Unsupervised feature learning based on autoencoder for epileptic seizures prediction

被引:0
|
作者
Peng He
Linhai Wang
Yaping Cui
Ruyan Wang
Dapeng Wu
机构
[1] Chongqing University of Posts and Telecommunications,School of Communication and Information Engineering
[2] Advanced Network and Intelligent Connection Technology Key Laboratory of Chongqing Education Commission of China,undefined
[3] Chongqing Key Laboratory of Ubiquitous Sensing and Networking,undefined
来源
Applied Intelligence | 2023年 / 53卷
关键词
Seizures prediction; Feature extraction; Unsupervised learning; Residual learning; Data augmentation;
D O I
暂无
中图分类号
学科分类号
摘要
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.
引用
收藏
页码:20766 / 20784
页数:18
相关论文
共 50 条
  • [21] AUTOENCODER INSPIRED UNSUPERVISED FEATURE SELECTION
    Han, Kai
    Wang, Yunhe
    Zhang, Chao
    Li, Chao
    Xu, Chao
    2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2018, : 2941 - 2945
  • [22] Unsupervised feature engineering algorithm BioSAE based on sparse autoencoder
    Zhou F.-F.
    Zhang Y.-C.
    Jilin Daxue Xuebao (Gongxueban)/Journal of Jilin University (Engineering and Technology Edition), 2022, 52 (07): : 1645 - 1656
  • [23] Data-driven electrophysiological feature based on deep learning to detect epileptic seizures
    Yamamoto, Shota
    Yanagisawa, Takufumi
    Fukuma, Ryohei
    Oshino, Satoru
    Tani, Naoki
    Khoo, Hui Ming
    Edakawa, Kohtaroh
    Kobayashi, Maki
    Tanaka, Masataka
    Fujita, Yuya
    Kishima, Haruhiko
    JOURNAL OF NEURAL ENGINEERING, 2021, 18 (05)
  • [24] Graph Regularized Autoencoder-Based Unsupervised Feature Selection
    Feng, Siwei
    Duarte, Marco F.
    2018 CONFERENCE RECORD OF 52ND ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS, AND COMPUTERS, 2018, : 55 - 59
  • [25] ON THE PREDICTION OF EPILEPTIC SEIZURES
    ROGOWSKI, Z
    GATH, I
    BENTAL, E
    BIOLOGICAL CYBERNETICS, 1981, 42 (01) : 9 - 15
  • [26] Prediction of epileptic seizures
    Litt, B
    Echauz, J
    LANCET NEUROLOGY, 2002, 1 (01): : 22 - 30
  • [27] Prediction of epileptic seizures
    Schulze-Bonhage, A.
    NERVENHEILKUNDE, 2008, 27 (05) : 421 - 424
  • [28] ContrastNet: Unsupervised feature learning by autoencoder and prototypical contrastive learning for hyperspectral imagery classification
    Cao, Zeyu
    Li, Xiaorun
    Feng, Yueming
    Chen, Shuhan
    Xia, Chaoqun
    Zhao, Liaoying
    NEUROCOMPUTING, 2021, 460 : 71 - 83
  • [29] Unsupervised feature extraction with convolutional autoencoder with application to daily stock market prediction
    Xie, Li
    Yu, Sheng
    CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE, 2021, 33 (16):
  • [30] Robust autoencoder feature selector for unsupervised feature selection
    Ling, Yunzhi
    Nie, Feiping
    Yu, Weizhong
    Ling, Yunhao
    Li, Xuelong
    INFORMATION SCIENCES, 2024, 660