Abstract
Epilepsy is a neurological disorder causing abnormal activities in the brain such as seizures, unusual behavior, sensations and loss of awareness. This disorder can be diagnosed with help of the Electroencephalogram (EEG) which evaluates the electrical activity in the brain, which is considered a dynamical system. The epileptic neuronal networks are made up of complex non-linear structures whose non-linear behavior manifests in the EEG signal. Due to the chaotic and non-linear nature of the EEG signal, we propose the use of Recurrence Plots (RP) to capture the non-linear dynamics in the EEG. Recurrence is a fundamental property of dynamical systems and contains information about the system behavior. The Recurrence Plots are a tool for the visualization and analysis of the dynamic system’s behavior. The ResNet ensemble trained on these Recurrence Plots attains cent percent accuracy in most class combination scenarios such as normal vs epileptic or pre-ictal vs ictal. Likewise, the sensitivity and specificity are also 100% in most class combination scenarios. Such a model can assist in the diagnosis of the disease and can also give an early alert to the patient on the onset of seizure.
Similar content being viewed by others
References
Acharya UR, Sharma M, Pachori RB (2017) A new approach to characterize epileptic seizures using analytic time-frequency flexible wavelet transform and fractal dimension. Pattern Recognit Lett 94:172–179
Acharya UR, Sree SV, Chattopadhyay S, Yu W, Ang PCA (2011) Application of recurrence quantification analysis for the automated identification of epileptic EEG signals. International Journal of Neural Systems 21(03):199–211
Anand RS, Kumar Y, Dewal ML (2014) Epileptic seizures detection in EEG using DWT-based ApEn and artificial neural network. Signal, Image and Video Processing, 2014 - Springer 8(7):1323–1334
Andrzejak R, Lehnertz K, Mormann F, Rieke C, David P, Elger C (2001) Indications of nonlinear deterministic and finite-dimensional structures in time series of brain electrical activity: dependence on recording region and brain state. Physical Review E, Statistical, Nonlinear, and Soft Matter Physics 64:061907
Brenner RJ (2000) False-negative mammograms: medical, legal, and risk management implications. Radiologic Clinics of North America 38(4):741–757
Carrington AM, Fieguth PW, Qazi H, Holzinger A, Chen HH, Mayr F, Manuel DG (2020) A new concordant partial AUC and partial c statistic for imbalanced data in the evaluation of machine learning algorithms. BMC Medical Informatics and Decision Making 20(4):1–12
Cole A, Quesney LF, Abou-Khalil B, Olivier A (1988) Pre-operative extracranial and intracranial EEG investigation in patients with temporal lobe epilepsy: trends, results and review of pathophysiologic mechanisms. Acta Neurologica Scandinavica Supplementum 78:61–72
Dias D, Dias U, Menini N, Lamparelli R, Le Maire G, Torres R (2019) Pixelwise remote sensing image classification based on recurrence plot deep features. In: IGARSS 2019-2019 IEEE international geoscience and remote sensing symposium. IEEE, pp 1310–1313
Frid-Adar M, Diamant I, Klang E, Amitai M, Goldberger J, Greenspan H (2017) Modeling the intra-class variability for liver lesion detection using a multi-class patch-based CNN. International Workshop on Patch-based Techniques in Medical Imaging, pp 129–137
Gao X, Yan X, Gao P, Gao X, Zhang S (2020) Automatic detection of epileptic seizure based on approximate entropy, recurrence quantification analysis and convolutional neural networks. Artificial Intelligence in Medicine 102:101711
Goebel R, Chander A, Holzinger K, Lecue F, Akata Z, Stumpf S, Kieseberg P, Holzinger A (2018) Explainable AI: the new 42? International Cross-domain Conference for Machine Learning and Knowledge extraction, pp 295–303
Hatami N, Gavet Y, Debayle J (2018) Classification of time-series images using deep convolutional neural networks. In: Tenth international conference on machine vision (ICMV 2017), vol 10696. International Society for Optics and Photonics, pp 106960Y
Ilakiyaselvan N, Khan AN, Shahina A (2020) Deep learning approach to detect seizure using reconstructed phase space images. J Biomed Res 34(3):240
Kim J, Lee JK, Lee KM (2016) Accurate image super-resolution using very deep convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1646–1654
Kim S, Park S, Lim S, Kim D (2018) Classification performance analysis of weight update method applied to various convnet models. In: 2018 international conference on control and robots (ICCR). IEEE, pp 78–83
Liu L, Chen J, Fieguth P, Zhao G, Chellappa R, Pietikäinen M (2019) From BoW to CNN: two decades of texture representation for texture classification. International Journal of Computer Vision 127(1):74–109
Liu Y, Wang Y, Yu R, Li M, Sharma V, Wang Y (2019) Optimizing CNN model inference on CPUs. In: USENIX annual technical conference (USENIX ATC 19), pp 1025–1040
Ng H-W, Nguyen VD, Vonikakis V, Winkler S (2015) Deep learning for emotion recognition on small datasets using transfer learning. In: Proceedings of the 2015 ACM on international conference on multimodal interaction, pp 443–449
Obeid I, Picone J (2016) The temple university hospital EEG data corpus. Frontiers in Neurosci 10:196
Obot IB, Onyeachu IB, Zeino A, Umoren SA (2019) Electrochemical noise (en) technique: review of recent practical applications to corrosion electrochemistry research. Journal of Adhesion Science and Technology 33(13):1453–1496
Rodriguez-Bermudez G, Garcia-Laencinas PJ (2015) Analysis of EEG signals using nonlinear dynamics and chaos: a review. Applied Mathematics and Information Sciences 9(5):2309–2321
Sammaritano M, de Lotbinière A, Andermann F, Olivier A, Gloor P, Quesney LF (1987) False laterahation by surface EEG of seizure onset in patients with temporal lobe epilepsy and gross focal cerebral lesions. Annals of Neurology 21(4):361–369
Sharmila A, Geethanjali P (2016) DWT based detection of epileptic seizure from EEG signals using naive bayes and k-NN classifiers. IEEE Access 4(4):7716–7727
Stam CJ (2005) Nonlinear dynamical analysis of EEG and MEG: review of an emerging field. Clinical Neuropsychology 116(10):2266–2301
Swami P, Gandhi TK, Panigrahi BK, Tripathi M, Anand S (2016) A novel robust diagnostic model to detect seizures in electroencephalography. Expert System Applications 56:116–130
Torse DA, Khanai R, Desai VV (2019) Classification of epileptic seizures using recurrence plots and machine learning techniques. In: 2019 International conference on communication and signal processing (ICCSP). IEEE, pp 0611–0615
Valente AC, Perez FVM, Megeto GAS, Cascone MH, Gomes O, Paula TS, Lin Q (2019) Comparison of texture retrieval techniques using deep convolutional features. Electronic Imaging 8:406–407
Author information
Authors and Affiliations
Corresponding author
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
Ravi, S., S, S., Shahina, A. et al. Epileptic seizure detection using convolutional neural networks and recurrence plots of EEG signals. Multimed Tools Appl 81, 6585–6598 (2022). https://doi.org/10.1007/s11042-021-11608-2
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-021-11608-2