Scholarlink

Recurrent epileptic seizures are neurological events described by irregular electrical activity in the brain. These seizures can be identified using electroencephalogram (EEG) signals. Accurate detection of seizures is essential for appropriate medical treatment. This paper presents end-to-end approaches to detect seizures from EEG subjects using Conditional Generative Adversarial Network (CGAN) and Optimized Support Vector Machine (O-SVM). The BONN dataset is used to collect EEG subjects in this study. Our developed CGAN-OSVM algorithm attained an accuracy of 96.667%. It is observed that optimizing the hyperparameters significantly improved accuracy. The developed end-to-end models are very robust and effective and helps in automated seizure detection.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A Novel Deep Learning Approach to Detect Seizures in EEG Signal Using Conditional GAN (CGAN) and Optimized SVM (O-SVM)

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Mohebbanaaz,
  • M. Jyothirmai,
  • Venkanna Chanagoni

摘要

Recurrent epileptic seizures are neurological events described by irregular electrical activity in the brain. These seizures can be identified using electroencephalogram (EEG) signals. Accurate detection of seizures is essential for appropriate medical treatment. This paper presents end-to-end approaches to detect seizures from EEG subjects using Conditional Generative Adversarial Network (CGAN) and Optimized Support Vector Machine (O-SVM). The BONN dataset is used to collect EEG subjects in this study. Our developed CGAN-OSVM algorithm attained an accuracy of 96.667%. It is observed that optimizing the hyperparameters significantly improved accuracy. The developed end-to-end models are very robust and effective and helps in automated seizure detection.