Unsupervised feature learning based on autoencoder for epileptic seizures prediction | Applied Intelligence Skip to main content
Springer Nature Link
Log in

Unsupervised feature learning based on autoencoder for epileptic seizures prediction

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

Epilepsy is one of the most common neurological diseases in the world. It’s essential to predict epileptic seizures since it can provide patients with enough time for timely treatment. Currently, electroencephalogram (EEG) analysis has been adopted as the most popular method of epileptic seizures prediction, of which one key element is extracting important EEG features. Conventional technologies of EEG analysis mostly utilize supervised learning methods with a mass of labeled data, which bring leakage risks to healthcare data. In addition, it’s difficult to achieve high accuracy of epileptic seizure prediction based on unsupervised learning methods with huge network parameters. Furthermore, the insufficiency of preictal data leads to overfitting challenges for deep learning algorithms. To deal with this problem, a data augmentation method based on randomly translation strategy is proposed to address the insufficient datasets without additional noise. In this paper, we propose an improved unsupervised feature learning method, residual convolution variational autoencoder with randomly translation strategy (RTS-RCVAE). Residual learning is embedded in the VAE model, which improves the model’s ability to converge in the unsupervised learning stage and reduces the loss of useful information. The proposed model is trained and verified via simulation using the public dataset CHB-MIT. The results indicate that the proposed model achieves a high accuracy rate of 98.43% and a false alarm rate of 0.009.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
¥17,985 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price includes VAT (Japan)

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

Data Availability

We evaluate our method on the public CHBMIT dataset, which is available at https://physionet.org/content/chbmit/1.0.0/.

References

  1. Fisher RS, Acevedo C, Arzimanoglou A et al (2014) ILAE Official report: a practical clinical definition of epilepsy. Epilepsia 55(4):475C482

    Article  Google Scholar 

  2. Assi EB, Nguyen DK, Rihana S et al (2017) Towards accurate prediction of epileptic seizures: a review[J]. Biomed Signal Process Control 34:144–157

    Article  Google Scholar 

  3. Qadri YA, Nauman A, Zikria YB et al (2020) The future of healthcare internet of things: a survey of emerging technologies[J]. IEEE Commun Surv Tutor 22(2):1121–1167

    Article  Google Scholar 

  4. Lammie C, Xiang W, Azghadi MR (2021) Towards memristive deep learning systems for Real-Time mobile epileptic seizure prediction. IEEE International Symposium on Circuits and Systems (ISCAS) 2021:1–5. https://doi.org/10.1109/ISCAS51556.2021.9401080

    Google Scholar 

  5. Hu D, Cao J, Lai X et al (2020) Epileptic state classification by fusing hand-crafted and deep learning EEG features[J]. IEEE Trans Circuits Syst II: Express Br 68(4):1542–1546

    Google Scholar 

  6. Ma M, Cheng Y, Wang Y et al (2021) Early prediction of epileptic seizure based on the BNLSTM-CASA Model[J]. IEEE Access 9:79600–79610

    Article  Google Scholar 

  7. Daoud H, Bayoumi MA (2019) Efficient epileptic seizure prediction based on deep learning[J]. IEEE Trans Biomed Circuit Syst 13(5):804–813

    Article  Google Scholar 

  8. Rasheed K, Qayyum A, Qadir J et al (2020) Machine learning for predicting epileptic seizures using EEG signals: A review[J]. IEEE Rev Biomed Eng 14:139–155

    Article  Google Scholar 

  9. El Halabi N, Daou RAZ, Achkar R et al (2020) Comparative study for classification methods to predict and detect epilepsy seizure[C]. In: 2020 IEEE 5th Middle East and Africa Conference on Biomedical Engineering (MECBME). IEEE, pp 1–6

  10. Bhattacharyya A, Pachori RB, Upadhyay A et al (2017) Tunable-Q wavelet transform based multiscale entropy measure for automated classification of epileptic EEG signals[J]. Appl Sci 7(4):385

    Article  Google Scholar 

  11. Sharma M, Pachori RB, Acharya UR (2017) A new approach to characterize epileptic seizures using analytic time-frequency flexible wavelet transform and fractal dimension[J]. Pattern Recognit Lett 94:172–179

    Article  Google Scholar 

  12. Wijayanto I, Hartanto R, Nugroho HA (2020) Complexity Based Multilevel Signal Analysis for Epileptic Seizure Detection[C]. In: 2020 3rd International Conference on Information and Communications Technology (ICOIACT). IEEE, pp 388–393

  13. Hussein R, Ahmed MO, Ward R et al (2019) Human intracranial EEG quantitative analysis and automatic feature learning for epileptic seizure prediction[J]

  14. Birjandtalab J, Pouyan MB, Cogan D et al (2017) Automated seizure detection using limited-channel EEG and non-linear dimension reduction[J]. Comput Biol Med 82:49–58

