Modified Atom Search Optimization-based Deep Recurrent Neural Network for epileptic seizure prediction using electroencephalogram signals

• Autorzy: Borhade Ratnaprabha Ravindra , Nagmode Manoj S.

Identyfikatory

DOI

10.1016/j.bbe.2020.10.001

• Języki publikacji: EN

Abstrakty

EN

Context and background: Epilepsy is considered as the common neurological disease in the world. Early prediction of epileptic seizure gained great influence on the epileptic patient's life. Epileptic patients suffer from unpredictable conditions that may occur at any moment. Motivation: Various epileptic seizure prediction methods are introduced for accurately predicting the pre-ictal state of human brain, but to determine the discriminative features poses a major challenge in the medical sector. Hypothesis: Develop a technique for epileptic seizure prediction using electroencephalogram signals that detects the epileptic seizure automatically. Method: In this research, an effective optimization algorithm, named Modified Atom Search Optimization-based Deep Recurrent Neural Network is proposed to perform accurate seizure prediction with less computation time. Here, the Deep Recurrent Neural Network classifier per-forms the seizure prediction using various hidden layers associated in the hierarchy layer based on the optimally selected features. The proposed Modified Atom Search Optimization algorithm is designed using the Squirrel Search Algorithm and Atom Search Optimization. It is worth interesting to note that the proposed Modified Atom Search Optimization-based Deep Recurrent Neural Network performed early and accurate seizure prediction using electroencephalogram signals. Result: The analysis of the proposed SASO-based Deep RNN is carried out using CHB-MIT Scalp EEG dataset using the metrics, namely accuracy, sensitivity, and specificity. The proposed algorithm obtained better performance in terms of specificity, accuracy, and sensitivity with the values of 97.536%, 96.545%, and 96.520% by varying training percentage, and 93.736%, 94.128%, and 96.520% by varying K-fold value. Conclusion: The proposed method has significant benefits like, faster convergence rate, easy to implement, low complexity, high speed, and robustness. The weights of the classifier are optimally trained using the proposed algorithm in order to reveal the effectiveness of prediction performance.

Słowa kluczowe

EN

epileptic seizure; deep recurrent neural network; electroencephalogram signal; atom search optimization; antiepileptic drugs

PL

napad padaczkowy; sieć rekurencyjna; sygnał elektroencefalograficzny; leki przeciwpadaczkowe

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2020
• Tom: Vol. 40, no. 4
• Strony: 1638--1653
• Opis fizyczny: Bibliogr. 39 poz., rys., tab., wykr.

Twórcy

autor

Borhade Ratnaprabha Ravindra

• Department of Electronics and Telecommunication Engineering, Zeal College of Engineering and Research, Pune University, Survey No. 39, Dhayari Narhe Rd, Narhe, Pune, Maharashtra, 411041, India

autor

Nagmode Manoj S.

• Department of Electronics and Telecommunication Engineering, Government College of Engineering and Research, Avsari, Pune, Pune University, Avasari-Khurd, Taluka-Ambegaon, Pune, Maharashtra, India

