FLANet: A multiscale temporal convolution and spatial-spectral attention network for EEG artifact removal with adversarial training

计算机科学 降噪 人工智能 工件(错误) 噪音(视频) 卷积(计算机科学) 滤波器(信号处理) 模式识别(心理学) 信号处理 人工神经网络 信号(编程语言) 深度学习 机器学习 计算机视觉 图像(数学) 数字信号处理 计算机硬件 程序设计语言
作者
Junkongshuai Wang,Yangjie Luo,Haoran Wang,Lu Wang,Lihua Zhang,Zhongxue Gan,Xiaoyang Kang
出处
期刊:Journal of Neural Engineering [IOP Publishing]
卷期号:22 (1): 016021-016021
标识
DOI:10.1088/1741-2552/adae34
摘要

Abstract Objective. Denoising artifacts, such as noise from muscle or cardiac activity, is a crucial and ubiquitous concern in neurophysiological signal processing, particularly for enhancing the signal-to-noise ratio in electroencephalograph (EEG) analysis. Novel methods based on deep learning demonstrate a notably prominent effect compared to traditional denoising approaches. However, those still suffer from certain limitations. Some methods often neglect the multi-domain characteristics of the artifact signal. Even among those that do consider these, there are deficiencies in terms of efficiency, effectiveness and computation cost. Approach. In this study, we propose a multiscale temporal convolution and spatial-spectral attention network with adversarial training for automatically filtering artifacts, named filter artifacts network (FLANet). The multiscale convolution module can extract sufficient temporal information and the spatial-spectral attention network can extract not only non-local similarity but also spectral dependencies. To make data denoising more efficient and accurate, we adopt adversarial training with novel loss functions to generate outputs that are closer to pure signals. Main results. The results show that the method proposed in this paper achieves great performance in artifact removal and valid information preservation on EEG signals contaminated by different types of artifacts. This approach enables a more optimal trade-off between denoising efficacy and computational overhead. Significance. The proposed artifact removal framework facilitates the implementation of an efficient denoising method, contributing to the advancement of neural analysis and neural engineering, and can be expected to be applied to clinical research and to realize novel human-computer interaction systems.

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
Yxian完成签到,获得积分10
刚刚
徐泽澄发布了新的文献求助10
刚刚
王明初发布了新的文献求助10
刚刚
1秒前
liaoyoujiao发布了新的文献求助10
1秒前
顺利的盈发布了新的文献求助10
2秒前
FashionBoy应助马宝强采纳,获得10
3秒前
nn发布了新的文献求助10
3秒前
酷波er应助zjh采纳,获得10
4秒前
4秒前
4秒前
5秒前
KINGMach完成签到,获得积分10
5秒前
小乌龟发布了新的文献求助10
5秒前
鲁鲁发布了新的文献求助50
6秒前
牛马发布了新的文献求助10
7秒前
7秒前
淡淡的豁完成签到,获得积分0
7秒前
7秒前
NexusExplorer应助等待小笼包采纳,获得10
7秒前
小罗卜完成签到,获得积分20
7秒前
WY发布了新的文献求助10
8秒前
泡泡yu完成签到,获得积分20
8秒前
荧荧发布了新的文献求助20
8秒前
9秒前
打打应助hyx采纳,获得10
9秒前
10秒前
LL完成签到,获得积分10
11秒前
11秒前
闪闪新梅发布了新的文献求助50
11秒前
香蕉觅云应助jj采纳,获得10
12秒前
12秒前
ZDSHI应助优秀画板采纳,获得10
12秒前
14秒前
14秒前
Zoe发布了新的文献求助10
14秒前
离蒲发布了新的文献求助20
16秒前
allin发布了新的文献求助10
16秒前
一路向北发布了新的文献求助10
16秒前
司藤完成签到 ,获得积分10
17秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
Handbook of pharmaceutical excipients, Ninth edition 5000
Aerospace Standards Index - 2026 ASIN2026 3000
Signals, Systems, and Signal Processing 610
Discrete-Time Signals and Systems 610
Research Methods for Business: A Skill Building Approach, 9th Edition 500
Social Work and Social Welfare: An Invitation(7th Edition) 410
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 纳米技术 有机化学 物理 生物化学 化学工程 计算机科学 复合材料 内科学 催化作用 光电子学 物理化学 电极 冶金 遗传学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 6055624
求助须知:如何正确求助?哪些是违规求助? 7883853
关于积分的说明 16287936
捐赠科研通 5200915
什么是DOI,文献DOI怎么找? 2782839
邀请新用户注册赠送积分活动 1765716
关于科研通互助平台的介绍 1646646