    Article  Google Scholar 

  15. Khan H, Marcuse L, Fields M et al (2017) Focal onset seizure prediction using convolutional networks[J]. IEEE Trans Biomed Eng 65(9):2109–2118

    Article  Google Scholar 

  16. Abdelhameed AM, Daoud HG, Bayoumi M (2018) Deep convolutional bidirectional LSTM recurrent neural network for epileptic seizure detection[C]. In: 2018 16th IEEE International New Circuits and Systems Conference (NEWCAS). IEEE, pp 139–143

  17. Qayyum A, Qadir J, Bilal M et al (2020) Secure and robust machine learning for healthcare: A survey[J]. IEEE Rev Biomed Eng 14:156–180

    Article  Google Scholar 

  18. Sahani M, Rout SK, Dash PK (2021) Epileptic seizure recognition using reduced deep convolutional stack autoencoder and improved kernel RVFLN from EEG signals[J]. IEEE Trans Biomed Circuit Syst 15 (3):595–605

    Article  Google Scholar 

  19. Abdelhameed AM, Bayoumi M (2018) Semi-supervised deep learning system for epileptic seizures onset prediction[C]. In: 2018 17th IEEE international conference on machine learning and applications (ICMLA). IEEE, pp 1186–1191

  20. Qiu Y, Zhou W, Yu N et al (2018) Denoising sparse autoencoder-based ictal EEG classification[J]. IEEE Trans Neural Syst Rehabilitation Eng 26(9):1717–1726

    Article  Google Scholar 

  21. Abdelhameed AM, Bayoumi M (2019) Semi-supervised EEG signals classification system for epileptic seizure detection[J]. IEEE Signal Process Lett 26(12):1922–1926

    Article  Google Scholar 

  22. Daoud H, Bayoumi M (2019) Deep learning approach for epileptic focus localization[J]. IEEE Trans Biomed Circuits Syst 14(2):209–220

    Article  Google Scholar 

  23. Li Y, Zhang XR, Zhang B et al (2019) A channel-projection mixed-scale convolutional neural network for motor imagery EEG decoding[J]. IEEE Trans Neural Syst Rehabilitation Eng 27(6):1170–1180

    Article  MathSciNet  Google Scholar 

  24. Xu Y, Yang J, Sawan M (2022) Multichannel synthetic preictal EEG signals to enhance the prediction of epileptic seizures[J]. IEEE Trans Biomed Eng

  25. Rasheed K, Qadir J, OBrien TJ et al (2021) A generative model to synthesize eeg data for epileptic seizure prediction[J]. IEEE Trans Neural Syst Rehabilitation Eng 29:2322–2332

    Article  Google Scholar 

  26. Fahimi F, Dosen S, Ang KK et al (2020) Generative adversarial networks-based data augmentation for brainCcomputer interface[J]. IEEE Trans Neural Netw Learn Syst 32(9):4039–4051

    Article  Google Scholar 

  27. Yu J, Zhou X (2020) One-dimensional residual convolutional autoencoder based feature learning for gearbox fault diagnosis[J]. IEEE Trans Industr Inform 16(10):6347–6358

    Article  Google Scholar 

  28. Wang Y, Ma Y, Jin R et al (2020) Comprehensive criteria-based generalized Steganalysis feature selection method[J]. IEEE Access 8:154418–154435

    Article  Google Scholar 

  29. Acharya UR, Fujita H, Sudarshan VK et al (2015) Application of entropies for automated diagnosis of epilepsy using EEG signals: A review[J]. Knowl Based Syst 88:85–96

    Article  Google Scholar 

  30. Kang JS, Kavuri S, Lee M (2019) ICA-evolution based data augmentation with ensemble deep neural networks using time and frequency kernels for emotion recognition from EEG-data[J]. IEEE Trans Affect Comput 13(2):616–627

    Article  Google Scholar 

  31. Wang R, Wang L, He P et al (2022) Epileptic Seizures Prediction Based on Unsupervised Learning for Feature Extraction[C]. In: ICC 2022-IEEE International conference on communications. IEEE, pp 4643–4648

  32. Natarajan K, Acharya UR, Alias F et al (2004) Nonlinear analysis of EEG signals at different mental states[J]. Biomed Eng Online 3(1):1–11

    Article  Google Scholar 

  33. Polat K et al (2007) Classification of epileptiform EEG using a hybrid system based on decision tree classifier and fast Fourier transform[J]. Appl Math Comput 187(2):1017–1026

    MathSciNet  MATH  Google Scholar 

  34. Vo K, Vishwanath M, Srinivasan R et al (2022) Composing Graphical Models with Generative Adversarial Networks for EEG Signal Modeling[C]. In: ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, pp 1231–1235

  35. Truong ND, Kuhlmann L, Bonyadi MR et al (2019) Epileptic seizure forecasting with generative adversarial networks[J]. IEEE Access 7:143999–144009