Bibliografia

• [1] Carney Paul R, Myers Stephen, Geyer James D. Seizure prediction: methods. Epilepsy Behav 2011;22:S94–101.
• [2] Firpi Hiram, Goodman Erik D, Echauz Javier. Epileptic seizure detection using genetically programmed artificial features. IEEE Trans Biomed Eng 2007;54(no. 2, February).
• [3] Mahmoodian Naghmeh, Boeseb Axel, Frieb Michael, Haddadni Javad. Epileptic seizure detection using cross-bispectrum of electroencephalogram signal. Seizure Eur J Epilepsy 2019;66:4–11.
• [4] Kerr MP. The impact of epilepsy on patients' lives. Acta Neurol Scand 2012;126:1–9.
• [5] Liu Chien-Liang, Xiao Bin, Hsaio Wen-Hoar, Tseng Vincent S. Epileptic seizure prediction with multi-view convolutional neural networks. IEEE Access 2019;7:170352–61.
• [6] Daoud Hisham, Bayoumi Magdy. Efficient epileptic seizure prediction based on deep learning. IEEE Trans Biomed Circuits Syst 2019;13(no.5):804–13.
• [7] Lehnertz Klaus, Mormann Florian, Kreuz Thomas, andrzejak Ralph G, Rieke Christoph, David Peter, Elger Christian E. Seizure prediction by nonlinear EEG analysis. IEEE Eng Med Biol Mag 2003;22(no.1):57–63.
• [8] Islam Md Shafiqul, El-Hajj Ahmad M, Alawieh Hussein, Dawy Zaher, Abbas Nabil, El-Imad Jamil. EEG mobility artifact removal for ambulatory epileptic seizureprediction applications. Biomed Signal Process Control 2020;55101638.
• [9] Zheng Tongyi, Luo Weili. An improved squirrel search algorithm for optimization. Complexity 2019.
• [10] Kueh Si Mon, Kazmierski Tom J. Low-power and low-cost dedicated bit-serialhardware neural network for epileptic seizure prediction system. IEEE J Trans Eng Health Med 2018;6:1–9.
• [11] Dasa Khakon, Daschakladar Debashis, Roy Partha Pratim, Chatterjee Atri, Saha Shankar Prasad. Epileptic seizure prediction by the detection of seizure waveform from the pre-ictal phase of EEG signal. Biomed Signal Process Control 2020;57:101720.
• [12] Martisius Ignas, Birvinskas Darius, Damasevicius Robertas, Jusas Vacius. EEG dataset reduction and classification using wave atom transform. Artif Neural Networks Mach Learn 2013;208–15.
• [13] Mihajlović Vojkan, Grundlehner Bernard, Vullers Ruud, Penders Julien. Wearable, wireless EEG solutions in daily life applications: what are we missing? IEEE J Biomed Health Inf 2015;19(no.1):6–21.
• [14] Bhagat Priti N, Ramesh KS, Patil Dr ST. An automatic diagnosis of epileptic seizure based on optimization using Electroencephalography Signals. JCR 2019;6(no.5):200–12.
• [15] Fu Yanming, Li Zhuohang, Qu Chiwen, Chen Haiqiang. Modified atom search optimization based on immunologic mechanism and reinforcement learning. Math Problems Eng 2019;2020.
• [16] Rajendra Acharya U, Molinari Filippo, VinithaSree S, Chattopadhyay Subhagata, Ng Kwan-Hoong, Suri Jasjit S. Automated diagnosis of epileptic EEG using entropies. Biomed Signal Process Control 2012;7:401–8.
• [17] Adeli Hojjat, Zhou Ziqin, Dadmehr Nahid. Analysis of EEG records in an epileptic patient using wavelet transform. J Neurosci Methods 2003;123:69–87.
• [18] Zhang Q, Hu Y, Potter T, Li R, Quach M, Zhang Y. Establishing functional brain networks using a nonlinear partial directed coherence method to predict epileptic seizures. J Neurosci Methods 2020;329:108447.
• [19] Geng M, Zhou W, Liu G, Li C, Zhang Y. Epileptic seizure detection based on stockwell transform and bidirectional long short-term memory. IEEE Trans Neural Syst Rehabil Eng 2020.
• [20] Tang Y, Durand DM. A tunable support vector machine assembly classifier forepileptic seizure detection. Expert Syst Appl 2012;39(no.4):3925–38.
