Search research articles

关于 JoVE

概览领导团队博客 JoVE 帮助中心

作者

出版流程编辑委员会范围与政策同行评审常见问题投稿

图书馆员

用户评价订阅访问资源图书馆顾问委员会常见问题

研究

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

相关概念视频

Seizures: Classification

Seizures: Classification

Epilepsy is primarily characterized by unpredictable seizures, either provoked by an identifiable factor, such as injury or illness, or unprovoked, occurring spontaneously without apparent cause.
Seizures are typically classified into two main categories: focal and generalized seizures.
Focal Seizures
Focal seizures originate from specific regions of the brain. These seizures are further sub-classified into two types:

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序

Same author

DiagPat: An Explainable Language Detection Model Using EEG Signals.

Sensors (Basel, Switzerland)·2026

Same author

A novel and accurate EEG emotion classification model based on multiple attention local binary patterns.

BMC medicine·2026

Same author

Different pattern: a new EEG-based method for mental performance detection.

BMC medical informatics and decision making·2026

Same author

Artificial Intelligence in Renal Imaging: A Multi-Dataset Study for Kidney Disease Classification.

Biomedicines·2026

Same author

PyramidPat explainable feature engineering for multiclass electroencephalography psychiatric disorders: Explainable feature engineering and classification.

Psychiatry research·2026

Same author

Operational Transformer: An investigation of epilepsy detection.

Brain topography·2026

Search research articles

相关实验视频

Updated: Jun 25, 2026

Application of an Amplitude-integrated EEG Monitor Cerebral Function Monitor to Neonates

Application of an Amplitude-integrated EEG Monitor Cerebral Function Monitor to Neonates

Published on: September 6, 2017

基于TATPat的可解释EEG模型用于新生儿发作检测.

Turker Tuncer¹, Sengul Dogan², Irem Tasci³

¹Department of Digital Forensics Engineering, College of Technology, Firat University, 23119, Elazig, Turkey.

Scientific reports

|November 4, 2024

概括

本研究介绍了一种可解释特征工程 (EFE) 模型,用于从脑电图 (EEG) 信号中检测新生儿发作. 该模型实现了高准确度,通过定向游说 (DLob) 提供了对发作原因的见解.

关键词:

因果连接原子理论是因果连接的.在 DLobV2 中使用.电脑电图信号分类电脑电图信号分类新生儿发作检测检测新生儿发作检测这就是TATPat.

更多相关视频

Continuous Video Electroencephalogram during Hypoxia-Ischemia in Neonatal Mice

Continuous Video Electroencephalogram during Hypoxia-Ischemia in Neonatal Mice

Published on: June 11, 2020

Multi-system Monitoring for Identification of Seizures, Arrhythmias and Apnea in Conscious Restrained Rabbits

Multi-system Monitoring for Identification of Seizures, Arrhythmias and Apnea in Conscious Restrained Rabbits

Published on: March 27, 2021

相关实验视频

Last Updated: Jun 25, 2026

Application of an Amplitude-integrated EEG Monitor Cerebral Function Monitor to Neonates

Application of an Amplitude-integrated EEG Monitor Cerebral Function Monitor to Neonates

Published on: September 6, 2017

Continuous Video Electroencephalogram during Hypoxia-Ischemia in Neonatal Mice

Continuous Video Electroencephalogram during Hypoxia-Ischemia in Neonatal Mice

Published on: June 11, 2020

Multi-system Monitoring for Identification of Seizures, Arrhythmias and Apnea in Conscious Restrained Rabbits

Multi-system Monitoring for Identification of Seizures, Arrhythmias and Apnea in Conscious Restrained Rabbits

Published on: March 27, 2021

科学领域:

神经科学是一个神经科学.
机器学习机器学习
人工智能的人工智能

背景情况:

脑电图 (EEG) 是一种成本效益高的方法来收集大脑数据.
脑电图信号处理对于神经科学和机器学习 (ML) 来说至关重要.
检测新生儿发作对于婴儿健康至关重要.

研究的目的:

使用可解释特征工程 (EFE) 模型检测和解释新生儿发作.
提出一种新的EFE模型,将定向游说 (DLob) 纳入解释性.
以高精度对新生儿EEG信号进行分类,并提供可解释的结果.

主要方法:

开发了一种具有四个阶段的新 EFE 模型:特征提取 (TATPat),特征选择 (CWNCA),可解释结果生成 (DLob/CCT) 和分类 (tSVM).
使用通道变压器和自动机从19通道新生儿EEG数据中提取特征 (TATPat),生成3249个特征.
采用基于累积权重的邻近组件分析 (CWNCA) 来进行特征选择,并使用基于t算法的支持向量机 (tSVM) 来进行分类.

主要成果:

在TATPat特征提取方法中,每个EEG段生成了3249个特征.
该EFE模型在10倍交叉验证 (CV) 时达到99.15%的准确性,在离开一个主体 (LOSO) CV时达到76.37%.
该模型成功生成了DLob字符串,用于解释性发作检测.

结论:

基于TATPat的EFE模型在分类新生儿EEG信号方面表现出强的表现.
拟议的模型对于神经科学中可解释的人工智能 (XAI) 有效.
这种方法为了解和检测新生儿发作提供了有价值的工具.