in nature and contain very crucial information about the state of the brain. Due to this randomness, the accuracy of analysis of EEG data by conventional and visual methods is reduced drastically. This paper aims at enhancing epilepsy seizure detection using deep learning models with an FPGA implementation of the short-time Fourier transform block. Detection of seizure has been achieved in the following stages: (1) time–frequency analysis of EEG segments using STFT; (2) extraction of frequency bands and features of interest; and (3) seizure detection using convolutional neural network (CNN) and bidirectional long short-term memory (Bi-LSTM). For this work, the Bonn EEG dataset has been used. The maximum error of ~ 0.13% was encountered while the comparison of STFT output generated via proposed hardware architecture vs the output generated via simulation was done. The average classification accuracy of 93.9% and 97.2% was achieved by CNN and Bi-LSTM models, respectively, considering all frequency bands for epileptic and non-epileptic patients.
Similar content being viewed by others
Data Availability
The data for this paper are acquired from the University of Bonn, Germany [42]. This dataset consists of data of subjects who are healthy, interictal, and ictal, which are divided into five exclusive segments. These are denoted as A, B, C, D, and E. There are 100 text files in every segment. Each text file consists the data of 4096 pulse per sample. With the help of a 128-channel amplifier, the EEG signals were recorded. The sampling frequency used while recording was set to 173.61 Hz. The duration of each channel of each segment was restricted to 23.6 s. Segments A and B are of a healthy, an ictal-free, person. These two segments are different even though taken from a healthy person because the data of Segment A represents a healthy person with eyes open and that of B represents a healthy person with closed eyes, while the remaining three segments consist of seizure. The segment C and D are taken from an interictal person. Segment C represents an interictal patient, and data recorded from hippocampal formation. Similarly, segment D represents an interictal patient, but the data recorded from the epileptogenic zone. Lastly, segment E represents an ictal person, who contains prominent seizure activity.
References
U.R. Acharya, S.L. Oh, Y. Hagiwara, J.H. Tan, H. Adeli, Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals. Comput. Biol. Med. 100, 270–278 (2018)
H. Adeli, S. Ghosh-Dastidar, N. Dadmehr, A wavelet-chaos methodology for analysis of EEGs and EEG sub bands to detect seizure and epilepsy. IEEE Trans. Biomed. Eng. 54(2), 205–211 (2007)
B.J. Antony, M.D. Abràmoff, M.M. Harper, W. Jeong, E.H. Sohn, Y.H. Kwon, R. Kardon, M.K. Garvin, A combined machine-learning and graph-based framework for the segmentation of retinal surfaces in SD-OCT volumes. Biomed. Opt. Express 4, 2712–2728 (2013)
A. Akselrod Ballin, et al. A region based convolutional network for tumor detection and classification in breast mammography, in Deep Learning and Data Labeling for Medical Applications (Springer, Cham, 2016), pp. 197–205
R. Bose, S. Pratiher, S. Chatterjee, Detection of epileptic seizure employing a novel set of features extracted from multifractal spectrum of electroencephalogram signals. IET Signal Process. 13(2), 157–164 (2018)
D. Chandler, J. Bisasky, J.L.V.M. Stanislaus, T. Mohsenin, Real-time multi-channel seizure detection and analysis hardware, in IEEE Biomedical Circuits and Systems Conference (BioCAS), San Diego, CA, USA (2011), pp. 41–44. https://doi.org/10.1109/BioCAS.2011.6107722
Z. Chen, B. Zhang, V. Stojanovic, Y. Zhang, Z. Zhang, Event-based fuzzy control for T-S fuzzy networked systems with various data missing. Neurocomputing 417, 322–332 (2020)
L.L. Chen, J. Zhang, J.Z. Zou, C.J. Zhao, G.S. Wang, A framework on wavelet-based nonlinear features and extreme learning machine for epileptic seizure detection. Biomed. Signal Process Control 10, 1–10 (2014)
P. Cheng, S. He, V. Stojanovic, X. Luan, F. Liu, Fuzzy fault detection for Markov jump systems with partly accessible hidden information: an event-triggered approach. IEEE Trans. Cybern. (2021). https://doi.org/10.1109/TCYB.2021.3050209
F.A. Gers, J. Schmidhuber, F. Cummins, learning to forget: continual prediction with LSTM. Neural Comput. 12(10), 2451–2471 (2000)
I. Guler, E.D. Ubeyli, Multiclass support vector machines for EEG-signals classification. IEEE Trans. Inf. Technol. Biomed. 11(2), 117–126 (2009)
S. Hochreiter, J. Schmidhuber, Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
A.K. Jaiswal, H. Banka, Epileptic seizure detection in EEG signal with GModPCA and support vector machine. Bio-Med. Mater. Eng. 28, 141–157 (2017)
A.R. Johansen, J. Jin et al., Epileptiform spike detection via convolutional neural networks, in IEEE International Conference Acoustics Speech and Signal Processing (ICASSP) (2016), pp. 754–758