• [21] Kiral-Kornek Isabell, Roy Subhrajit, Nurse Ewan, Mashford Benjamin, Karoly Philippa, Carroll Thomas, Payne Daniel, Saha Susmita, Baldassano Steven, O'Brien Terence, Grayden David, Cook Mark, Freestone Dean, Harrer Stefan. Epileptic seizure prediction using big data and deep learning: toward a mobile system. EBioMedicine 2018;27:103–11.
• [22] Basterrech Sebastian, Kromer Pavel. A nature-inspired biomarker for mental concentration using a single-channel EEG. Neural Comput Appl 2019.
• [23] Usman Syed Muhammad, Usman Muhammad, Fong Simon. Epileptic seizures prediction using machine learning methods. Comput Math Methods Med 2017.
• [24] Sun Chengfa, Cui Hui, Nie Weiwei, Wang Xiuying, Yuan Qi. Epileptic seizure Detection with EEG textural features and imbalanced classification based on easy ensemble learning. Int J Neural Syst 2019. 1950021-1950021.
• [25] Raghu S, Sriraam N, Temel Y, Rao SV, Kubben PL. EEG based multi-class seizure type classification using convolutional neural network and transfer learning. Neural Networks 2020.
• [26] Mafarja Majdi, Aljarah Ibrahim, Faris Hossam, Hammouri Abdelaziz I. Binary grasshopper optimisation algorithm approaches for feature selection problems. Expert Syst Appl 2018.
• [27] Ocak Hasan. Optimal classification of epileptic seizures in EEG using wavelet analysis and genetic algorithm. Signal Process 2008;88(no.7):1858–67.
• [28] Behnam Morteza, Pourghassem Hossein. Real-time seizure prediction using RLS filtering and interpolated histogram feature based on hybrid optimization algorithm of Bayesian classifier and Hunting search. Comput Methods Programs Biomed 2016;132:115–36. August.
• [29] Behnam Morteza, Pourghassem Hossein. Power complexity feature-based seizure prediction using DNN and firefly- BPNN optimization algorithm. 2015 22nd Iranian Conference on Biomedical Engineering; 2016.
• [30] Zainuddin Zarita, Lai Kee Huong, Ong Pauline. An enhanced harmony search based algorithm for feature selection: applications in epileptic seizure detection and prediction. Comput Electr Eng 2016;53:143–62.
• [31] Hosseini Mohammad-Parsa, Pompili Dario, Elisevich Kost, Soltanian-Zadeh Hamid. Optimized deep learning for EEG big data and seizure prediction BCI via internet of things. IEEE Trans Big Data 2017;3(no.4):392–404.
• [32] Detti Paolo, Zabalo Garazi, de Lara Manrique, Bruni Renato, Pranzo Marco, Vatti Francesco Sarnariand Giampaolo. Patient-specific approach for short-term epileptic seizures prediction through the analysis of EEG synchronization. IEEE Trans Biomed Eng 2018;66(no.6):1494–504.
• [33] Hussein Ramy, Palangi Hamid, Ward Rabab K, Jane Wang Z. Optimized deep neural network architecture for robust detection of epileptic seizures using EEG signals. Clin Neurophysiol 2019;130(no.1):25–37.
• [34] Zhao Weiguo, Wang Liying, Zhang Zhenxing. Atom search optimization and its application to solve a hydro geologic parameter estimation problem. Knowledge-Based Syst 2019;163:283–304.
• [35] Jain Mohit, Singh Vijander, Rani Asha. A novel nature-inspired algorithm for optimization: squirrel search algorithm. Swarm Evol Comput 2018;1–28.
• [36] Hong KS, Khan MJ, Hong MJ. Feature extraction and classification methods for hybrid fNIRS-EEG brain-computer interfaces. Front Human Neurosci 2018;12:246.
• [37] Usman SM, Khalid S, Akhtar R, Bortolotto Z, Bashir Z, Qiu H. Using scalp EEG and intracranial EEG signals for predicting epileptic seizures: review of available methodologies. Seizure 2019.
• [38] CHB-MIT Scalp EEG Dataset Taken from, https://physionet.org/content/chbmit/1.0.0/. [Assessed January 2020].
• [39] Ibrahim SW, Djemal R, Alsuwailem A, Gannouni S. Electroencephalography (EEG)-based epileptic seizure prediction using entropy and K-nearest neighbor (KNN). Commun Sci Technol 2017;2(no. 1).