基于深度学习的SeizureNet：突破癫痫发作自动检测

需积分: 10 79 浏览量更新于2024-08-24 收藏 945KB PDF 举报

"《脑电图排名第一算法.pdf》一文是由人工智能领域的知名教授指导完成的研究成果，主要关注于精准医学和人工智能在癫痫发作检测中的应用。文章的核心内容围绕一个名为SeizureNet的创新模型展开，该模型旨在通过卷积神经网络（Convolutional Neural Network, CNN）对单通道脑电图（Electroencephalogram, EEG）信号进行分析，以实现更高效、准确的癫痫发作自动检测。首先，SeizureNet采用了两个CNN层，它们的作用是提取时间不变的特征。这种设计使得模型能够捕捉到EEG信号中的模式和动态变化，即使在不同时间点也能保持较高的识别一致性。这两个CNN层通过对EEG信号的多次卷积和池化操作，有效地减小了数据维度，同时保留了重要的特征信息。接下来，论文介绍了一个全连接层，它用于学习高级别的特征表示。全连接层可以将先前CNN层提取的局部特征映射到一个全局的、抽象的特征空间，从而更好地理解和区分癫痫与非癫痫状态。这个过程利用了深度学习的强大能力，能够从大量数据中自动学习复杂的特征组合。然而，传统方法在处理癫痫发作检测时存在局限性，尽管在某些特定的EEG分类问题上表现出色，但在其他情况下性能欠佳。SeizureNet的设计目标正是为了克服这些不足，通过集成深度学习的优势，提供一种更为通用且鲁棒的解决方案。相比于传统方法，SeizureNet可能在准确性、泛化能力和处理复杂数据的能力上有所提升，这对于临床医生和癫痫患者来说具有显著的实际意义。总结来说，《脑电图排名第一算法.pdf》这篇论文不仅介绍了SeizureNet模型的构建细节，还展示了其在解决癫痫发作自动检测难题上的潜力，对于推动精准医学领域，特别是利用人工智能技术进行个性化诊断和治疗具有重要的学术价值和实践指导作用。"

SeizureNet: a model for robust detection of epileptic seizures using EEG

signals based on convolutional neural network

Wei Zhao

, Wenfeng Wang

Chengyi University College, Jimei University, Jimei Ave 199, Xiamen, People's Republic of China

School of Electronic and Electrical Engineering, Shanghai Institute of Technology, Haiquan Road 100,

Shanghai, People's Republic of China

Email: wangwenfeng@nimte.ac.cn

Abstract: The epilepsy is a neurological disorder and generally detected by electroencephalogram (EEG) signals. The manual

inspection of epileptic seizures is a time-consuming and laborious process. Extensive automatic detection algorithms were

proposed by using traditional approaches, which show good accuracy for several specific EEG classification problems but

perform poorly in others. To address this issue, we present a novel model, named SeizureNet, for robust detection of epileptic

seizures using EEG signals based on convolutional neural network. Firstly, we utilize two CNNs to extract time-invariant

features from single-channel EEG signals. Then, a fully connected layer is employed to learn high-level features. Finally, these

features are supplied to a softmax layer to classify. We evaluated the model on a benchmark database provided by the

University of Bonn and adopted a ten-fold cross-validation approach. The proposed model has achieved the accuracy of

98.50%~100.00% in classifying non-seizure and seizure, 97.00%~99.00% in classifying healthy, inter-ictal and ictal, and 95.84%

in classifying among five-class EEG states.

1. Introduction

Epileptic seizures are caused by a disturbance in the

electrical activity of the brain. Electroencephalogram (EEG)

is an electrophysiological monitoring method to record the

electrical activity of the brain. The EEG is the prime signal

that has been widely used for detecting epilepsy [1-3]. The

visual inspection of EEG is a time-consuming and laborious

process. Hence, automatic EEG signal analysis for clinical

screening is necessary for the diagnosis of epilepsy.

Recently, numerous research work has been carried

out to automatic detection of epileptic seizures using EEG

signals and evaluated on the University of Bonn EEG

dataset, a widely used benchmark database for seizure

recognition. The published work related to EEG-based

epileptic seizure detection mainly involves three

classification problems: two-class classification, three-class

classification, and five-class classification. The details will

be introduced in later section. The approaches fall into two

major groups: traditional methods and deep learning

methods. Most conventional methods first extract features

from raw EEG and then fed to the classifier for

classification. The feature exaction techniques contain

Fourier transform (FT) [4-5], discrete wavelet transform

(DWT) [6-10], approximate entropy (ApEn), [7, 9], Tsallis

entropy [11], local mean decomposition (LMD) [12],

tunable-Q wavelet transform (TQWT) [13] and so on.

Besides, several methods use multiple feature extraction

techniques. Such as Bhattacharyya et al. [13] utilized

TQWT and k-nearest neighbor entropy (KNNE) to exact the

features of EEG. The commonly used classifier involves the

artificial neural network (ANN) [9], decision trees (DT) [4],

k-nearest neighbor (KNN) [10], support vector machine

(SVM) [8] and so on. Also, many techniques adopted an

optimized classifier for classification. For example, Zhang et

al. [11] employed SVM optimized by genetic algorithm

(GA-SVM) for classification.

The performance of these traditional techniques

depends on handwrought feature extractors, as well as

selected classifiers. To address this issue, many approaches

based on deep learning technology were proposed. Such as

Petrosian et al. [15] applied recurrent neural networks (RNN)

combined with signal wavelet decomposition to learn

temporal patterns for epileptic seizure detection. Lin et al.

[16] proposed a deep learning framework based on stacked

sparse autoencoder (SSAE) to learn the sparse and high-

level representations of EEG signals. Hussein et al. [1]

developed an optimized deep neural network based on long

short-term memory (LSTM) to learn the temporal

dependencies in EEG data for the robust detection of

epileptic seizures.

Epilepsy detection based on convolutional neural

networks (CNN) has also attracted much attention. Acharya

et al. [17] implemented a 13-layer deep CNN algorithm to

detect normal, preictal, and seizure classes. Liu et al. [18]

also developed their models based on CNN, which show

good accuracy for two-class classification but perform

poorly for three-class classification. Besides, Zhao et al. [19]

designed a model based on CNN, which consists of three

convolutional blocks and three fully-connected (FC) layers.

And each convolutional block composes of five types of

layers. They achieved good experimental results on two-

class and three-class classifications.

Besides, several approaches that combine CNN with

traditional technologies have been proposed for seizure

detection. Ullah et al. [2] implemented a system that is an

ensemble of pyramidal one-dimensional CNN models,

which combined CNN with a majority vote (MV). San-

Segundo et al. [20] presented a model based on FT and

CNN. Gao et al. [21] proposed a method based on ApEn,

recurrence quantification analysis (RQA), and CNN. Türk et

al. [22] obtained two-dimensional (2D) frequency-time

scalograms of EEG records by using continuous wavelet

transform (CWT), then fed into CNN.

下载后可阅读完整内容，剩余5页未读，立即下载

kindwang1979

粉丝: 0
资源: 5

基于深度学习的SeizureNet：突破癫痫发作自动检测

小波变换.pdf

dtss_review.pdf

Optimizing Spatial Filters for Robust.pdf

FFT分析仪的发展历程借鉴.pdf

浅谈数据挖掘——以医学为例.pdf

基于3D卷积神经网络的IR-BCI脑电视频解码研究.pdf

基于SVM多分类技术的肌电辅助脑电智能轮椅控制系统.pdf

2018 MICCAI 第1卷.rar

search.rar_PDF_

2018 MICCAI 第四卷.rar

最新资源