    Article  Google Scholar 

  36. Zhang D, Stewart E, Ye J et al (2019) Roller bearing degradation assessment based on a deep MLP convolution neural network considering outlier regions[J]. IEEE Trans Instrum Meas 69(6):2996–3004

    Article  Google Scholar 

  37. Geng D, Chen ZS (2021) Auxiliary classifier generative adversarial network for interictal epileptiform discharge modeling and EEG data augmentation[C]. In: 2021 10th International IEEE/EMBS Conference on Neural Engineering (NER). IEEE, pp 1130–1133

  38. Pascual D, Amirshahi A, Aminifar A et al (2020) Epilepsygan: Synthetic epileptic brain activities with privacy preservation[J]. IEEE Trans Biomed Eng 68(8):2435–2446

    Article  Google Scholar 

  39. Lee MB, Kim YH, Park KR (2019) Conditional generative adversarial network-based data augmentation for enhancement of iris recognition accuracy[J]. IEEE Access 7:122134–122152

    Article  Google Scholar 

  40. Moharm K, Eltahan M, Elsaadany E (2020) Wind Speed Forecast using LSTM and Bi-LSTM Algorithms over Gabal El-Zayt Wind Farm[C]. In: 2020 International Conference on Smart Grids and Energy Systems (SGES). IEEE, pp 922–927

  41. Wang Y, Ma Y, Jin R et al (2020) Comprehensive criteria-based generalized steganalysis feature selection method[J]. IEEE Access 8:154418–154435

    Article  Google Scholar 

  42. Al-Amaren A, Ahmad MO, Swamy MNS (2022) A low-complexity residual deep neural network for image edge detection[J]. Appl Intell, pp 1–18

  43. Dissanayake T, Fernando T, Denman S et al (2021) Deep learning for patient-independent epileptic seizure prediction using scalp EEG signals[J]. IEEE Sens J 21(7):9377–9388

    Article  Google Scholar 

  44. Ma M, Cheng Y, Wang Y et al (2021) Early prediction of epileptic seizure based on the BNLSTM-CASA model[J]. IEEE access 9:79600–79610

    Article  Google Scholar 

Download references

Acknowledgements

This work was partially supported by Natural Science Foundation of China (Grant 61901070, 61801065, 61771082, 61871062, U20A20157 and 62061007), in part by the Science and Technology Research Program of Chongqing Municipal Education Commission (Grant KJQN202000603 and KJQN201900611), in part by the Natural Science Foundation of Chongqing (Grant CSTB2022NSCQ-MSX0468, cstc2020jcyjzdxmX0024 and cstc2021jcyjmsxmX0892) and in part by University Innovation Research Group of Chongqing (Grant CxQT20017), in part by Youth Innovation Group Support Program of ICE Discipline of CQUPT (SCIE-QN-2022-04).

Author information

Author notes

    Authors and Affiliations

    1. School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, 400065, China

      Peng He, Linhai Wang, Yaping Cui, Ruyan Wang & Dapeng Wu

    2. Advanced Network and Intelligent Connection Technology Key Laboratory of Chongqing Education Commission of China, Chongqing, 400065, China

      Peng He, Linhai Wang, Yaping Cui, Ruyan Wang & Dapeng Wu

    3. Chongqing Key Laboratory of Ubiquitous Sensing and Networking, Chongqing, 400065, China

      Peng He, Linhai Wang, Yaping Cui, Ruyan Wang & Dapeng Wu

    Authors
    1. Peng He
      View author publications

      You can also search for this author inPubMed Google Scholar

    2. Linhai Wang
      View author publications

      You can also search for this author inPubMed Google Scholar

    3. Yaping Cui
      View author publications

      You can also search for this author inPubMed Google Scholar

    4. Ruyan Wang
      View author publications

      You can also search for this author inPubMed Google Scholar

    5. Dapeng Wu
      View author publications

      You can also search for this author inPubMed Google Scholar

    Corresponding author

    Correspondence to Peng He.

    Ethics declarations

    Conflict of Interests

    The authors declare that they have no competing interests.

    Additional information

    Publisher’s note

    Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

    Linhai Wang, Yaping Cui, Ruyan Wang and Dapeng Wu are contributed equally to this work.

    Rights and permissions

    Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

    Reprints and permissions

    About this article

    Check for updates. Verify currency and authenticity via CrossMark

    Cite this article

    He, P., Wang, L., Cui, Y. et al. Unsupervised feature learning based on autoencoder for epileptic seizures prediction. Appl Intell 53, 20766–20784 (2023). https://doi.org/10.1007/s10489-023-04582-9

    Download citation

    • Accepted:

    • Published:

    • Issue Date:

    • DOI: https://doi.org/10.1007/s10489-023-04582-9

    Keywords