Objective We propose an autoencoder model based on a one-dimensional convolutional neural network (1DCNN) as the feature extraction network for efficient detection of epileptic EEG anomalies. Methods The local information of normal EEG signals was captured by utilizing the local feature extraction ability of 1DCNN for training of an autoencoder to learn the expression of normal EEG data in low dimensional feature space. With the difference between the input and output as the anomaly score, the threshold was determined by the optimal equilibrium point of the ROC curve, and the EEG signals exceeding the threshold were diagnosed as the seizure data. The performance of the 1DCNN-AE epilepsy detection model was evaluated using the publicly available CHB-MIT scalp EEG dataset and TUH scalp EEG dataset. Results The AUC of the 1DCNN-AE model reached 0.890 of CHB-MIT and 0.686 of TUH under the average level of patients, and the epilepsy detection rate reached 0.974 and 0.893, and these results were better than the latest epilepsy anomaly detection models LSTM-VAE and GRU-VAE. The 1DCNN model had a parameter quantity of 58.5M, which was at the same level with LSTM-VAE (47.4 M) and GRU-VAE (36.9 M) but with much smaller FLOPs (0.377 G) than LSTM-VAE (21.6 G) and GRU-VAE (16.2 G). Conclusion The autoencoder model based one-dimensional convolutional neural network can effectively detect abnormal EEG signals in epileptic seizure.
HassanAR, SubasiA. Automatic identification of epileptic seizures from EEG signals using linear programming boosting[J]. Comput Methods Programs Biomed, 2016, 136: 65-77.
[2]
Mian QaisarS, SubasiA. Effective epileptic seizure detection based on the event-driven processing and machine learning for mobile healthcare[J]. J Ambient Intell Humaniz Comput, 2022, 13(7): 3619-31.
[3]
MilliganTA. Epilepsy: a clinical overview[J]. Am J Med, 2021, 134(7): 840-7.
[4]
ShoeibiA, KhodatarsM, GhassemiN, et al. Epileptic seizures detection using deep learning techniques: a review[J]. Int J Environ Res Public Health, 2021, 18(11): 5780.
[5]
ZhangS, LiuGD, XiaoRL, et al. A combination of statistical parameters for epileptic seizure detection and classification using VMD and NLTWSVM[J]. Biocybern Biomed Eng, 2022, 42(1): 258-72.
[6]
Vijay AnandS, Shantha SelvakumariR. Noninvasive method of epileptic detection using DWT and generalized regression neural network[J]. Soft Comput, 2019, 23(8): 2645-53.
[7]
SameerM, GuptaB. Time–frequency statistical features of delta band for detection of epileptic seizures[J]. Wirel Pers Commun, 2022, 122(1): 489-99.
[8]
RiazF, HassanA, RehmanS, et al. EMD-based temporal and spectral features for the classification of EEG signals using supervised learning[J]. IEEE Trans Neural Syst Rehabil Eng, 2016, 24(1): 28-35.
[9]
AcharyaUR, MolinariF, SreeSV, et al. Automated diagnosis of epileptic EEG using entropies[J]. Biomed Signal Process Contr, 2012, 7(4): 401-8.
[10]
XiangJ, LiCG, LiHF, et al. The detection of epileptic seizure signals based on fuzzy entropy[J]. J Neurosci Methods, 2015, 243: 18-25.
[11]
JounyCC, BergeyGK. Characterization of early partial seizure onset: frequency, complexity and entropy[J]. Clin Neurophysiol, 2012, 123(4): 658-69.
[12]
OsowskiS, SwiderskiB, CichockiA, et al. Epileptic seizure characterization by Lyapunov exponent of EEG signal[J]. COMPEL Int J Comput Math Electr Electron Eng, 2007, 26(5): 1276-87.
[13]
SharmaM, PachoriRB, Rajendra AcharyaU. A new approach to characterize epileptic seizures using analytic time-frequency flexible wavelet transform and fractal dimension[J]. Pattern Recognit Lett, 2017, 94: 172-9.
[14]
AarabiA, HeB. Seizure prediction in patients with focal hippocampal epilepsy[J]. Clin Neurophysiol, 2017, 128(7): 1299-307.
[15]
C SKR, M S. A 1-D CNN-FCM model for the classification of epileptic seizure disorders[J]. Neural Comput Appl, 2023, 35(24): 17871-81.
[16]
TianXB, DengZH, YingWH, et al. Deep multi-view feature learning for EEG-based epileptic seizure detection[J]. IEEE Trans Neural Syst Rehabil Eng, 2019, 27(10): 1962-72.
YuJH, GaoX, LiBF, et al. A filter-augmented auto-encoder with learnable normalization for robust multivariate time series anomaly detection[J]. Neural Netw, 2024, 170: 478-93.
[19]
FanJ, LiuZT, WuHF, et al. LUAD: a lightweight unsupervised anomaly detection scheme for multivariate time series data[J]. Neurocomputing, 2023, 557: 126644.
[20]
EnayatiE, MortazaviR, BasiriA, et al. Time series anomaly detection via clustering-based representation[J]. Evol Syst, 2024, 15(4): 1115-36.
[21]
ZhuW, LiWJ, DorseyER, et al. Unsupervised anomaly detection by densely contrastive learning for time series data[J]. Neural Netw, 2023, 168: 450-8.
[22]
EmamiA, KuniiN, MatsuoT, et al. Autoencoding of long-term scalp electroencephalogram to detect epileptic seizure for diagnosis support system[J]. Comput Biol Med, 2019, 110: 227-33.
[23]
YouS, ChoBH, YookS, et al. Unsupervised automatic seizure detection for focal-onset seizures recorded with behind-the-ear EEG using an anomaly-detecting generative adversarial network[J]. Comput Methods Programs Biomed, 2020, 193: 105472.
[24]
YouS, ChoBH, ShonYM, et al. Semi-supervised automatic seizure detection using personalized anomaly detecting variational autoencoder with behind-the-ear EEG[J]. Comput Methods Programs Biomed, 2022, 213: 106542.
SchleglT, SeeböckP, WaldsteinSM, et al. F-AnoGAN: fast unsupervised anomaly detection with generative adversarial networks[J]. Med Image Anal, 2019, 54: 30-44.
[33]
QiuXJ, YanF, LiuHH. A difference attention ResNet-LSTM network for epileptic seizure detection using EEG signal[J]. Biomed Signal Process Contr, 2023, 83: 104652.
[34]
SaichandNV, Gopiya NaikS. Epileptic seizure detection using novel Multilayer LSTM Discriminant Network and dynamic mode Koopman decomposition[J]. Biomed Signal Process Contr, 2021, 68: 102723.
[35]
HuXM, YuanSS, XuFZ, et al. Scalp EEG classification using deep Bi-LSTM network for seizure detection[J]. Comput Biol Med, 2020, 124: 103919.
[36]
ChungJ, GulcehreC, ChoK H,et al.Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling[J].Eprint Arxiv, 2014.DOI:10.48550/arXiv.1412.3555 .