V. Joshi, R.B. Pachori, A. Vijesh, Classification of ictal and seizure-free EEG signals using fractional linear prediction. Biomed. Signal Process. Control 9, 1–5 (2014)
N. Kannathal, M.L. Choo, U.R. Acharya, P.K. Sadasivan, Entropies for detection of epilepsy in EEG. Comput. Methods Progr. Biomed. 80(3), 187–194 (2005)
Y. Kaya, M. Uyar, R. Tekin, S. Yıldırım, 1D-local binary pattern-based feature extraction for classification of epileptic EEG signals. Appl. Math. Comput. 243, 209–219 (2014)
P. Kwan, M.J. Brodie, Early identification of refractory epilepsy. N. Engl. J. Med. 342(5), 314–319 (2000)
Y. LeCun, Y. Bengio, G. Hinton, Deep learning. Nature 521(7553), 436 (2015)
A. Liu, J.S. Hahn, G.P. Heldt, R.W. Coen, Detection of neonatal seizures through computerized EEG analysis. Electroencephalogram Clin. Neurophysiol. 82, 30–37 (1992)
P.E. McSharry, L.A. Smith, L. Tarassenko, Comparison of predictability of epileptic seizures by a linear and a nonlinear method. IEEE Trans. Biomed. Eng. 50(5), 628–633 (2003)
P.E. McSharry, L.A. Smith, L. Tarassenko, Prediction of epileptic seizures: are nonlinear methods relevant? Nat. Med. 9(3), 241–242 (2003)
F. Mormann, R.G. Andrzejak, C.E. Elger, K. Lehnertz, Seizure prediction: the long and winding road. Brain 130(Pt 2), 314–333 (2007). https://doi.org/10.1093/brain/awl241
S. Mousavi, M. Niknazar, B. Vahdat, Epileptic seizure detection using AR model on EEG signals, in Cairo International Biomedical Engineering Conference (IEEE, 2008)
M. Mursalin, Y. Zhang, Y. Chen, N.V. Chawla, Automated epileptic seizure detection using improved correlation-based feature selection with random forest classifier. Neurocomputing 241, 204–214 (2017)
A.K. Ngugi, C. Bottomley et al., Estimation of the burden of active and life-time epilepsy: a meta-analytic approach. Epilepsia 51, 883–890 (2010)
V.P. Nigam, D. Graupe, A neural-network-based detection of epilepsy. Neurol. Res. 26(1), 55–60 (2004)
C. Park, G. Choi et al., Epileptic seizure detection for multi-channel EEG with deep convolutional neural network, in Proceedings of International Conference on Electronics, Information and Communication (ICEIC) (2018), pp. 1–5
K. Polat, S. Gunes, Classification of epileptiform EEG using a hybrid system based on decision tree classifier and fast Fourier transform. Appl. Math. Comput. 187(2), 1017–1026 (2007)
S. Ramakrishnan, A.S. Muthanantha Murugavel, Epileptic seizure detection using fuzzy rules based sub-band specific features and layered multi-class SVM. Pattern Anal. Appl. 22(3), 1161–1176 (2018)
M. Sameer, B. Gupta, Detection of epileptical seizures based on alpha band statistical features. Wirel. Pers. Commun. 115(2), 909–925 (2020)
R.R. Sharma, R.B. Pachori, Time–frequency representation using IEVDHM–HT with application to classification of epileptic EEG signals. IET Sci. Meas. Technol. 12(1), 72–82 (2017)
R.R. Sharma, P. Varshney, R.B. Pachori, S.K. Vishvakarma, Automated system for epileptic EEG detection using iterative filtering. IEEE Sens. Lett. 2(4), 1–4 (2018)
A. Sharmila, P. Geethanjali, DWT Based detection of epileptic seizure from EEG signals using Naive Bayes and k-NN classifiers. IEEE Access 4, 7716–7727 (2016)
V. Srinivasan, C. Eswaran, A.N. Sriraam, Artificial neural network based epileptic detection using time-domain and frequency-domain features. J. Med. Syst. 29(6), 647–660 (2005)
A. Subasi, EEG signal classification using wavelet feature extraction and a mixture of expert model. Expert Syst. Appl. 32(4), 1084–1093 (2007)
H. Tao, J. Li, Y. Chen, V. Stojanovic, H. Yang, Robust point-to-point iterative learning control with trial-varying initial conditions. IET Control Theory Appl. 14(19), 3344–3350 (2020). https://doi.org/10.1049/iet-cta.2020.0557
O. Tsinalis, P.M. Matthews et al., Automatic sleep stage scoring with single-channel EEG using convolutional neural networks. eprint arXiv:1610.01683
A.T. Tzallas, M.G. Tsipouras, D.I. Fotiadis, Epileptic seizure detection in EEGs using time–frequency analysis. IEEE Trans. Inf. Technol. Biomed. 13(5), 703–710 (2009)
G. Wang, Z. Deng, K.S. Choi, Detection of epilepsy with Electroencephalogram using rule-based classifiers. Neurocomputing 228, 283–290 (2017)
T. Wei, X. Li, V. Stojanovic, Input-to-state stability of impulsive reaction–diffusion neural networks with infinite distributed delays. Nonlinear Dyn. 103, 1733–1755 (2021)
Institute of Medical Biometry, Informatics and Epidemiology of the "Medizinische Einrichtungen der Universität Bonn”. http://www.meb.uni-bonn.de/epileptology/science/physik/eeg.data.html
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Ethical Approval
This article does not contain any studies with human participants or animals performed by any of the authors.
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
Beeraka, S.M., Kumar, A., Sameer, M. et al. Accuracy Enhancement of Epileptic Seizure Detection: A Deep Learning Approach with Hardware Realization of STFT. Circuits Syst Signal Process 41, 461–484 (2022). https://doi.org/10.1007/s00034-021-01789-4
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00034-021-01789-4